Search

Simple Summary: The integration of advanced imaging techniques and radiomics analysis represents a promising direction in thyroid nodule management. Radiomics plays a pivotal role in differentiating between cancerous and benign lesions by offering a deeper, more nuanced analysis of medical images. By quantifying tumor heterogeneity and providing objective, standardized metrics, radiomics captures subtle tissue characteristics that may elude visual inspection. This study aimed to improve the preoperative differentiation of thyroid incidentalomas (TIs) using radiomics analysis on F-18 FDG-PET/CT. Of 960 radiomics features, nine key features were selected using the LASSO algorithm to create a radiomics score. The score demonstrated good predictive performance for identifying malignant thyroid nodules. This model shows promise for aiding in the diagnosis of thyroid cancer. Background/Objectives: Accurate diagnosis is essential to avoid unnecessary procedures for thyroid incidentalomas (TIs). Advances in radiomics and machine learning applied to medical imaging offer promise for assessing thyroid nodules. This study utilized radiomics analysis on F-18 FDG PET/CT to improve preoperative differential diagnosis of TIs. Methods: A total of 152 patient cases were retrospectively analyzed and split into training and validation sets (7:3) using stratification and randomization. Results: The least absolute shrinkage and selection operator (LASSO) algorithm identified nine radiomics features from 960 candidates to construct a radiomics signature predictive of malignancy. Performance of the radiomics score was evaluated using receiver operating characteristic (ROC) analysis and area under the curve (AUC). In the training set, the radiomics score achieved an AUC of 0.794 (95% CI: 0.703–0.885, p < 0.001). Validation was performed on internal and external datasets, yielding AUCs of 0.702 (95% CI: 0.547–0.858, p = 0.011) and 0.668 (95% CI: 0.500–0.838, p = 0.043), respectively. Conclusions: These results demonstrate that the selected nine radiomics features effectively differentiate malignant thyroid nodules. Overall, the radiomics model shows potential as a valuable predictive tool for thyroid cancer in patients with TIs, supporting improved preoperative decision-making. [ABSTRACT FROM AUTHOR]

Simple Summary: Patients diagnosed with estrogen receptor-positive/human epidermal growth factor receptor 2 (HER2)-negative breast cancer may benefit from adjuvant chemotherapy, subject to a risk assessment for relapse. EndoPredict®, a second-generation genomic assay, is widely used to calculate this risk. However, the use of such genomic tests in breast cancer may result in significant economic costs for public healthcare systems. This article presents the development of a predictive nomogram for estimating a high-risk test result based on clinicopathological data from patients who underwent the EndoPredict® test at our center. The objective of this nomogram is to assist clinicians in identifying patients who are most likely to benefit from the test, thereby optimizing its utilization and reducing unnecessary costs. Background/Objectives: The EndoPredict® assay has been widely used in recent years to estimate the risk of distant recurrence and the absolute chemotherapy benefit for patients with estrogen (ER)-positive/human epidermal growth factor receptor 2 (HER2)-negative breast cancer. However, there are no well-defined criteria for selecting patients who may benefit from the test. The aim of this study was to develop a novel nomogram to estimate the probability of obtaining a high-risk EndoPredict® result in clinical practice. Methods: The study cohort comprised 348 cases of T1-3/N0-1a/M0 ER-positive/HER2-negative breast carcinoma. A multivariate analysis was conducted using a training cohort (n = 270) based on clinicopathological features that demonstrated a statistically significant correlation with the EndoPredict® result in a univariate analysis. The predictive model was subsequently represented as a nomogram to estimate the probability of obtaining a high-risk result in the EndoPredict® assay. The predictive model was then validated using a separate validation cohort (n = 78). Results: The clinicopathological features incorporated into the nomogram included tumor size, tumor grade, sentinel lymph node status, pN stage, and Ki67. The internal validation of the model yielded an area under the curve (AUC) of 0.803 (95% CI = 0.751, 0.855) in the receiver operating characteristic (ROC) curve for the training cohort, with an optimal sensitivity and specificity at a threshold of 0.536. The external validation yielded an AUC of 0.789 (95% CI = 0.689, 0.890) in its ROC curve, with optimal sensitivity and specificity achieved at a threshold of 0.393. Conclusions: This study presents, for the first time, the development of a clinically accessible nomogram designed to estimate the probability of obtaining a high-risk result in the EndoPredict® assay. The use of easily available clinicopathological features allows for the optimization of patient selection for the EndoPredict® assay, ensuring that those who would most benefit from undergoing the test are identified. [ABSTRACT FROM AUTHOR]

Simple Summary: Radiotherapy is the primary and only curative treatment for nasopharyngeal carcinoma (NPC). The adoption of intensity-modulated radiotherapy (IMRT) alone or combined with optimized chemotherapeutic strategies has improved survival rates while reducing treatment-related toxicities. However, the persistent tumor status, including residual tumor presence and early recurrence, is the predominant cause of treatment failure, associated with poorer survival outcomes. This study extracted the radiomic features from pretreatment PET images, which were used to construct a prediction model to identify patients with NPC at high risk of having persistent tumors after treatment. The model trained by the AdaBoost algorithm showed significant diagnostic performance in predicting treatment failure. This model exhibited the feasibility of assisting clinicians in identifying high-risk patients before treatment, allowing for more personalized treatment plans and improving patient outcomes. Background/Objectives: The duration of the response to radiotherapy-related treatment is a critical prognostic indicator for patients with nasopharyngeal carcinoma (NPC). Persistent tumor status, including residual tumor presence and early recurrence, is associated with poorer survival outcomes. To address this, we developed a prediction model to identify patients at a high risk of persistent tumor status prior to initiating treatment. Methods: This retrospective study included 104 patients with NPC receiving radiotherapy-related treatment who had completed a 3-year follow-up period; 29 were classified into the persistent tumor status group and 75 into the disease-free group. Radiomic features were extracted from pretreatment positron emission tomography (PET) images and used to construct a prediction model by employing machine learning algorithms. The model's diagnostic performance was assessed using the area under the receiver operating characteristic curve (AUC), whereas SHapley Additive exPlanations (SHAP) analysis was conducted to determine the contribution of individual features to the model. Results: The prediction model developed using the AdaBoost algorithm and validated through five-fold cross-validation achieved the highest AUC of 0.934. Its sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 89.66%, 86.67%, 72.22%, 95.59%, and 87.5%, respectively. SHAP analysis revealed that the feature of high dependence low metabolic uptake emphasis50 had the greatest impact on model predictions. Furthermore, patients classified as disease-free exhibited markedly higher overall survival rates compared with those with persistent tumor status. Conclusions: In conclusion, the proposed prediction model efficiently identified patients with NPC at a high risk of persistent tumor status by using radiomic features extracted from pretreatment PET images. [ABSTRACT FROM AUTHOR]

Simple Summary: Gastric cancer (GC) affects more than one million and is the fifth most frequently diagnosed cancer and the fourth leading cause of cancer death worldwide. Past studies have usually focused on a limited number of clinical or demographic factors to predict GC prognosis. In contrast, we used twenty-four features, including demographic, laboratory, clinical, and socio-economic information, to predict GC mortality. We investigated two case groups divided by cause of mortality (all-cause and disease-specific) with the construction of six machine learning (ML) models. In addition, the Shapley Additive Explanation (SHAP) method, an explainable artificial intelligence technique, was used. This approach allows us to identify and interpret the key features that have a significant impact on GC mortality. Key predictors of the mortality classification model included occurrence in other organs, age at diagnosis, AJCC7 stage, tumor size, CEA, smoking, and CA19-9. Accurate prediction of mortality and detection of risk factors for GC based on ML might provide opportunities for appropriate therapeutic interventions and decision-making. Background/Objectives: Gastric cancer is a leading cause of cancer-related mortality, particularly in East Asia, with a notable burden in Republic of Korea. This study aimed to construct and develop machine learning models for the prediction of gastric cancer mortality and the identification of risk factors. Methods: All data were acquired from the Korean Clinical Data Utilization for Research Excellence by multiple medical centers in South Korea. A total of 23,717 gastric cancer patients were divided into two groups by cause of mortality (all-cause of 2664 and disease-specific of 1620) and investigated. We used comprehensive data integrating clinical, pathological, lifestyle, and socio-economic factors. Cox proportional hazards analysis was conducted to estimate hazard ratios for mortality. Five machine learning models (random forest, gradient boosting machine, XGBoost, light GBM, and cat boosting) were developed to predict mortality. The models were interpreted by SHAP, one of the explainable AI techniques. Results: For all-cause mortality, the gradient-boosting machine learning model demonstrated the highest performance with an AUC-ROC of 0.795. For disease-specific mortality, the light GBM model outperformed others, achieving an AUC-ROC of 0.867. Significant predictors included the AJCC7 stage, tumor size, lymph node count, and lifestyle factors such as smoking, drinking, and diabetes. Conclusions: This study underscores the importance of integrating both clinical and lifestyle data to enhance mortality prediction accuracy in gastric cancer patients. The findings highlight the need for personalized treatment approaches in the Korean population and emphasize the role of demographic-specific data in predictive modeling. [ABSTRACT FROM AUTHOR]

Simple Summary: Developing effective artificial intelligence (AI) systems for rare diseases such as osteosarcoma is challenging owing to the limited available data. This study introduces a novel approach for preparing training data for AI systems that detect osteosarcoma using X-rays. Traditional methods label tumor areas as a single entity; however, our new approach divides tumor regions into three distinct classes: intramedullary, cortical, and extramedullary. This three-class annotation method enables AI systems to learn more effectively from limited datasets by incorporating detailed anatomical knowledge. This new approach to data preparation resulted in more robust AI models that could detect subtle tumor changes at lower threshold values, demonstrating how strategic data annotation methods can enhance AI performance even with limited training samples. This methodological innovation in data preparation offers a new paradigm for developing AI systems for rare diseases, for which traditional data-driven approaches often fall short. Background/Objectives: Developing high-performance artificial intelligence (AI) models for rare diseases is challenging owing to limited data availability. This study aimed to evaluate whether a novel three-class annotation method for preparing training data could enhance AI model performance in detecting osteosarcoma on plain radiographs compared to conventional single-class annotation. Methods: We developed two annotation methods for the same dataset of 468 osteosarcoma X-rays and 378 normal radiographs: a conventional single-class annotation (1C model) and a novel three-class annotation method (3C model) that separately labeled intramedullary, cortical, and extramedullary tumor components. Both models used identical U-Net-based architectures, differing only in their annotation approaches. Performance was evaluated using an independent validation dataset. Results: Although both models achieved high diagnostic accuracy (AUC: 0.99 vs. 0.98), the 3C model demonstrated superior operational characteristics. At a standardized cutoff value of 0.2, the 3C model maintained balanced performance (sensitivity: 93.28%, specificity: 92.21%), whereas the 1C model showed compromised specificity (83.58%) despite high sensitivity (98.88%). Notably, at the 25th percentile threshold, both models showed identical false-negative rates despite significantly different cutoff values (3C: 0.661 vs. 1C: 0.985), indicating the ability of the 3C model to maintain diagnostic accuracy at substantially lower thresholds. Conclusions: This study demonstrated that anatomically informed three-class annotation can enhance AI model performance for rare disease detection without requiring additional training data. The improved stability at lower thresholds suggests that thoughtful annotation strategies can optimize the AI model training, particularly in contexts where training data are limited. [ABSTRACT FROM AUTHOR]

Simple Summary: Melanoma is a dangerous type of skin cancer that can grow quickly and spread to other parts of the body, making early detection and diagnosis essential for saving lives. However, it can be difficult to tell the difference between melanoma and harmless skin spots, even for experts. This study explores how advanced computer technologies called convolutional neural networks (CNNs) can help detect melanoma more accurately. These systems analyze skin images and identify patterns that indicate whether a spot is likely to be cancerous. We compared four different types of CNN to find the best balance between accuracy and efficiency. Our findings show that some models are not only highly accurate but also fast and lightweight, making them suitable for use in clinics or even on mobile devices. This research highlights the potential of artificial intelligence to assist doctors and improve early melanoma detection, ultimately saving more lives. Background/Objectives: Melanoma, an aggressive form of skin cancer, accounts for a significant proportion of skin-cancer-related deaths worldwide. Early and accurate differentiation between melanoma and benign melanocytic nevi is critical for improving survival rates but remains challenging because of diagnostic variability. Convolutional neural networks (CNNs) have shown promise in automating melanoma detection with accuracy comparable to expert dermatologists. This study evaluates and compares the performance of four CNN architectures—DenseNet121, ResNet50V2, NASNetMobile, and MobileNetV2—for the binary classification of dermoscopic images. Methods: A dataset of 8825 dermoscopic images from DermNet was standardized and divided into training (80%), validation (10%), and testing (10%) subsets. Image augmentation techniques were applied to enhance model generalizability. The CNN architectures were pre-trained on ImageNet and customized for binary classification. Models were trained using the Adam optimizer and evaluated based on accuracy, area under the receiver operating characteristic curve (AUC-ROC), inference time, and model size. The statistical significance of the differences was assessed using McNemar's test. Results: DenseNet121 achieved the highest accuracy (92.30%) and an AUC of 0.951, while ResNet50V2 recorded the highest AUC (0.957). MobileNetV2 combined efficiency with competitive performance, achieving a 92.19% accuracy, the smallest model size (9.89 MB), and the fastest inference time (23.46 ms). NASNetMobile, despite its compact size, had a slower inference time (108.67 ms), and slightly lower accuracy (90.94%). Performance differences among the models were statistically significant (p < 0.0001). Conclusions: DenseNet121 demonstrated a superior diagnostic performance, while MobileNetV2 provided the most efficient solution for deployment in resource-constrained settings. The CNNs show substantial potential for improving melanoma detection in clinical and mobile applications. [ABSTRACT FROM AUTHOR]

Simple Summary: Muscle depletion (MD), a key predictor of survival in hepatocellular carcinoma (HCC), is often excluded from current prognostic tools. Analyzing data from 1072 HCC patients at Taipei Tzu Chi Hospital (2006–2016), this study identified MD-related factors, along with hepatitis and tumor size, as significant survival predictors. Incorporating MD into the Barcelona Clinic Liver Cancer (BCLC) staging system improved survival prediction accuracy, offering a more reliable tool for HCC management and better clinical decision-making. Background: Muscle depletion (MD) is a critical factor that influences clinical outcomes in patients with hepatocellular carcinoma (HCC). Although its role in cancer prognosis is recognized, its integration into widely used prognostic systems remains underexplored. This study aimed to evaluate the prognostic impact of MD on overall survival (OS) in HCC patients and to improve existing noninvasive prognostic models by incorporating MD-related metrics. Methods: A retrospective analysis was conducted on 1072 HCC patients treated at Taipei Tzu Chi Hospital between January 2006 and December 2016. All patients had follow-up data and computed tomography (CT) scans at vertebral level L3 for MD evaluation. Independent prognostic factors for OS were identified using Cox proportional hazards models, and the predictive performance of various prognostic models was assessed through the area under the receiver operating characteristic curve (AUROC). Results: The key independent predictors of OS in HCC patients included hepatitis B virus infection, hepatitis C virus infection, liver cirrhosis, tumor size, serum alpha-fetoprotein levels, and MD-related metrics (psoas muscle-to-spine ratio, psoas muscle-to-vertebral ratio, and myosteatosis). Among existing models, the Barcelona Clinic Liver Cancer (BCLC) stage, the Child–Turcotte–Pugh (CTP) class, and the albumin–bilirubin (ALBI) grade demonstrated robust predictive performance for OS. However, incorporating MD significantly improved the predictive accuracy of these models, with the MD–BCLC model showing the highest AUROC (0.804, 95% CI: 0.777–0.832, p < 0.001). Conclusions: MD is an independent and significant prognostic predictor for patients with HCC. Integrating MD metrics into established systems, particularly the BCLC staging system, markedly improves OS prediction, providing a more comprehensive tool for clinical decision-making in the management of HCC. [ABSTRACT FROM AUTHOR]

Simple Summary: This study explored how diffusion-weighted MRI (DW-MRI) differs in oropharyngeal cancer (OPC) based on HPV status before and during radiation therapy. MRI data from 178 OPC patients were analyzed and showed that HPV-positive tumors had lower initial ADC values and specific texture features than HPV-negative tumors. During treatment, the change in ADC values was higher in HPV-positive tumors compared with HPV-negative tumors. These findings highlight the potential of DW-MRI as a non-invasive biomarker for HPV status. Background: This study aimed to explore the differences in quantitative diffusion-weighted (DW) MRI parameters in oropharyngeal squamous cell carcinoma (OPC) based on Human Papillomavirus (HPV) status before and during radiotherapy (RT). Methods: Echo planar DW sequences acquired before and during (chemo)radiotherapy (CRT) of 178 patients with histologically proven OPC were prospectively analyzed. The volumetric region of interest (ROI) was manually drawn on the apparent diffusion coefficient (ADC) map, and 105 DW-MRI radiomic parameters were extracted. Change in ADC values (Δ ADC) was calculated as the difference between baseline and during RT at week 4, normalized by the baseline values. Results: Pre-treatment first-order 10th percentile ADC and Gray Level co-occurrence matrix (GLCM)-correlation were significantly lower in HPV-positive compared with HPV-negative tumors (82.4 × 10−5 mm2/s vs. 90.3 × 10−5 mm2/s, p = 0.03 and 0.18 vs. 0.30, p < 0.01). In the fourth week of RT, all first-order ADC values were significantly higher in HPV-positive tumors (p < 0.01). Δ ADC mean was significantly higher for the HPV-positive compared with the HPV-negative OPC group (95% vs. 55%, p < 0.01). A predictive model for HPV status based on smoking status, alcohol consumption, GLCM correlation, and mean ADC and 10th percentile ADC values yielded an area under the curve of 0.77 (95% CI 0.70–0.84). Conclusions: Our results highlight the potential of DW-MR imaging as a non-invasive biomarker for the prediction of HPV status, although its current role remains supplementary to pathological confirmation. [ABSTRACT FROM AUTHOR]

Simple Summary: This study investigates lung cancer detection by combining metabolomics and advanced machine learning to identify small cell lung cancer (SCLC) with high accuracy. We analyzed 461 serum samples from publicly available data to create a stacking-based ensemble model that can distinguish between SCLC, non-small cell lung cancer (NSCLC), and healthy controls. The model has 85.03% accuracy in multi-class classification and 88.19% accuracy in binary classification (SCLC vs. NSCLC). This innovation relies on sophisticated feature selection techniques to identify significant metabolites, particularly positive ions. SHAP analysis identifies key predictors such as benzoic acid, DL-lactate, and L-arginine, shedding new light on cancer metabolism. This non-invasive approach presents a promising alternative to traditional diagnostic methods, with the potential to transform early lung cancer detection. By combining metabolomics and machine learning, the study paves the way for faster, more accurate, and patient-friendly cancer diagnostics, potentially improving treatment outcomes and survival rates. Background: Small cell lung cancer (SCLC) is an extremely aggressive form of lung cancer, characterized by rapid progression and poor survival rates. Despite the importance of early diagnosis, the current diagnostic techniques are invasive and restricted. Methods: This study presents a novel stacking-based ensemble machine learning approach for classifying small cell lung cancer (SCLC) and non-small cell lung cancer (NSCLC) using metabolomics data. The analysis included 191 SCLC cases, 173 NSCLC cases, and 97 healthy controls. Feature selection techniques identified significant metabolites, with positive ions proving more relevant. Results: For multi-class classification (control, SCLC, NSCLC), the stacking ensemble achieved 85.03% accuracy and 92.47 AUC using Support Vector Machine (SVM). Binary classification (SCLC vs. NSCLC) further improved performance, with ExtraTreesClassifier reaching 88.19% accuracy and 92.65 AUC. SHapley Additive exPlanations (SHAP) analysis revealed key metabolites like benzoic acid, DL-lactate, and L-arginine as significant predictors. Conclusions: The stacking ensemble approach effectively leverages multiple classifiers to enhance overall predictive performance. The proposed model effectively captures the complementary strengths of different classifiers, enhancing the detection of SCLC and NSCLC. This work accentuates the potential of combining metabolomics with advanced machine learning for non-invasive early lung cancer subtype detection, offering an alternative to conventional biopsy methods. [ABSTRACT FROM AUTHOR]

Simple Summary: This study investigates four blood-based biomarkers, mSEPT9, IGFBP2, DKK3, and PKM2, for colorectal cancer (CRC) detection. Current CRC screening methods are often invasive, leading to low compliance. We evaluated the diagnostic accuracy of these plasma biomarkers individually and their combinations in 124 CRC patients and 124 healthy controls. Our results showed that the combination of plasma biomarkers improved accuracy; the combined model outperformed individual biomarkers in detecting CRC. These findings suggest that a multi-biomarker blood test could offer a less invasive, effective alternative for CRC detection, potentially improving early detection rates and patient adherence to screening guidelines. Further research is needed to validate these findings in larger, diverse populations and explore their integration into routine clinical practice. Background: Colorectal cancer (CRC) is a leading cause of death worldwide. Despite its preventability through screening, compliance still needs to improve due to the invasiveness of current tools. There is a growing demand for validated molecular biomarker panels for minimally invasive blood-based CRC screening. This study assessed the diagnostic accuracy of four promising blood-based CRC biomarkers, individually and in combination. Methods: This case–control study involved plasma samples from 124 CRC cases and 124 age- and sex-matched controls. Biomarkers tested included methylated DNA encoding the Septin-9 gene (mSEPT9) using Epi proColon® 2.0 CE, insulin-like growth factor binding protein 2 (IGFBP2), dickkopf-3 (DKK3), and pyruvate kinase M2 (PKM2) by ELISA. Diagnostic accuracy was measured using the receiver operating characteristic (ROC), area under the curve (AUC), as well as sensitivity and specificity. Results: Diagnostic accuracy for mSEPT9, IGFBP2, DKK3, and PKM2 was 62.9% (95% CI: 56.8–62.9%), 69.7% (95% CI: 63.1–69.7%), 61.6% (95% CI: 54.6–61.6%), and 50.8% (95% CI: 43.4–50.8%), respectively. The combined biomarkers yielded an AUC of 74.4% (95% CI: 68.1–80.6%), outperforming all biomarkers except IGFBP2. Conclusions: These biomarkers show potential for developing a minimally invasive CRC detection tool as an alternative to existing approaches, potentially increasing adherence, early detection, and survivorship. [ABSTRACT FROM AUTHOR]

Simple Summary: Lung cancer (LC) is the leading cause of cancer-related mortality in Thailand, particularly in the Chiang Mai province. Beyond cigarette smoking, long-term exposure to indoor radon is a significant risk factor for the development of LC. In Kong Khaek, a subdistrict of the Mae Chaem district in Chiang Mai, the average indoor radon activity concentration exceeds both global and national averages. Understanding the impact of chronic low-dose radiation exposure on human populations living in high-background radiation areas is crucial. However, no specific biomarkers are currently available to detect LC resulting from prolonged exposure to indoor radon. Background: Indoor radon is a significant risk factor for the development of LC. This study aimed to identify potential biomarkers for LC risk in high background radiation areas using a metabolomics approach (UHPLC-HRMS). Methods: Based on the indoor radon activity concentration measurements in the Kong Khaek subdistrict, serum samples were collected from 45 nonsmoker or former smoker participants, comprising 15 LC patients and 30 matched healthy controls (low- and high-radon groups, respectively). Results: A total of 90 and 111 differential metabolites were identified in the LC group compared with the low- and high-radon groups, respectively, using criteria such as a variable importance in projection (VIP) of >1, a fold change (FC) of >1 or <0.5, and a p value of <0.05. Receiver operating characteristic (ROC) curves (an AUC of ≥ 0.9) indicated that 30 and 21 of these metabolites had the potential to serve as biomarkers of LC development in the low- and high-radon groups, respectively. The KEGG pathway enrichment analysis suggested that D-sphingosine may have been a candidate biomarker associated with LC in both groups. Conclusions: Overall, this study provides new insights into metabolic biomarkers for screening LC development in high-risk individuals with prolonged exposure to indoor radon. Further large-scale studies are needed to validate our results. [ABSTRACT FROM AUTHOR]

Simple Summary: Despite the promising results of radiomics for the characterisation of primary prostate cancer, its use in clinical practice is still limited due to a lack of results validation. In this study, we validated a previously published radiomics signature in a bicentric setting. Then, we also explored the role of the previously identified radiomics features if models are trained on new data. Furthermore, we investigated the performance of radiomics analysis if feature selection and model training are performed in the bicentric cohort. Results show that radiomics models work well when tested in their development settings, but generalise poorly to new datasets, thus warning about the need to interpret with caution results from single-centre studies or studies lacking proper external validation. Background: PSMA PET radiomics is a promising tool for primary prostate cancer (PCa) characterisation. However, small single-centre studies and lack of external validation hinder definitive conclusions on the potential of PSMA PET radiomics in the initial workup of PCa. We aimed to validate a radiomics signature in a larger internal cohort and in an external cohort from a separate centre. Methods: One hundred and twenty-seven PCa patients were retrospectively enrolled across two independent hospitals. The first centre (IRCCS San Raffaele Scientific Institute, Centre 1) contributed 62 [68Ga]Ga-PSMA-11 PET scans, 20 patients classified as low-grade (ISUP grade < 4), and 42 as high-grade (ISUP grade ≥ 4). The second centre (Stanford University Hospital, Centre 2) provided 65 [68Ga]Ga-PSMA-11 PET scans, and 49 low-grade and 16 high-grade patients. A radiomics model previously generated in Centre 1 was tested on the two cohorts separately and afterward on the entire dataset. Then, we evaluated whether the radiomics features selected in the previous investigation could generalise to new data. Several machine learning (ML) models underwent training and testing using 100-fold Monte Carlo cross-validation, independently at both Centre 1 and Centre 2, with a 70–30% train–test split. Additionally, models were trained in one centre and tested in the other, and vice versa. Furthermore, data from both centres were combined for training and testing using Monte Carlo cross-validation. Finally, a new radiomics signature built on this bicentric dataset was proposed. Several performance metrics were computed. Results: The previously generated radiomics signature resulted in an area under the receiver operating characteristic curve (AUC) of 80.4% when tested on Centre 1, while it generalised poorly to Centre 2, where it reached an AUC of 62.7%. When the whole cohort was considered, AUC was 72.5%. Similarly, new ML models trained on the previously selected features yielded, at best, an AUC of 80.9% for Centre 1 and performed at chance for Centre 2 (AUC of 49.3%). A new signature built on this bicentric dataset reached, at best, an average AUC of 91.4% in the test set. Conclusions: The satisfying performance of radiomics models when used in the original development settings, paired with the poor performance otherwise observed, emphasises the need to consider centre-specific factors and dataset characteristics when developing radiomics models. Combining radiomics datasets is a viable strategy to reduce such centre-specific biases, but external validation is still needed. [ABSTRACT FROM AUTHOR]

Simple Summary: In this study, machine learning models were developed to predict lymph node invasion in Japanese prostate cancer patients, using a structured approach to improve predictive accuracy. Traditional methods, such as the Briganti nomogram, have been widely used but may lack flexibility and adaptability to diverse clinical datasets. Our machine learning models, especially Light Gradient-Boosting Machine and Random Forest, showed higher flexibility and accuracy compared to conventional models. Through a thorough data analysis and feature engineering, including the use of predictive features such as PSA levels and tumor stage, we enhanced model performance and interpretability. A decision curve analysis indicated significant clinical benefits, suggesting that these models can better identify candidates for lymph node dissection, thereby minimizing unnecessary procedures. However, validation with larger and multi-institutional datasets is needed to confirm the utility of these models in broader clinical settings. Background/Objectives: Extended pelvic lymph node dissection is a crucial surgical technique for managing intermediate to high-risk prostate cancer. Accurately predicting lymph node metastasis before surgery can minimize unnecessary lymph node dissections and their associated complications. This study assessed the efficacy of various machine learning models for predicting lymph node metastasis in a cohort of Japanese patients who underwent robot-assisted laparoscopic radical prostatectomy. Methods: Data from 625 patients who underwent extended pelvic lymph node dissection or standard dissection with lymph node metastasis between October 2010 and February 2023 were analyzed. Four machine learning models—Random Forest, Light Gradient-Boosting Machine, Logistic Regression, and Support Vector Machine—were used to predict lymph node metastasis. Their performance was assessed using receiver operating characteristic curves, a decision curve analysis, and predictive values at different thresholds. Results: Lymph node metastasis was observed in 34 patients (5.4%). The Light Gradient-Boosting Machine had the highest AUC of 0.924, followed by the Random Forest model with an AUC of 0.894. The decision curve analysis indicated substantial net benefits for both models, particularly at low threshold probabilities. The Light Gradient-Boosting Machine demonstrated superior accuracy, achieving 95.6% at the 0.05 threshold and 96.7% at the 0.10 threshold, outperforming other models and conventional nomograms in the validation dataset. Conclusion: Machine learning models, especially Light Gradient-Boosting Machine and Random Forest, show significant potential for predicting lymph node metastasis in prostate cancer, thereby aiding in reducing unnecessary surgical interventions. [ABSTRACT FROM AUTHOR]

Simple Summary: In recent years, pembrolizumab has become applicable for recurrent and metastatic head and neck cancer (RMHNC), but only a limited number of patients can benefit from it. In this study, we explored predictive markers for the therapeutic effect and prognosis of pembrolizumab for RMHNC. The results showed that the immune-modified Glasgow Prognostic Score (imGPS), which we previously proposed, is a better predictive marker than the previously known neutrophil-to-lymphocyte ratio (NLR) and mGPS. The imGPS can be easily evaluated with just a blood test, so we hope that it will become more widely used in the clinical environment. Background: Previously, we proposed that the immune-modified Glasgow Prognostic Score (imGPS), which adds the lymphocyte count to the mGPS, is helpful as a prognostic marker for patients with head and neck squamous cell carcinoma. In this study, we investigated the imGPS as a marker for the therapeutic effect of pembrolizumab in treating recurrent and metastatic head and neck cancer (RMHNC). Methods: This study included RMHNC patients who were treated with pembrolizumab from December 2019 to April 2024. ALB, CRP, lymphocyte counts, neutrophil-to-lymphocyte ratios (NLRs), mGPSs, and imGPSs were extracted as biomarkers, and the response rate and prognosis were analyzed for each. Results: A total of 54 patients were enrolled. Lymphocyte counts were correlated with the overall response rates (ORRs) (p = 0.0082). Although the mGPS did not show significant differences in ORRs, imGPSs revealed a significant difference (p = 0.013). CRP, ALB, and lymphocyte counts were correlated with overall survival (OS) and/or progression-free survival (PFS). NLRs, mGPSs, and imGPSs were also correlated with OS and/or PFS, with imGPSs showing the greatest area under the curve (OS; AUC = 0.795, PFS; AUC = 0.754). Conclusions: This study demonstrates that the imGPS is an excellent predictive marker for the therapeutic effect and prognosis of pembrolizumab for RMHNC. The imGPS can be employed with daily blood tests, highlighting the potential to forecast the impact of the ICI with high reliability. [ABSTRACT FROM AUTHOR]

Simple Summary: This study investigates differentially expressed genes and their effect on pancreatic ductal adenocarcinoma (PDAC). These differentially expressed genes were identified in PDAC using transcriptomic profiles from the gene expression omnibus repository and the GEO2R web-based tool. Protein–protein interaction analysis was performed using the STRING database to characterize gene clusters. The following three functional gene clusters were identified: (1) extracellular matrix/cell adhesion, (2) metabolism, and (3) mucus secretion. Based on the TCGA database, expression of these gene clusters was associated with PDAC tumorigenesis, metastasis, and patient survival. This study identifies 68 differentially expressed genes that appear to be crucial in PDAC development and prognosis, thus providing potential targets for future therapeutic intervention in pancreatic cancer. Objectives: Technological advances in identifying gene expression profiles are being applied to study an array of cancers. The goal of this study was to identify differentially expressed genes in pancreatic ductal adenocarcinoma (PDAC) and examine their potential role in tumorigenesis and metastasis. Methods: The transcriptomic profiles of PDAC and non-tumorous tissue samples were derived from the gene expression omnibus (GEO), which is a public repository. The GEO2R tool was used to further derive differentially expressed genes from those profiles. Results: In this study, a total of 68 genes were derived from upregulated PDAC genes in three or more transcriptomic profiles and were considered PDAC gene sets. The identified PDAC gene sets were examined in the molecular signatures database (MSigDB) for ontological investigation, which revealed that these genes were involved in the extracellular matrix and associated with the cell adhesion process in PDAC tumorigenesis. The gene set enrichment analysis showed greater enrichment scores for the gene sets. Moreover, the identified gene sets were examined for protein–protein interaction using the STRING database. Based on functional k-means clustering, the following three functional cluster groups were identified in this study: extracellular matrix/cell adhesion, metabolic, and mucus secretion-related protein groups. The receiver operating characteristic (ROC) curve revealed greater specificity and sensitivity for these cluster genes in predicting PDAC tumorigenesis and metastases. In addition, the expression of the cluster genes affects the overall survival rate of PDAC patients. Using the cancer genome atlas (TCGA) database, the associations between expression levels and clinicopathological features were validated. Conclusions: Overall, the genes identified in this study appear to be critical in PDAC development and can serve as potential diagnostic and prognostic targets for pancreatic cancer treatment. [ABSTRACT FROM AUTHOR]

Simple Summary: This study explores various resampling methods and classifiers for imbalanced datasets, focusing on cancer diagnosis and prognosis. Traditional methods like SMOTE and ADASYN were replaced by GANs, which generate high-quality synthetic data to address class imbalance. The study evaluated Boosting, Bagging, Linear, and Non-linear classifiers using metrics like accuracy and ROC AUC. Baseline models struggled with imbalanced data, emphasizing the need for resampling. GAN-based resampling significantly improved detection of minority classes and overall performance, boosting the average ROC AUC from 0.8276 to over 0.9734. GradientBoosting achieved the highest ROC AUC of 0.9890, showing GANs' effectiveness in enhancing predictive accuracy. Background/Objectives: This study examines the effectiveness of different resampling methods and classifier models for handling imbalanced datasets, with a specific focus on critical healthcare applications such as cancer diagnosis and prognosis. Methods: To address the class imbalance issue, traditional sampling methods like SMOTE and ADASYN were replaced by Generative Adversarial Networks (GANs), which leverage deep neural network architectures to generate high-quality synthetic data. The study highlights the advantage of GANs in creating realistic, diverse, and homogeneous samples for the minority class, which plays a significant role in mitigating the diagnostic challenges posed by imbalanced data. Four types of classifiers, Boosting, Bagging, Linear, and Non-linear, were assessed to evaluate their performance using metrics such as accuracy, precision, recall, F1 score, and ROC AUC. Results: Baseline performance without resampling showed significant limitations, underscoring the need for resampling strategies. Using GAN-generated data notably improved the detection of minority instances and overall classification performance. The average ROC AUC value increased from baseline levels of approximately 0.8276 to over 0.9734, underscoring the effectiveness of GAN-based resampling in enhancing model performance and ensuring more balanced detection across classes. With GAN-based resampling, GradientBoosting classifier achieved a ROC AUC of 0.9890, the highest among all models, demonstrating the effectiveness of GAN-generated data in enhancing performance. Conclusions: The findings underscore that advanced models like Boosting and Bagging, when paired with effective resampling strategies such as GANs, are better suited for handling imbalanced datasets and improving predictive accuracy in healthcare applications. [ABSTRACT FROM AUTHOR]

Simple Summary: Papillary thyroid cancer (PTC) is the most common subtype of thyroid cancer (TC), accounting for approximately 80–90% of all TC cases. PTC is generally considered a low-grade malignancy. However, aggressive behaviors, such as cervical lymph node metastasis, can be observed in some cases, with central lymph node metastasis (CLNM) regarded as the primary site of lymph node metastasis. In current clinical practice in China, prophylactic central lymph node dissection is commonly performed regardless of whether CLNM is present. This approach is associated with an increased risk of complications and unnecessary lymph node removal, raising concerns about overtreatment. Therefore, there is an urgent need for an efficient method to predict CLNM in PTC patients, which could guide clinical diagnosis and treatment strategies. In this study, we developed a fusion model based on the attention mechanism-based multimodal classification network (AMMCNet) architecture, integrating MRI images and clinicopathological data to efficiently predict CLNM in PTC patients. Background: Central lymph node metastasis (CLNM) in papillary thyroid cancer (PTC) significantly influences surgical decision-making strategies. Objectives: This study aims to develop a predictive model for CLNM in PTC patients using magnetic resonance imaging (MRI) and clinicopathological data. Methods: By incorporating deep learning (DL) algorithms, the model seeks to address the challenges in diagnosing CLNM and reduce overtreatment. The results were compared with traditional machine learning (ML) models. In this retrospective study, preoperative MRI data from 105 PTC patients were divided into training and testing sets. A radiologist manually outlined the region of interest (ROI) on MRI images. Three classic ML algorithms (support vector machine [SVM], logistic regression [LR], and random forest [RF]) were employed across different data modalities. Additionally, an AMMCNet utilizing convolutional neural networks (CNNs) was proposed to develop DL models for CLNM. Predictive performance was evaluated using receiver operator characteristic (ROC) curve analysis, and clinical utility was assessed through decision curve analysis (DCA). Results: Lesion diameter was identified as an independent risk factor for CLNM. Among ML models, the RF-(T1WI + T2WI, T1WI + T2WI + Clinical) models achieved the highest area under the curve (AUC) at 0.863. The DL fusion model surpassed all ML fusion models with an AUC of 0.891. Conclusions: A fusion model based on the AMMCNet architecture using MRI images and clinicopathological data was developed, effectively predicting CLNM in PTC patients. [ABSTRACT FROM AUTHOR]

Simple Summary: Penile cancer is aggressive and rapidly progressive. Early detection is crucial for survival. Many men delay seeking help due to a lack of awareness and fear of embarrassment. This study explored the use of artificial intelligence (AI) in detection of penile cancer. AI was trained on 136 penile lesions images from scientific publications. This included 65 penile cancer, 44 precancerous, and 27 benign images. It performed well in distinguishing between benign lesions and penile cancer with high accuracy. However, it faced challenges in accurately identifying precancerous lesions. These findings suggest that AI has potential in early detection of penile cancer, but more research is needed to refine and validate the AI software with real-life data. The goal is to complement and not replace clinicians. The AI algorithm may allow patients to evaluate any concerning penile lesion from the comfort and privacy of their home, potentially encouraging earlier medical consultation. Background/Objective: Penile cancer is aggressive and rapidly progressive. Early recognition is paramount for overall survival. However, many men delay presentation due to a lack of awareness and social stigma. This pilot study aims to develop a convolutional neural network (CNN) model to differentiate penile cancer from precancerous and benign penile lesions. Methods: The CNN was developed using 136 penile lesion images sourced from peer-reviewed open access publications. These images included 65 penile squamous cell carcinoma (SCC), 44 precancerous lesions, and 27 benign lesions. The dataset was partitioned using a stratified split into training (64%), validation (16%), and test (20%) sets. The model was evaluated using ten trials of 10-fold internal cross-validation to ensure robust performance assessment. Results: When distinguishing between benign penile lesions and penile SCC, the CNN achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.94, with a sensitivity of 0.82, specificity of 0.87, positive predictive value of 0.95, and negative predictive value of 0.72. The CNN showed reduced discriminative capability in differentiating precancerous lesions from penile SCC, with an AUROC of 0.74, sensitivity of 0.75, specificity of 0.65, PPV of 0.45, and NPV of 0.88. Conclusion: These findings demonstrate the potential of artificial intelligence in identifying penile SCC. Limitations of this study include the small sample size and reliance on photographs from publications. Further refinement and validation of the CNN using real-life data are needed. [ABSTRACT FROM AUTHOR]

Simple Summary: Small intestinal neuroendocrine tumors (SI-NETs) can lead to carcinoid syndrome and carcinoid heart disease (CHD). In this prospective study we aimed to identify early risk markers for CHD and mortality in patients with SI-NETs. We measured basal serum 5-HIAA and cumulative 5-HIAA (Cum-5-HIAA) based on repeated measurements, proBNP, vascular function, transesophageal echocardiography (TTE), and hepatic tumor load in 65 patients with SI-NETs during the median follow-up of 5 years in 54 of the patients who underwent prospective follow-up. Survival was evaluated during the median follow-up of 6 years. Three patients had CHD at baseline and two (4%) developed CHD. Cum-5-HIAA and proBNP correlated with CHD. Of note, Cum-5-HIAA was the best biomarker for CHD, outperforming pro-BNP, chromogranin A (CgA), and individual 5-HIAA. The strongest predictors of mortality were the diagnosis of CHD and high liver tumor burden, while high blood vessel stiffness was also associated with lower survival rates. The incidence of CHD was low during follow-up, probably reflecting efficient treatment regimens. These findings may help identify patients at high risk for CHD and mortality and guide early interventions to improve patient outcomes. Background: Small intestinal neuroendocrine tumors (SI-NETs) are characterized by carcinoid syndrome and carcinoid heart disease (CHD). The aim of the present study was to identify early risk markers for carcinoid heart disease and survival in a prospective median-term follow-up setting. Methods: We measured 5-HIAA and cumulative 5-HIAA exposure (Cum-5-HIAA) based on repeated measurements, proBNP, vascular function, hepatic tumor load, and transthoracic echocardiography (TTE) at baseline and during the median 5-year follow-up. Of 65 patients with SI-NETs, 54 patients underwent a prospective follow-up. In addition, survival was evaluated during the median follow-up of 6 years. Results: At baseline, three patients had CHD. During the median follow-up of 5 years, two patients (4%) developed CHD. Cum-5-HIAA and proBNP correlated with CHD (Westberg score, Spearman's ρ = 0.32 and 0.31, respectively). Cum-5-HIAA had a superior diagnostic capability, predicting CHD in receiver operator characteristic analysis with an AUC of 0.98 (95% CI: 0.94–1.00) and outperformed proBNP, chromogranin A (CgA), and individual serum 5-HIAA measurements (AUC = 0.75, 0.85, and 0.91, respectively). Minor changes in valve regurgitation were frequently detected but did not correlate with vascular function. Regurgitation increased or decreased in 29% of tricuspid and 30% of pulmonic valves. CHD, hepatic tumor load, serum 5-HIAA, and elevated aortic pulse wave velocity (PWV) were associated with increased mortality in SI-NET patients. Conclusions: Cum-5-HIAA is a promising biomarker for CHD risk and outperformed other biomarkers. CHD and hepatic tumor load are the strongest predictors of mortality. PWV is a novel predictor of survival. The incidence of CHD was low among the SI-NET patients, probably reflecting successful treatment regimens. [ABSTRACT FROM AUTHOR]

Simple Summary: In this study, we evaluated the expression of Toll-like receptors (TLRs) on NK and NKT-like cells in patients with gastric cancer (GC) in comparison to its two subtypes: intestinal and diffuse, and in healthy volunteers. We showed that TLR expression increases with disease progression, which may be related to the adaptive immune response to tumor progression. Furthermore, we identified differences in TLR expression depending on the gastric cancer subtype. RT-qPCR analysis revealed significantly higher expression of TLR2, TLR3, TLR4, and TLR9 genes in patients with GC. The results suggest that TLR expression levels may represent a valuable diagnostic and prognostic biomarker and potentially support the personalization of treatment and the development of new immunotherapy strategies in the future. Background/Objectives: The aim of this study was to determine the assessment of the percentage of NK and NKT-like cells expressing Toll-like receptors (TLR-2, TLR-3, TLR-4, and TLR-9) in patients with gastric cancer (GC) compared with healthy volunteers (HV) and to investigate differences according to cancer subtype. We also assessed TLR gene expression by RT-qPCR to assess whether TLRs could be diagnostic and prognostic biomarkers. Methods: The study included 86 patients with histologically confirmed gastric cancer and 30 healthy volunteers. Peripheral blood samples were collected from the participants, and TLR expression on NK and NKT-like cells was assessed by flow cytometry and RT-qPCR. The expression of TLR2, TLR3, TLR4, and TLR9 genes was assessed using genetic material derived from NK and NKT-like cells sourced from PBMC. The obtained results were statistically analyzed using Mann–Whitney U and Kruskal–Wallis tests, and the predictive ability of variables was assessed using ROC curve analysis. Results: A significantly higher expression of TLR receptors (TLR-2, TLR-3, TLR-4, and TLR-9) was found in patients with gastric cancer compared to healthy volunteers (p < 0.05). TLR expression also differed depending on the cancer subtype, and higher expression was observed in more advanced GC subtypes. RT-qPCR analysis showed significantly increased expression of TLR genes in the group of GC patients. ROC curves indicate a high ability of TLRs to differentiate between GC patients and healthy individuals. Conclusions: The expression of TLRs on NK and NKT-like cells is clearly increased in patients with gastric cancer, especially in more advanced subtypes of the tumor. The results suggest that TLRs could potentially be used as diagnostic and prognostic biomarkers and represent potential targets for immune therapies in GC. However, further studies are needed to determine the functional role of TLRs in disease progression and the possibility of their use in personalized treatment. [ABSTRACT FROM AUTHOR]

Simple Summary: The O-RADS system demonstrates high diagnostic performance in distinguishing benign from malignant adnexal masses, even when used by inexperienced examiners. However, the false positive rate remains relatively high, mainly due to the over-interpretation of solid-appearing components in classic benign lesions. Despite this, inter-observer variability among non-expert raters was substantial. Incorporating O-RADS system training into residency programs is beneficial for inexperienced practitioners. This study could be an educational model for gynecologic residency training for other systems of sonographic features. Objective: To evaluate the accuracy of the O-RADS system in differentiating between benign and malignant adnexal masses, as assessed by inexperienced gynecologists. Methods: Ten gynecologic residents attended a 20 h training course on the O-RADS system conducted by experienced examiners. Following the training, the residents performed ultrasound examinations on patients admitted with adnexal masses under supervision, recording the data in a database that included videos and still images. The senior author later accessed this ultrasound database and presented the cases offline to ten residents for O-RADS rating, with the raters being blinded to the final diagnosis. The efficacy of the O-RADS system by the residents and inter-observer variability were assessed. Results: A total of 201 adnexal masses meeting the inclusion criteria were evaluated, consisting of 136 (67.7%) benign masses and 65 (32.3%) malignant masses. The diagnostic performance of the O-RADS system showed a sensitivity of 90.8% (95% CI: 82.2–96.2%) and a specificity of 86.8% (95% CI: 80.4–91.8%). Inter-observer variability in scoring was analyzed using multi-rater Fleiss Kappa analysis, yielding Kappa indices of 0.642 (95% CI: 0.641–0.643). The false positive rate was primarily due to the misclassification of solid components in classic benign masses as O-RADS-4 or O-RADS-5. Conclusions: The O-RADS system demonstrates high diagnostic performance in distinguishing benign from malignant adnexal masses, even when used by inexperienced examiners. However, the false positive rate remains relatively high, mainly due to the over-interpretation of solid-appearing components in classic benign lesions. Despite this, inter-observer variability among non-expert raters was substantial. Incorporating O-RADS system training into residency programs is beneficial for inexperienced practitioners. This study could be an educational model for gynecologic residency training for other systems of sonographic features. [ABSTRACT FROM AUTHOR]

Simple Summary: ASPM is a gene involved in cell division, and recent research shows that it plays an important role in breast cancer (BC). This study looked at large datasets of BC patients to see how ASPM is linked to tumor growth and patient outcomes. We found that patients with higher levels of ASPM had more aggressive forms of cancer and poorer chances of survival. This suggests that ASPM may be useful as a marker to predict how aggressive the BC is and how well it will respond to treatment. These findings could guide future research and potentially lead to new treatments targeting ASPM in cancer. Background: Assembly factor for spindle microtubules (ASPM) has gained significant attention in cancer research due to its association with tumor growth and progression. Through the analysis of large-scale genomic datasets, ASPM has been identified as the top upregulated gene in breast cancer (BC), characterized by high proliferation. This multicohort study aimed to investigate the clinicopathological and prognostic significance of ASPM mRNA and protein expression in BC. Methods: ASPM mRNA expression was assessed using the Cancer Genome Atlas (TCGA) BC cohort and has been further validated in the Molecular Taxonomy of BC International Consortium (METABRIC) (n = 1980), The Uppsala cohort (n = 249), in addition to the combined multicentric cohort (n = 7252). ASPM protein expression was evaluated in a large BC cohort (n = 1300) using immunohistochemistry. The correlations between ASPM expression, clinicopathological parameters, molecular subtypes and outcome were assessed. The response to taxane treatment was compared to the clinical prognosis of ASPM using the ROC plotter. Results: High ASPM mRNA and protein expression were significantly associated with aggressive BC features and poor survival across all cohorts. The association with poor outcomes was maintained in the adjuvant chemotherapy and radio-therapy-treated patients. Responders to taxane treatment showed significantly elevated ASPM levels compared to non-responders. Conclusions: High ASPM expression predicts poor prognosis in BC. It may play a role in treatment resistance within a specific subgroup of patients. Further clinical trials are warranted to explore the potential of ASPM as a target for therapeutic interventions in cancer. [ABSTRACT FROM AUTHOR]

Simple Summary: Locally advanced cervical cancer (LACC) poses a significant challenge in oncology due to its heterogeneous nature and inconsistent response to standard chemoradiation therapy. The ability to predict response to treatment early in LACC has profound implications for enhancing patient care through tailored and adaptive therapies. Sequential FDG-PET imaging is crucial in managing LACC, offering a non-invasive method to assess tumor progression and response to chemoradiation over the course of treatment. The current study had recourse to longitudinal FDG-PET radiomics for early prediction of treatment response to chemoradiation in LACC. The implications of this study aid in demonstrating the potentially pivotal role of longitudinal radiomics in personalized medicine and improving therapeutic outcomes for LACC. Objectives: This study aimed to assess the capacity of longitudinal FDG-PET radiomics for early distinguishing between locally advanced cervical cancer (LACC) patients who responded to treatment and those who did not. Methods: FDG-PET scans were obtained before and midway through concurrent chemoradiation for a study cohort of patients with LACC. Radiomics features related to image textures were extracted from the primary tumor volumes and stratified for relevance to treatment response status with the aid of random forest recursive feature elimination. Predictive models based on the k-nearest neighbors time series classifier were developed using the top-selected features to differentiate between responders and non-responders. The performance of the developed models was evaluated using receiver operating characteristic (ROC) curve analysis and n-fold cross-validation. Results: The top radiomics features extracted from scans taken midway through treatment showed significant differences between the two responder groups (p-values < 0.0005). In contrast, those from pretreatment scans did not exhibit significant differences. The AUC of the mean ROC curve for the predictive model based on the top features from pretreatment scans was 0.8529, while it reached 0.9420 for those derived midway through treatment scans. Conclusions: The study highlights the potential of longitudinal FDG-PET radiomics extracted midway through treatment for predicting response to chemoradiation in LACC patients and emphasizes that interim PET scans could be crucial in personalized medicine, ultimately enhancing therapeutic outcomes for LACC. [ABSTRACT FROM AUTHOR]

Simple Summary: A transvaginal ultrasound examination is often used in clinical practice as the standard first-line imaging investigation for the assessment of adnexal masses. The accurate identification of malignancy ensures timely intervention and allows for the referral of the patient to a specialized center, particularly given the aggressive nature of ovarian cancer. Over the years, various serum biomarkers (CA125, HE4) and ultrasound-based models (e.g., Risk of Malignancy Algorithm (ROMA score), Risk of Malignancy Index (RMI I-IV), and Assessment of Different NEoplasia in the adneXa (ADNEX model) have been proposed to predict the malignancy risk of an adnexal mass. Comparing these models is essential to determine which one offers the best diagnostic accuracy and clinical utility. Objective: We aimed to compare the clinical utility and diagnostic accuracy of the ADNEX model, ROMA score, RMI I, and RMI IV, as well as two serum markers (CA125 and HE4) in preoperative discrimination between benign and malignant adnexal masses (AMs). Methods: We conducted a retrospective study extracting all consecutive patients with AMs seen at our Institution between January 2015 and December 2020. Accuracy metrics included sensitivity (SE), specificity (SP), and area under the receiver operating characteristic curve (AUC), and their 95% confidence intervals (CI) were calculated for basic discrimination between AMs. Model performance was evaluated in terms of discrimination ability and clinical utility (net benefit, NB). Results: A total of 581 women were included; 481 (82.8%) had a benign ovarian tumor and 100 (17.2%) had a malignant tumor. The SE and SP of CA125, HE4, ROMA score, RMI I, RMI IV, and ADNEX model were 0.60 (0.54–0.66) and 0.80 (0.76–0.83); 0.39 (0.30–0.49) and 0.96 (0.94–0.98); 0.59 (0.50–0.68) and 0.92 (0.88–0.95); 0.56 (0.46–0.65) and 0.98 (0.96–0.99); 0.54 (0.44–0.63) and 0.96 (0.94–0.98); 0.82 (0.73–0.88) and 0.91 (0.89–0.94), respectively. The overall AUC was 0.76 (0.74–0.79) for CA125, 0.81 (0.78–0.83) for HE4, 0.82 (0.80–0.85) for ROMA, 0.86 (0.84–0.88) for RMI I, 0.83 (0.81–0.86) for RMI IV, and 0.92 (0.90–0.94) for ADNEX. The NB for ADNEX was higher than other biomarkers and models across all decision thresholds between 5% and 50%. Conclusions: The ADNEX model showed a better discrimination ability and clinical utility when differentiating malignant from benign Ams, compared to CA125, HE4, ROMA score, RMI I, and RMI IV. [ABSTRACT FROM AUTHOR]

Simple Summary: Thyroid nodules must be accurately classified as benign or malignant. The aim of this study is to develop a machine learning model based on thyroid ultrasound images in order to classify nodules into the two classes. Ultrasound (US) images were collected from 142 patients for training, validation and internal testing of three models, plus 21 images to externally test the best performing model. The random forest classifier model could perform the classification task, identifying all the malignant nodes and most of the benign. Background/Objectives: Thyroid nodules are a very common finding, mostly benign but sometimes malignant, and thus require accurate diagnosis. Ultrasound and fine needle biopsy are the most widely used and reliable diagnostic methods to date, but they are sometimes limited in addressing benign from malignant nodules, mainly with regard to ultrasound, by the operator's experience. Radiomics, quantitative feature extraction from medical images and machine learning offer promising avenues to improve diagnosis. The aim of this work was to develop a machine learning model based on thyroid ultrasound images to classify nodules into benign and malignant classes. Methods: For this purpose, images of ultrasonography from 142 subjects were collected. Among these subjects, 40 patients (28.2%) belonged to the class "malignant" and 102 patients (71.8%) belonged to the class "benign", according to histological diagnosis from fine-needle aspiration. This image set was used for the training, cross-validation and internal testing of three different machine learning models. A robust radiomic approach was applied, under the hypothesis that the radiomic feature could capture the disease heterogeneity among the two groups. Three models consisting of four ensembles of machine learning classifiers (random forests, support vector machines and k-nearest neighbor classifiers) were developed for the binary classification task of interest. The best performing model was then externally tested on a cohort of 21 new patients. Results: The best model (ensemble of random forest) showed Receiver Operating Characteristic-Area Under the Curve (ROC-AUC) (%) of 85 (majority vote), 83.7 ** (mean) [80.2–87.2], accuracy (%) of 83, 81.2 ** [77.1–85.2], sensitivity (%) of 70, 67.5 ** [64.3–70.7], specificity (%) of 88, 86.5 ** [82–91], positive predictive value (PPV) (%) of 70, 66.5 ** [57.9–75.1] and negative predictive value (NPV) (%) of 88, 87.1 ** [85.5–88.8] (* p < 0.05, ** p < 0.005) in the internal test cohort. It achieved an accuracy of 90.5%, a sensitivity of 100%, a specificity of 86.7%, a PPV of 75% and an NPV of 100% in the external testing cohort. Conclusions: The model constituted of four ensembles of random forest classifiers could identify all the malignant nodes and the consistent majority of benign in the external testing cohort. [ABSTRACT FROM AUTHOR]

Simple Summary: Upper tract urothelial carcinoma (UTUC) is a rare but aggressive cancer that is difficult to predict and treat effectively. Current methods for assessing a patient's outlook often fall short. Our research introduces a new approach that could change this. We look at the fat surrounding the kidney using detailed CT scan analysis, combined with standard clinical information. This method provides a more accurate prediction of how patients with UTUC might fare. By examining the texture and patterns in this fat tissue, we can potentially detect early signs of cancer spread that are not visible to the naked eye. Our findings could help doctors make better treatment decisions, such as whether to use chemotherapy before surgery or how extensive the surgery should be. This personalized approach aims to improve outcomes for patients with this challenging cancer. Background: Upper tract urothelial carcinoma (UTUC) presents significant challenges in prognostication due to its rarity and complex anatomy. This study introduces a novel approach integrating perirenal fat (PRF) radiomics with clinical factors to enhance prognostic accuracy in UTUC. Methods: The study retrospectively analyzed 103 UTUC patients who underwent radical nephroureterectomy. PRF radiomics features were extracted from preoperative CT scans using a semi-automated segmentation method. Three prognostic models were developed: clinical, radiomics, and combined. Model performance was assessed using concordance index (C-index), time-dependent Area Under the Curve (AUC), and integrated Brier score. Results: The combined model demonstrated superior performance (C-index: 0.784, 95% CI: 0.707–0.861) compared to the radiomics (0.759, 95% CI: 0.678–0.840) and clinical (0.653, 95% CI: 0.547–0.759) models. Time-dependent AUC analysis revealed the radiomics model's particular strength in short-term prognosis (12-month AUC: 0.9281), while the combined model excelled in long-term predictions (60-month AUC: 0.8403). Key PRF radiomics features showed stronger prognostic value than traditional clinical factors. Conclusions: Integration of PRF radiomics with clinical data significantly improves prognostic accuracy in UTUC. This approach offers a more nuanced analysis of the tumor microenvironment, potentially capturing early signs of tumor invasion not visible through conventional imaging. The semi-automated PRF segmentation method presents advantages in reproducibility and ease of use, facilitating potential clinical implementation. [ABSTRACT FROM AUTHOR]

Simple Summary: This study raises the question whether all breast cancer patients need axillary lymph node dissection (ALND) after neoadjuvant chemotherapy (NAC). Researchers assessed a novel clinical variable: the sentinel lymph node ratio (SLN-R) to predict additional cancerous lymph nodes during ALND. SLN-R was defined as total number of positive sentinel nodes among all sentinel nodes removed during axillary staging after NAC. Axillary surgery included Targeted Axillary Dissection (TAD) technique for cN1 breast cancer patients. We analyzed data from 1521 patients, focusing on 118 with specific cancer stages and positive sentinel /TAD nodes results after NAC. The results indicated that an SLN-R value below 0.35 could suggest a lower chance of finding more cancerous nodes, with a 10.2% false-negative rate. This means SLN-R could help identify patients who might avoid unnecessary surgeries. By combining SLN-R with other clinical factors, the study aims to create a predictive tool, enhancing personalized care and improving patients' quality of life. Background/Objectives: The aim of the study was to determine the clinical value of the sentinel lymph node ratio (SLN-R) in predicting additional positive lymph nodes during axillary lymph node dissection (ALND) in breast cancer patients following neoadjuvant chemotherapy (NAC). Methods: A cross-sectional study was performed at a single institution evaluating data from 1521 BC patients. Inclusion criteria comprised cT1/cT4, cN0/cN1 status with positive post-NAC axillary staging by SLN/TAD, respectively, and subsequent ALND. Results: The study included 118 patients, divided into two groups based on the presence or absence of additional node metastasis at ALND: 39 in the residual disease group (RD) and 79 in the non-residual disease group (nRD). Univariate logistic regression analysis of SLN-R was conducted to assess its predictive value, yielding an odds ratio (OR) of 7.79 (CI 1.92–29.5, p = 0.003). An SLN-R cut-off point of <0.35 was identified using ROC curve analysis, with a false-negative rate of 10.2%, as a predictor for no additional metastasis at ALND following post-NAC SLN/TAD positivity. Conclusions: The study concludes that SLN-R is a valuable predictor for determining the omission of ALND in cases where SLN/TAD is positive after NAC. This metric, in combination with other clinical variables, could help develop a nomogram to spare patients from ALND. [ABSTRACT FROM AUTHOR]

Simple Summary: This study investigated the relationship between systemic inflammatory reaction (SIR) indices and endometrial thickness in postmenopausal women with abnormal uterine bleeding. A new biomarker, SIR-En, combining SII (Systemic Inflammatory Index) and endometrial thickness, was developed. This study compared 192 patients with endometrial cancer and 50 with endometrial hyperplasia. The results showed that patients with cancer had significantly higher SIR-En values than those with hyperplasia (8710 vs. 6420; p = 0.003). The SIR-En index demonstrated moderate diagnostic ability for endometrial cancer, with an area under the ROC curve (AUC) of 0.6351 and a cut-off of 13,806, yielding high specificity (94%) and positive predictive value (96%). This suggests that SIR-En could aid in discriminating the endometrial carcinoma from atypical hyperplasia, improving diagnosis and treatment strategies. Objective: This study aimed to evaluate the efficacy of a new biomarker, termed SIR-En, in identifying patients at risk of endometrial carcinoma among those presenting with abnormal uterine bleeding during menopause. Material and Methods: A retrospective case–control analysis was conducted on 242 women with menopausal abnormal uterine bleeding and endometrial thickness ≥ 4 mm. Peripheral blood samples were collected within 7 days before histological diagnosis. systemic inflammatory reaction (SIR) indices were calculated, including NLR, MLR, PLR, and SII. SIR-En was derived by multiplying SII and endometrial thickness. Statistical analyses, including multivariate linear regression and ROC curve analysis, were performed to assess the diagnostic capability of SIR-En. Results: Patients were categorized into endometrial hyperplasia (50 patients) and endometrial cancer (192 patients) groups. The SIR-En index was significantly higher in the carcinoma group (8710 vs. 6420; p = 0.003). The ROC curve for SIR-En had an AUC of 0.6351 (95% CI: 0.5579–0.7121). Using Youden's method, the optimal SIR-En cutoff was 13,806, showing a specificity of 0.940 and a positive predictive value of 0.957. Conclusions: Combining systemic inflammatory indices with endometrial thickness, the SIR-En index can effectively distinguish between endometrial hyperplasia and carcinoma in menopausal women with abnormal uterine bleeding. Despite the retrospective design, the identified cutoff's high specificity and positive predictive value support its potential utility in clinical practice. Further prospective studies are required to validate these findings and optimize clinical application. [ABSTRACT FROM AUTHOR]

Simple Summary: A colposcopy provides a comprehensive examination of the female genital tract, including the cervix, vagina, and vulva. However, its diagnostic accuracy, especially for vaginal lesions, remains suboptimal due to the challenge in detecting subtle alterations. Integrating artificial intelligence (AI) into colposcopy holds potential to enhance the detection rates of clinically important lesions. Our study pioneered the development of an AI algorithm capable of differentiating low-grade (LSILs) and high-grade (HSILs) squamous intraepithelial lesions in the vagina. The promising results we achieve in differentiating HPV-associated dysplastic lesions demonstrate that AI can significantly address the current challenges in medical practice. There are already promising results when using AI to detect HPV lesions in the cervix and anus, suggesting that in the future, this ubiquitous tool for lesion detection across different anatomical regions could be a reality. The future integration of these technologies into the colposcopy process could revolutionize healthcare, making early detection a reality for women worldwide. Background/Objectives: While human papillomavirus (HPV) is well known for its role in cervical cancer, it also affects vaginal cancers. Although colposcopy offers a comprehensive examination of the female genital tract, its diagnostic accuracy remains suboptimal. Integrating artificial intelligence (AI) could enhance the cost-effectiveness of colposcopy, but no AI models specifically differentiate low-grade (LSILs) and high-grade (HSILs) squamous intraepithelial lesions in the vagina. This study aims to develop and validate an AI model for the differentiation of HPV-associated dysplastic lesions in this region. Methods: A convolutional neural network (CNN) model was developed to differentiate HSILs from LSILs in vaginoscopy (during colposcopy) still images. The AI model was developed on a dataset of 57,250 frames (90% training/validation [including a 5-fold cross-validation] and 10% testing) obtained from 71 procedures. The model was evaluated based on its sensitivity, specificity, accuracy and area under the receiver operating curve (AUROC). Results: For HSIL/LSIL differentiation in the vagina, during the training/validation phase, the CNN demonstrated a mean sensitivity, specificity and accuracy of 98.7% (IC95% 96.7–100.0%), 99.1% (IC95% 98.1–100.0%), and 98.9% (IC95% 97.9–99.8%), respectively. The mean AUROC was 0.990 ± 0.004. During testing phase, the sensitivity was 99.6% and 99.7% for both specificity and accuracy. Conclusions: This is the first globally developed AI model capable of HSIL/LSIL differentiation in the vaginal region, demonstrating high and robust performance metrics. Its effective application paves the way for AI-powered colposcopic assessment across the entire female genital tract, offering a significant advancement in women's healthcare worldwide. [ABSTRACT FROM AUTHOR]

Simple Summary: This study investigates the correlation between 68Ga-PSMA PET/CT imaging and histopathological grading in treatment-naive prostate cancer patients. We retrospectively analyzed 86 patients who underwent 68Ga-PSMA PET/CT scans for prostate cancer staging, with a subset of 40 patients also undergoing radical prostatectomy. The PET/CT results, specifically SUVmax values, were compared with Gleason scores and PSA levels to assess their association with cancer grades. Results indicated a significant positive correlation between SUVmax and ISUP grades, suggesting that higher SUVmax values correspond to more advanced prostate cancer stages. Furthermore, the analysis of biopsy and radical prostatectomy pathology reports revealed a substantial rate of grading changes, underscoring the limitations of biopsy alone for accurate staging. These findings highlight the potential utility of 68Ga-PSMA PET/CT as a diagnostic tool in stratifying prostate cancer risk and guiding treatment decisions. Future studies are recommended to validate these observations and explore further applications of this imaging modality. Objective: This study aimed to evaluate the correlation between 68Ga-PSMA uptake in PSMA PET/CT in primary prostate cancer (PC) and its histopathological grading (Gleason score and ISUP grade). Additionally, we compared preoperative biopsy histopathological findings with definitive pathology results in radical prostatectomy (RP) specimens. Methods: We retrospectively analyzed 86 patients who underwent 68Ga-PSMA PET/CT for primary PC staging, of which 40 patients later underwent radical prostatectomy. PET/CT results, including SUVmax values, were correlated with GS and PSA concentrations. Histopathology reports were analyzed and compared between biopsy and final pathology results following RP. Results: A significant positive correlation was observed between SUVmax and ISUP grades (Pearson's ρ = 0.34, p < 0.001), with higher SUVmax values associated with more advanced grades. A cut-off SUVmax value of 5.64 was determined to predict upstaging in patients, yielding a sensitivity of 76% and a specificity of 60% (AUC = 0.82, 95% CI: 0.70–0.94). Additionally, 57.5% of patients experienced a grade shift following RP, with a 35% upgrade and 22.5% downgrade in ISUP grades. Conclusion: 68Ga-PSMA PET/CT demonstrated high sensitivity in detecting high-risk prostate cancer, particularly in patients with GS > 7 or PSA levels ≥ 10 ng/mL. The findings suggest that this imaging modality may be less effective for the staging of patients with lower GS or PSA values, that is, low-risk PCa. Further prospective studies are necessary to validate these results. [ABSTRACT FROM AUTHOR]

Simple Summary: Renal Cell Carcinoma is a common cancer in Western countries. To date, the gold standard treatment for localized non-metastatic disease is partial or radical nephrectomy. When surgical treatment is feasible, the prediction of postoperative renal function might influence the treatment algorithm. On the other hand, there is growing evidence indicating that immune response and nutritional status are crucial factors in human cancer development and progression. In this scenario, the Controlling Nutritional Status (CONUT) score was initially developed as a malnutrition screening tool. Its formula includes serum albumin levels, total lymphocyte count, and total serum cholesterol. Serum albumin is used as an indicator of protein reserves. Cholesterol is used as a caloric depletion parameter. Total lymphocyte count represents an indicator of immune defense impairment due to malnutrition. In this study, we evaluated the impact of the CONUT score on clinically significant decline in estimated glomerular filtration rate in patients with non-metastatic Clear Cell Renal Cell Carcinoma undergoing radical nephrectomy. Our findings confirmed that a preoperative high CONUT score is an independent predictor of a significant renal function decline after surgery. Being easy to use, cost effective, and ideally a completely automated tool, its preoperative assessment could be part of a personalized risk-stratification tailored to the clinical conditions and comorbidities of each patient. Background and Objectives: We aimed at evaluating the impact of Controlling Nutritional Status (CONUT) score on clinically significant decline in estimated glomerular filtration rate (eGFR) in patients with non-metastatic Clear Cell Renal Cell Carcinoma (ccRCC) undergoing radical nephrectomy (RN). Materials and methods: We retrospectively analyzed a multi-institutional cohort of 140 patients with ccRCC who underwent RN between 2016 and 2018 at three Urological Centers. The CONUT score was calculated with an algorithm including serum albumin, total lymphocyte count, and cholesterol. Clinical and pathologic features were analyzed using Fisher's exact test for categorical variables and a Mann–Whitney U test for continuous variables. To define the independent predictors of clinically significant eGFR decline, univariable (UVA) and multivariable (MVA) binomial logistic regression analyses were performed in order to assess the Odds Ratio (OR) with 95% Confidence Intervals (CIs). Results: The optimal cut-off value to discriminate between a low and high CONUT score was assessed by calculating the ROC curve. The area under the curve (AUC) was 0.67 (95%CI 0.59–0.78) with the most appropriate cut-off value at 2 points. Overall, 46 patients (32.9%) had a high CONUT score (>2). Statistically significant variables associated with eGFR decline at 24 months were age ≥ 70 (OR 2.01; 95%CI 1.17–3.09; p = 0.05), stage II–III chronic kidney disease (CKD) (OR 6.05; 95%CI 1.79–28.3; p = 0.001), and a high CONUT score (OR 3.98; 95%CI 1.58–10.4; p = 0.004). Conclusions: The CONUT score is a low-time-consuming, cost-effective, and promising tool able to preoperatively screen patients at risk of developing CKD after a RN. [ABSTRACT FROM AUTHOR]

Simple Summary: In patients with hepatocellular carcinoma (HCC), predicting survival after treatment is crucial for informed decision-making. This retrospective study investigated how muscle health (myosteatosis) and liver function (the albumin–bilirubin grade) influence survival outcomes in patients undergoing transarterial chemoembolization (TACE), resulting in the development of the Myo-ALBI prognostic score. The Myo-ALBI score was found to be a more accurate tool for predicting survival compared to existing methods. This study highlights the potential of the Myo-ALBI score to help clinicians personalize treatments and improve patient outcomes. Objective: This study aimed to investigate the prognostic value of preoperative myosteatosis and the albumin–bilirubin (ALBI) grade in patients with hepatocellular carcinoma (HCC) undergoing transarterial chemoembolization (TACE) and develop a robust prognostic score based on these factors. Methods: Patients with HCC who underwent TACE between January 2009 and December 2020 were included. Multivariate Cox regression analysis identified prognostic factors. CT-based body composition parameters were acquired from baseline abdominal CT images at the level of the third lumbar vertebra. A prognostic score (Myo-ALBI) was developed based on the presence of preoperative myosteatosis and the ALBI grade, and its prognostic value was evaluated. Results: Of 446 patients, 63% were male, and the mean age was 62.4 years. Preoperative myosteatosis was present in 41.5% of patients. The BCLC stages were mostly B (67.9%). Multivariate analysis shows that preoperative myosteatosis, ALBI grade 2, and ALBI grade 3 were independent prognostic factors. The Myo-ALBI grade was incorporated into a prognostic model, including alpha-fetoprotein and up-to-seven criteria, to generate a nomogram. The C-index of the nomogram based on the Myo-ALBI grade (0.743) was significantly higher than the non-Myo-ALBI nomogram (0.677), the up-to-seven criteria (0.653), the ALBI grade (0.616), and the Child–Pugh class (0.573) (all p < 0.05). The t-ROC curve for the nomogram was consistently superior to the other models throughout the observation period in all patients and the BCLC-B subgroup. Conclusions: The combination of preoperative CT-derived myosteatosis and ALBI grade enhances prognostication for patients with unresectable HCC undergoing TACE. The Myo-ALBI nomogram constructed in this study could support individualized prognosis prediction, assisting in treatment decision-making for HCC patients. [ABSTRACT FROM AUTHOR]

Simple Summary: Multi-parametric MRI is a first-line imaging modality for prostate cancer detection. Magnetic resonance elastography (MRE) is a useful tool for measuring parenchymal stiffness to diagnose liver fibrosis. A known physical characteristic of prostate cancer is that it is harder than a normal prostate gland. We hypothesized that the quantitative stiffness value derived from MRE could be used to discriminate prostate cancer from benign prostate hyperplasia and normal parenchyma. Until now, the application of MRE to prostate cancer has been sporadic; it has only been used for investigational purposes due to the uncomfortable perineal placement of the acoustic device and inconvenience to patients during preparation. Therefore, we attempted to place an acoustic driver on the lower abdominal wall and determined that detecting and classifying prostate cancer via MRE is feasible. Our observation of 75 consecutive patients revealed that the stiffness value of prostate cancer was significantly different from normal parenchyma, and an accuracy of 87% was estimated at a cutoff value of 4.2 kPa in discriminating prostate cancer from normal parenchyma. In terms of differentiating prostate cancer from benign prostate hyperplasia, an accuracy of 62% was estimated. Additionally, the stiffness values tended to increase as the ISUP grade increased. This observation suggests that the stiffness value derived from pelvic MRE is helpful for detecting and classifying prostate cancer and could be an adjunct to multi-parametric MRI. We investigated the feasibility of magnetic resonance elastography (MRE) using a pelvic acoustic driver for the detection and classification of prostate cancer (PCa). A total of 75 consecutive patients (mean age, 70; range, 56–86) suspected of having PCa and who underwent multi-parametric MRI including MRE and subsequent surgical resection were included. The analyzed regions consisted of cancer (n = 69), benign prostatic hyperplasia (BPH) (n = 70), and normal parenchyma (n = 70). A histopathologic topographic map served as the reference standard for each region. One radiologist and one pathologist performed radiologic–pathologic correlation, and the radiologist measured stiffness values in each region of interest on elastograms automatically generated by dedicated software. Paired t-tests were used to compare stiffness values between two regions. ROC curve analysis was also used to extract a cutoff value between two regions. The stiffness value of PCa (unit, kilopascal (kPa); 4.9 ± 1.1) was significantly different to that of normal parenchyma (3.6 ± 0.3, p < 0.0001) and BPH (4.5 ± 1.4, p = 0.0454). Under a cutoff value of 4.2 kPa, a maximum accuracy of 87% was estimated, with a sensitivity of 73%, a specificity of 99%, and an AUC of 0.839 for discriminating PCa from normal parenchyma. Between PCa and BPH, a maximum accuracy of 62%, a sensitivity of 70%, a specificity of 56%, and an AUC of 0.598 were estimated at a 4.5 kPa cutoff. The stiffness values tended to increase as the ISUP grade increased. In conclusion, it is feasible to detect and classify PCa using pelvic MRE. Our observations suggest that MRE could be a supplement to multi-parametric MRI for PCa detection. [ABSTRACT FROM AUTHOR]

Simple Summary: Each patient responds uniquely to treatment, which makes personalized ultra-fractionated stereotactic adaptive radiotherapy (PULSAR) a promising strategy that delivers high-dose radiation at extended intervals for tailored adaptation. Currently, treatment modifications mainly rely on physicians' assessments of tumor size changes. Our study aims to develop a more objective multiomics-based approach for predicting treatment outcomes in PULSAR, including radiomics, dosiomics, and delta features. By leveraging multiomics analysis and machine learning, we intend to transition the adaptation and decision-making process from empirical judgments to a more data-informed strategy, allowing clinicians to swiftly respond to changes in tumor behavior and provide more personalized treatment for each patient. Objectives: This retrospective study aims to develop a multiomics approach that integrates radiomics, dosiomics, and delta features to predict treatment responses in brain metastasis (BM) patients undergoing PULSAR. Methods: A retrospective study encompassing 39 BM patients with 69 lesions treated with PULSAR was undertaken. Radiomics, dosiomics, and delta features were extracted from both pre-treatment and intra-treatment MRI scans alongside dose distributions. Six individual models, alongside an ensemble feature selection (EFS) model, were evaluated. The classification task focused on distinguishing between two lesion groups based on whether they exhibited a volume reduction of more than 20% at follow-up. Performance metrics, including sensitivity, specificity, accuracy, precision, F1 score, and the area under the receiver operating characteristic (ROC) curve (AUC), were assessed. Results: The EFS model integrated the features from pre-treatment radiomics, pre-treatment dosiomics, intra-treatment radiomics, and delta radiomics. It outperformed six individual models, achieving an AUC of 0.979, accuracy of 0.917, and F1 score of 0.821. Among the top nine features of the EFS model, six features came from post-wavelet transformation and three from original images. Conclusions: The study demonstrated the feasibility of employing a data-driven multiomics approach to predict treatment outcomes in BM patients receiving PULSAR treatment. Integrating multiomics with intra-treatment decision support in PULSAR shows promise for optimizing patient management and reducing the risks of under- or over-treatment. [ABSTRACT FROM AUTHOR]

Simple Summary: Non-iodine avid differentiated thyroid cancer (DTC) may be a diagnostic problem, especially in patients with an indeterminate response to treatment (i.e., with thyroglobulin (Tg) concentration in the range of 1–10 ng/mL). PET/CT with [18F]FDG may be a useful technique for visualizing non-iodine avid DTC lesions. Presented study assessed the usefulness of using exogenous stimulation with recombinant human TSH (rhTSH) before PET/CT with [18F]FDG in detecting non-iodine avid foci of DTC in patients with elevated sTg and negative 131I WBS and the usefulness of Tg concentration in predicting a positive result of [18F]FDG PET/CT in this type of patients and to determine the optimal Tg cut-off point for obtaining a positive [18F]FDG PET/CT result. In a retrospective analysis including 73 patients with DTC suspected of having non-iodine avid recurrence or metastases there was no effect of rhTSH stimulation on the sensitivity and specificity of PET/CT, but a positive impact on the number of lesions visible in the examination was observed. Moreover, rhTSH stimulation allowed for visualization of non-iodine avid lesions with lower Tg concentration. Introduction: Non-iodine avid metastases of differentiated thyroid cancer (DTC) can be found using PET/CT with a fluorine-18-labeled glucose analog ([18F]FDG). There are ongoing discussions on the appropriateness of using exogenous thyrotropin (TSH) stimulation before this examination. Material and Methods: In a retrospective study, 73 PET/CT scans with [18F]FDG performed after exogenous stimulation with recombinant human TSH (rhTSH) and without such stimulation were analyzed. All analyzed patients were suspected of having non-iodine-avid foci of DTC. Results: The stimulation with rhTSH before the PET/CT did not affect the percentage of positive results: 37.5% (18/48) with rhTSH and 40% (10/25) without rhTSH (p = 0.83). The analysis of the ROC curves established the cut-off thyroglobulin point for a positive PET/CT result separately for both subgroups. There was no statistically significant difference between obtaining a positive PET/CT result and the baseline thyroglobulin concentration (both stimulated and unstimulated). The exogenous stimulation of TSH prior to the PET/CT had no effect on the [18F]FDG uptake in the PET/CT lesions. Conclusions: PET/CT with [18F]FDG remains a useful method for the diagnosis of non-iodine-avid DTC lesions; in the presented group, a positive effect of rhTSH stimulation on the number of DTC foci visible in the PET/CT was found, but without affecting its effectiveness. [ABSTRACT FROM AUTHOR]

Simple Summary: Nasopharynx cancer treatment often involves radiation therapy, but choosing the best method can be challenging. This study compares two advanced radiation techniques: one using X-rays and another using protons. Both aim to target the tumor while sparing healthy tissues, but their effectiveness can vary based on the cancer's location and stage. Researchers want to determine which technique works best for different patients, particularly those with cancer close to sensitive brain structures. By analyzing treatment plans for 28 patients, we developed guidelines to help doctors choose the most suitable technique. This research could lead to more personalized and effective treatments, potentially improving outcomes and quality of life for patients with nasopharynx cancer. The findings may also help healthcare providers use resources more efficiently, benefiting both patients and the broader medical community. Background: Proton therapy requires caution when treating patients with targets near neural structures. Intuitive and quantitative guidelines are needed to support decision-making concerning the treatment modality. This study compared dosimetric profiles of intensity-modulated proton therapy (IMPT) and intensity-modulated radiation therapy (IMRT) using helical tomotherapy (HT) for adaptive re-planning in cT3-4 nasopharyngeal cancer (NPCa) patients, aiming to establish criteria for selecting appropriate treatment modalities. Methods: HT and IMPT plans were generated for 28 cT3-4 NPCa patients undergoing definitive radiotherapy. Dosimetric comparisons were performed for target coverage and high-priority organs at risk (OARs). The correlation between dosimetric parameters and RT modality selection was analyzed with the target OAR distances. Results: Target coverages were similar, while IMPT achieved better dose spillage. HT was more favorable for brainstem D1, optic chiasm Dmax, optic nerves Dmax, and p-cord D1. IMPT showed advantages for oral cavity Dmean. Actually, 14 IMPT and 14 HT plans were selected as adaptive plans, with IMPT allocated to most cT3 patients (92.9% vs. 42.9%, p = 0.013). The shortest distances from the target to neural structures were negatively correlated with OAR doses. Receiver operating characteristic curve analyses were carried out to discover the optimal cut-off values of the shortest distances between the target and the OARs (temporal lobes and brainstem), which were 0.75 cm (AUC = 0.908, specificity = 1.00) and 0.85 cm (AUC = 0.857, specificity = 0.929), respectively. Conclusions: NPCa patients with cT4 tumor or with the shortest distance between the target and critical neural structures < 0.8 cm were suboptimal candidates for IMPT adaptive re-planning. These criteria may improve resource utilization and clinical outcomes. [ABSTRACT FROM AUTHOR]

Simple Summary: This study aimed to develop and validate a radiomic model for predicting overall survival (OS) in glioblastoma multiforme (GBM) patients using pre-treatment MRI images. A retrospective dataset of 289 patients from multiple institutions was used to extract 660 radiomic features (RFs) from each patient's tumor volume. The initial model was enhanced by incorporating clinical variables and validated through repeated three-fold cross-validation. The final clinical–radiomic model utilized primary gross tumor volume (GTV) and T2-FLAIR MRI modality and includes the age variable and two robust RFs. The model achieved a moderately good discriminatory performance (C-Index: 0.69) and significant patient stratification (p = 7 × 10−5) on the validation cohort. Notably, the trained model exhibited the highest integrated area under curve (iAUC) at 11 months (0.81) in the literature. The study concluded that the validated clinical–radiomic model can effectively stratify GBM patients into low and high-risk groups based on OS. Future work will focus on integrating deep learning-based features and standardized convolutional filters to improve OS predictions. Purpose: To develop and validate an MRI-based radiomic model for predicting overall survival (OS) in patients diagnosed with glioblastoma multiforme (GBM), utilizing a retrospective dataset from multiple institutions. Materials and Methods: Pre-treatment MRI images of 289 GBM patients were collected. From each patient's tumor volume, 660 radiomic features (RFs) were extracted and subjected to robustness analysis. The initial prognostic model with minimum RFs was subsequently enhanced by including clinical variables. The final clinical–radiomic model was derived through repeated three-fold cross-validation on the training dataset. Performance evaluation included assessment of concordance index (C-Index), integrated area under curve (iAUC) alongside patient stratification into low and high-risk groups for overall survival (OS). Results: The final prognostic model, which has the highest level of interpretability, utilized primary gross tumor volume (GTV) and one MRI modality (T2-FLAIR) as a predictor and integrated the age variable with two independent, robust RFs, achieving moderately good discriminatory performance (C-Index [95% confidence interval]: 0.69 [0.62–0.75]) with significant patient stratification (p = 7 × 10−5) on the validation cohort. Furthermore, the trained model exhibited the highest iAUC at 11 months (0.81) in the literature. Conclusion: We identified and validated a clinical–radiomic model for stratification of patients into low and high-risk groups based on OS in patients with GBM using a multicenter retrospective dataset. Future work will focus on the use of deep learning-based features, with recently standardized convolutional filters on OS tasks. [ABSTRACT FROM AUTHOR]

Simple Summary: Lung cancer is the most common form of cancer globally, making early detection essential for improving patient outcomes. In this study, deep learning methods were used to analyze CT lung images to detect cancer at an early stage. Several pre-trained models were employed, with InceptionResNetV2 achieving the highest detection accuracy of 98.5%. When cancer was detected, the extent of the tumor area was determined through segmentation models. The most accurate results were obtained using the InceptionUNet model, which achieved a Jaccard index of 95.3% in identifying the tumor area. These findings demonstrate the potential of deep learning for enhancing both the detection and localization of lung cancer, which may contribute to more effective treatment strategies. Background: Lung cancer is the leading cause of cancer-related deaths worldwide, ranking first in men and second in women. Due to its aggressive nature, early detection and accurate localization of tumors are crucial for improving patient outcomes. This study aims to apply advanced deep learning techniques to identify lung cancer in its early stages using CT scan images. Methods: Pre-trained convolutional neural networks (CNNs), including MobileNetV2, ResNet152V2, InceptionResNetV2, Xception, VGG-19, and InceptionV3, were used for lung cancer detection. Once the disease was identified, the tumor's region was segmented using models such as UNet, SegNet, and InceptionUNet. Results: The InceptionResNetV2 model achieved the highest detection accuracy of 98.5%, while UNet produced the best segmentation results, with a Jaccard index of 95.3%. Conclusions: The study demonstrates the effectiveness of deep learning models, particularly InceptionResNetV2 and UNet, in both detecting and segmenting lung cancer, showing significant potential for aiding early diagnosis and treatment. Future work could focus on refining these models and exploring their application in other medical domains. [ABSTRACT FROM AUTHOR]

Simple Summary: The optimal selection of patients with advanced high-grade serous ovarian cancer (HGSOC) who are likely to benefit from upfront cytoreductive surgery remains challenging. With the results of the TRUST trial, the fifth randomized phase III trial comparing oncologic outcomes of primary versus interval cytoreductive surgery, expected to be presented soon, there is a high unmet clinical need to define novel biomarkers to optimize pretherapeutic patient assessment and allow for more personalized clinical decision making. Building on the growing evidence of the predictive and prognostic value of fibrinogen in various solid cancers, this study is the first to observe an independent association between the "Fibrinogen–Albumin-Ratio Index" (FARI) and surgical outcomes in patients with advanced HGSOC undergoing primary cytoreductive surgery. Given that the FARI seems to act as a surrogate for intra-abdominal tumor load, the further clinical validation of this cost-effective and readily available biomarker appears promising. Background/Objectives: The present study evaluates predictive implications of the pretherapeutic Fibrinogen–Albumin-Ratio Index (FARI) in high-grade serous ovarian cancer (HGSOC) patients undergoing primary cytoreductive surgery. Methods: This retrospective study included 161 patients with HGSOC International Federation of Gynecology and Obstetrics (FIGO) stage ≥ IIb, who underwent primary cytoreductive surgery followed by platinum-based chemotherapy. Associations between the FARI and complete tumor resection status were described by receiver operating characteristics, and binary logistic regression models were fitted. Results: Higher preoperative FARI values correlated with higher ascites volumes (r = 0.371, p < 0.001), and higher CA125 levels (r = 0.271, p = 0.001). A high FARI cut at its median (≥11.06) was associated with lower rates of complete tumor resection (OR 3.13, 95% CI [1.63–6.05], p = 0.001), and retrained its predictive value in a multivariable model independent of ascites volumes, CA125 levels, FIGO stage, and Charlson Comorbidity Index (CCI). Conclusions: The FARI appears to act as a surrogate for higher intra-abdominal tumor load. After clinical validation, FARI could serve as a readily available serologic biomarker to complement preoperative patient assessment, helping to identify patients who are likely to achieve complete tumor resection during primary cytoreductive surgery. [ABSTRACT FROM AUTHOR]

Simple Summary: The prevalence of indeterminate pulmonary nodule (IPN) findings in early lung cancer screening settings highlights the need for novel imaging biomarkers to assist clinicians in making informed therapeutic decisions. The surrounding vasculature of pulmonary nodules, termed "macro-vasculature", has been identified as a potential biomarker for evaluating nodule malignancy. However, the relationship between the macro-vasculature's arteries and veins surrounding an IPN and its malignancy remains unclear. This study aimed to investigate this association. Our findings indicate that arterial characteristics significantly outweigh venous characteristics in distinguishing malignant from benign nodules. Additionally, incorporating arterial information surrounding a nodule enhances the performance in differentiating malignant from benign nodules. Clarifying the relationship between macro-vasculature arteries and nodule malignancy may facilitate clinical follow-up procedures for screen-detected pulmonary nodules. Objective: This study aims to investigate the association between the arteries and veins surrounding a pulmonary nodule and its malignancy. Methods: A dataset of 146 subjects from a LDCT lung cancer screening program was used in this study. AI algorithms were used to automatically segment and quantify nodules and their surrounding macro-vasculature. The macro-vasculature was differentiated into arteries and veins. Vessel branch count, volume, and tortuosity were quantified for arteries and veins at different distances from the nodule surface. Univariate and multivariate logistic regression (LR) analyses were performed, with a special emphasis on the nodules with diameters ranging from 8 to 20 mm. ROC-AUC was used to assess the performance based on the k-fold cross-validation method. Average feature importance was evaluated in several machine learning models. Results: The LR models using macro-vasculature features achieved an AUC of 0.78 (95% CI: 0.71–0.86) for all nodules and an AUC of 0.67 (95% CI: 0.54–0.80) for nodules between 8–20 mm. Models including macro-vasculature features, demographics, and CT-derived nodule features yielded an AUC of 0.91 (95% CI: 0.87–0.96) for all nodules and an AUC of 0.82 (95% CI: 0.71–0.92) for nodules between 8–20 mm. In terms of feature importance, arteries within 5.0 mm from the nodule surface were the highest-ranked among macro-vasculature features and retained their significance even with the inclusion of demographics and CT-derived nodule features. Conclusions: Arteries within 5.0 mm from the nodule surface emerged as a potential biomarker for effectively discriminating between malignant and benign nodules. [ABSTRACT FROM AUTHOR]

Simple Summary: This study investigated the impact of radiation doses to the heart and lungs on overall survival (OS) in patients with locally advanced non-small-cell lung cancer (LA-NSCLC) treated with radiotherapy. An analysis of 120 patients, each with exactly three years of follow-up, revealed that higher radiation doses to the heart and lungs were significantly associated with worse OS. Importantly, the combination of heart and lung radiation doses provided enhanced and more detailed risk stratification, making it a more powerful predictor of poor survival than individual doses alone. These findings suggest that minimizing combined radiation exposure to both organs may improve survival outcomes in LA-NSCLC patients. Background/Objectives: Despite advancements in treatment for patients with unresectable locally advanced non-small cell lung cancer (LA-NSCLC), overall survival (OS) remains poor. The specific effects of varying heart and lung doses on OS in LA-NSCLC patients have not been thoroughly investigated, especially their combined impact on survival. This study aimed to examine the impact on OS of both individual and combined heart and lung doses in patients with LA-NSCLC treated with radiotherapy over a three-year follow-up period. Methods: A total of 120 patients who received definitive radiotherapy for LA-NSCLC (stage III, 92.5%) from January 2015 to January 2020 were retrospectively reviewed. The endpoint in this study was OS. Each patient was followed for a fixed period of three years. Results: Univariate Cox regression analysis showed that OS was significantly related to mean heart dose (MHD, hazard ratio [HR], 3.4 [1.8–6.3]; p < 0.001), pericardium V40 (HR, 3.2 [1.7–6.0]; p < 0.001), and total lung V20 (HR, 2.6 [1.4–5.0]; p = 0.003), and these were independent predictors for worse OS in multivariate analysis. Kaplan–Meier curve analysis with log-rank tests revealed that survival was significantly worse in patients with higher MHD (p < 0.001), pericardium V40 (p < 0.001), and total lung V20 (p = 0.002). Combining MHD and total lung V20, and pericardium V40 and total lung V20 provided enhanced risk stratification for OS (p < 0.001 for both combinations). Conclusions: The combination of heart and lung doses provided enhanced and more detailed risk stratification in prediction of OS for a fixed period of three years in LA-NSCLC patients treated with radiotherapy. [ABSTRACT FROM AUTHOR]

Simple Summary: Thyroid cancer is very common, with approximately 580,000 cases reported worldwide in 2020. Proper evaluation and management are necessary to ensure maximum patient care. It is important to consider the entire thyroid stimulating hormone (TSH) test results rather than the average or partial TSH test results to accurately evaluate the TSH status of patients with low-risk papillary thyroid carcinoma (PTC) after lobectomy. In patients with low-risk PTC after lobectomy, recurrence-free survival can be worse if the TSH status of patients, despite fulfilling the 2015 American Thyroid Association guideline recommendations, is maintained below a certain percentage among the total number of TSH tests during the postoperative follow-up period. Clinicians should make deliberate efforts to maintain the postoperative TSH status of patients with low-risk PTC who underwent lobectomy within an appropriate level during the postoperative follow-up period using thorough examinations. Background: The 2015 American Thyroid Association guidelines recommend the maintenance of serum thyroid stimulating hormone (TSH) levels ≤2 mIU/L in patients with low-risk papillary thyroid carcinoma (PTC) who underwent lobectomy; however, the evidence is insufficient. We investigated the association between maintaining the TSH status at ≤2 mIU/L and tumor recurrence in patients with low-risk PTC who underwent lobectomy through a 5-year landmark analysis. Methods: Between 2010 and 2016, 662 patients with low-risk PTC were included. The postoperative TSH status was determined using the 'TSH > 2 ratio', which was calculated using the TSH test results during the 5-year follow-up. The optimal cutoff value of 'TSH > 2 ratio' for tumor recurrence was determined using a receiver operating characteristic curve analysis. Recurrence-free survival (RFS) was compared between the groups using Kaplan–Meier and Cox proportional hazard regression analyses. Results: Patients with 'TSH > 2 ratio' > 0.1833 (n = 498) had a worse RFS outcome compared to patients with 'TSH > 2 ratio' ≤ 0.1833 (n = 164; p < 0.001). 'TSH > 2 ratio' > 0.1833 was a significant risk factor for tumor recurrence after the 5-year landmark (hazard ratio: 4.795, 95% confidence interval: 2.102–10.937, p < 0.001). Conclusions: Maintaining TSH levels ≤ 2 mIU/L below a certain percentage among the total TSH tests during the 5-year follow-up period has a negative impact on tumor recurrence. [ABSTRACT FROM AUTHOR]

Simple Summary: Colorectal cancer is one of the leading causes of cancer-related deaths worldwide. Traditional methods for predicting patient outcomes rely heavily on the physical characteristics of tumors. Our research aims to develop a new, simple risk score that uses three specific molecular markers found in tumor tissues. By examining the presence and levels of these markers, we hope to better predict which patients have a higher risk of poor outcomes. This can help doctors make more informed decisions about treatment options. Our findings may lead to improved survival rates by identifying high-risk patients who need more aggressive treatment and sparing low-risk patients from unnecessary procedures. Introduction: Several new molecular markers in colorectal carcinomas have been discovered; however, classical histopathological predictors are still being used to predict survival in patients. We present a novel risk score, which uses molecular markers, to predict outcomes in patients with colorectal carcinoma. Methods: The immunohistochemistry of tissue micro arrays was used to detect and quantify H2BUB1, RBM3 and Ki-67. Different intensities of staining were categorized for these markers and a score was established. A multivariate analysis was performed and survival curves were established. Results: 1791 patients were evaluated, and multivariate analysis revealed that our risk score, the 3-biomarker classifier, is an independent marker to predict survival. We found a high risk-score to be associated with dismal median survival for the patients. Conclusions: A more personalized score might be able to better discriminate low- and high-risk patients and suggest adjuvant treatment compared to classical pathological staging. Our score can serve as a tool to predict outcomes in patients suffering from colorectal carcinoma. [ABSTRACT FROM AUTHOR]

Simple Summary: Cutaneous melanoma (CM) is an aggressive skin cancer that develops from melanocytic cells. The most important prognostic factor is still the vertical tumour thickness according to Breslow. Liver function is associated with better overall patient outcomes and is currently under increasing investigation in cancer patients. Current findings show that liver function is an important factor in different tumour entities and represents a potential biomarker. Therefore, we aimed to evaluate liver metabolism by using liver scores in CM. High tumour thickness (≥1.66 mm) and aspartate transaminase-to-platelet ratio index (APRI ≥ 0.2241) at the initial diagnosis were associated with a worse prognosis in stage I and II melanoma. Background: Neoadjuvant and adjuvant therapies are currently getting increasingly important in cutaneous melanoma (CM) management. However, there is still a lack of prognostic tools to identify which patients have a poor prognosis. There is increasing evidence that the liver score may be a potential prognostic parameter in different tumour types. The aim was to investigate whether established liver scores can establish the prognosis of CM. Methods: According to established methods, the APRI, the MELD score, the MELD-Na score and the De Ritis ratio were calculated from the laboratory values at the time of the initial diagnosis. Survival was compared with the Kaplan–Meier curve and tested with log-rank tests. Risk factors associated with cutaneous melanoma-specific survival (CMSS) and progression-free survival (PFS) were assessed by using the Cox proportional hazards regression model. To determine the diagnostic accuracy, we performed a time-dependent ROC analysis. Results: A total of 423 patients were included, including 141 patients in AJCC stage (2017) I (33.3%), 82 in stage II (19.4%), 128 in stage III (30.3%) and 72 in stage IV (17%). Median time until melanoma-specific death was 99 months (IQR: 37–126). In addition, 37.6% of patients relapsed with a median time to relapse of 88 months (IQR: 17.5–126). In all stages, tumour thickness and ulceration were independent markers for predicting CMSS and PFS (p < 0.05). The multivariable analysis with all stages showed no significant association with CM outcome for liver scores (p > 0.05). The subgroup analysis revealed that the APRI (≥0.2241) was associated with CMSS and PFS in melanoma stages I and II, independently of tumour thickness, age and ulceration (HR 2.57, 95% CI 1.14–5.75; HR 2.94, 95% CI 1.42–6.09, respectively). Conclusions: The 20-year prognosis of AJCC stage I and II CM was dependent on tumour thickness and the APRI. High tumour thickness and an APRI ≥ 0.2241 at the initial diagnosis were associated with a worse prognosis. Future studies should investigate the independent prognostic value of the APRI in low-stage CM. Furthermore, the APRI score could be a potential biomarker for nomograms. [ABSTRACT FROM AUTHOR]

Simple Summary: This study assessed the preoperative diagnostic efficacy of the apparent diffusion coefficient on diffusion-weighted magnetic resonance imaging for identifying lymph node metastasis in biliary tract cancer, comparing it with the diagnostic efficacy of short-axis and long-axis diameters of lymph nodes measured by computed tomography. The results demonstrated that the minimum ADC value provided the highest diagnostic accuracy. Objective: The diagnostic efficacy of the apparent diffusion coefficient (ADC) in diffusion-weighted magnetic resonance imaging (DW-MRI) for lymph node metastasis in biliary tract cancer was investigated in the present study. Methods: In total, 112 surgically resected lymph nodes from 35 biliary tract cancer patients were examined in this study. The mean and minimum ADC values of the lymph nodes as well as the long-axis and short-axis diameters of the lymph nodes were assessed by computed tomography (CT). The relationship between these parameters and the presence of histological lymph node metastasis was evaluated. Results: Histological lymph node metastasis was detected in 31 (27.7%) out of 112 lymph nodes. Metastatic lymph nodes had a significantly larger short-axis diameter compared with non-metastatic lymph nodes (p = 0.002), but the long-axis diameter was not significantly different between metastatic and non-metastatic lymph nodes. The mean and minimum ADC values for metastatic lymph nodes were significantly reduced compared with those for non-metastatic lymph nodes (p < 0.001 for both). However, the minimum ADC value showed the highest accuracy for the diagnosis of histological lymph node metastasis, with an area under the curve of 0.877, sensitivity of 87.1%, specificity of 82.7%, and accuracy of 83.9%. Conclusions: The minimum ADC value in DW-MRI is highly effective for the diagnosis of lymph node metastasis in biliary tract cancer. Accurate preoperative diagnosis of lymph node metastasis in biliary tract cancer should enable the establishment of more appropriate treatment strategies. [ABSTRACT FROM AUTHOR]

Simple Summary: This study investigates the influence of various pharmacokinetic parameters on 177Lu-PSMA therapies via physical, biological, and statistical measures. Employing a clinically validated physiologically based pharmacokinetic (PBPK) model, realistic time–activity curves (TACs) in tumors, salivary glands, and kidneys are generated, allowing for the calculation of metrics such as AUC, dose, BED, and fBED. The results demonstrate the significant impact of multiple parameters on the measured outcomes. In addition to the great impact of administered ligand amount, tumor volume, and receptor density, other pharmacokinetic parameters such as rates of radiopharmaceutical association, internalization, and release were identified as key influencers. Notably, alterations in the parameters induced distinct modifications in TAC features, affecting radiobiological, pharmacokinetic, and statistical aspects. These insights contribute to advancing personalized treatment regimens by understanding the key contributions of various parameters towards improving therapeutic efficacy while minimizing radiation-related toxicities. Purpose: To investigate the impact of physiologically based pharmacokinetic (PBPK) parameters on physical, biological, and statistical measures in lutetium-177-labeled radiopharmaceutical therapies (RPTs) targeting the prostate-specific membrane antigen (PSMA). Methods: Using a clinically validated PBPK model, realistic time–activity curves (TACs) for tumors, salivary glands, and kidneys were generated based on various model parameters. These TACs were used to calculate the area-under-the-TAC (AUC), dose, biologically effective dose (BED), and figure-of-merit BED (fBED). The effects of these parameters on radiobiological, pharmacokinetic, time, and statistical features were assessed. Results: Manipulating PBPK parameters significantly influenced AUC, dose, BED, and fBED outcomes across four different BED models. Higher association rates increased AUC, dose, and BED values for tumors, with minimal impact on non-target organs. Increased internalization rates reduced AUC and dose for tumors and kidneys. Higher serum protein-binding rates decreased AUC and dose for all tissues. Elevated tumor receptor density and ligand amounts enhanced uptake and effectiveness in tumors. Larger tumor volumes required dosimetry adjustments to maintain efficacy. Setting the tumor release rate to zero intensified the impact of association and internalization rates, enhancing tumor targeting while minimizing the effects on salivary glands and kidneys. Conclusions: Optimizing PBPK parameters can enhance the efficacy of lutetium-177-labeled RPTs targeting PSMA, providing insights for personalized and effective treatment regimens to minimize toxicity and improve therapeutic outcomes. [ABSTRACT FROM AUTHOR]

Simple Summary: Preoperative risk prediction prior to oncologic esophagectomy is crucial for assisting surgeons in accurate patient selection and patients in their informed decision making. A new risk stratification tool, the IESG prediction model, was recently introduced, categorizing patients into different risk levelsMachine learning is a subfield of artificial intelligence and may allow for a more accurate identification of patients at risk. Therefore, we evaluated the IESG risk model and compared its performance with ML models. We found that the IESG risk model provided an overall adequate risk estimation. However, ML showed better results in the accurate risk stratification of patients, demonstrating its potential as a novel and powerful approach for future patient assessment. Risk prediction prior to oncologic esophagectomy is crucial for assisting surgeons and patients in their joint informed decision making. Recently, a new risk prediction model for 90-day mortality after esophagectomy using the International Esodata Study Group (IESG) database was proposed, allowing for the preoperative assignment of patients into different risk categories. However, given the non-linear dependencies between patient- and tumor-related risk factors contributing to cumulative surgical risk, machine learning (ML) may evolve as a novel and more integrated approach for mortality prediction. We evaluated the IESG risk model and compared its performance to ML models. Multiple classifiers were trained and validated on 552 patients from two independent centers undergoing oncologic esophagectomies. The discrimination performance of each model was assessed utilizing the area under the receiver operating characteristics curve (AUROC), the area under the precision–recall curve (AUPRC), and the Matthews correlation coefficient (MCC). The 90-day mortality rate was 5.8%. We found that IESG categorization allowed for adequate group-based risk prediction. However, ML models provided better discrimination performance, reaching superior AUROCs (0.64 [0.63–0.65] vs. 0.44 [0.32–0.56]), AUPRCs (0.25 [0.24–0.27] vs. 0.11 [0.05–0.21]), and MCCs (0.27 ([0.25–0.28] vs. 0.15 [0.03–0.27]). Conclusively, ML shows promising potential to identify patients at risk prior to surgery, surpassing conventional statistics. Still, larger datasets are needed to achieve higher discrimination performances for large-scale clinical implementation in the future. [ABSTRACT FROM AUTHOR]

Simple Summary: Studies analyzing specific treatment-related prognostic factors can provide important information about disease biology and improve the use of biomarkers to optimize treatment decisions. The aim of our retrospective study was to determine the prognostic performance of clinicopathological factors and blood biomarkers in patients with unresectable metastatic melanoma treated with BRAF and MEK inhibitors. A total of 199 patients were included in the multivariate analysis of the risk of progression and death. We found that primary tumor localization on the limbs, Clark invasion level V, M1c stage or M1d stage at the start of therapy, and elevated baseline serum S100B level were independently and significantly associated with poor outcomes. The present study suggests that clinicopathological factors, including primary tumor characteristics and stage of metastatic disease, as well as serum markers may provide information on the probability of survival in patients with advanced melanoma treated with BRAF and MEK inhibitors. Prognostic studies can provide important information about disease biology and improve the use of biomarkers to optimize treatment decisions. Methods: A total of 199 patients with advanced melanoma treated with BRAF + MEK inhibitors were included in our single-center retrospective study. We analyzed the risk of progression and death using multivariate Cox proportional hazard models. The predictive effect of prognostic factors on progression-free survival (PFS) was evaluated in ROC analysis. Results: We found that primary tumor localization, Clark level, pT category, baseline M stage and baseline serum S100B are independent and significant prognostic factors for PFS. The discriminative power of the combination of these factors was excellent for predicting 18 month PFS (AUC 0.822 [95% CI 0.727; 0.916], p < 0.001). Primary tumor localization on the extremities, Clark level V, baseline M1c stage or M1d stage, and elevated baseline serum S100B and LDH levels were independently and significantly associated with unfavorable overall survival (OS). Conclusion: Baseline M stage and serum S100B appear to be independent prognostic factors for both PFS and OS in melanoma patients treated with BRAF + MEK inhibitors. We newly identified significant and independent prognostic effects of primary tumor localization and Clark level on survival that warrant further investigation. [ABSTRACT FROM AUTHOR]

Simple Summary: Total thyroidectomy and dissection of cervical lymph node compartments, depending on serum calcitonin levels and ultrasound findings, is standard treatment for patients with medullary thyroid cancer. The aim of this study was to evaluate whether pre-operative calcitonin and CEA levels can be useful as biomarkers of the extent of lymph node metastases at diagnosis. Results indicate that pre-operative serum calcitonin and CEA levels can predict presence, number, and site of lymph node metastases and, more specifically, values of 90 pg/mL for calcitonin and 17 ng/mL for CEA accurately indicate the N1b status. Since surgery is the only curative treatment for medullary thyroid cancer and there is not a strong indication regarding the extent of lymphadenectomy, these findings may help in the choice of the extent of neck dissection. Background: In medullary thyroid cancer (MTC), lymph node metastases are often present at diagnosis and the extent of surgery is usually based upon pre-operative calcitonin and CEA levels as well as ultrasound findings. The aim of this study was to evaluate the role of pre-operative calcitonin and CEA levels as predictive markers of the burden of lymph node metastases at diagnosis. Methods: we conducted a retrospective study analyzing 87 MTC patients. Results: The median levels of calcitonin and CEA were 88.4 pg/mL and 7.0 ng/mL, respectively, in patients with no lymph nodes metastases; 108.0 pg/mL and 9.6 ng/mL, respectively, in patients with metastases to 1–5 lymph nodes; 520.5 pg/mL and 43.2 ng/mL, respectively, in patients with metastases to >5 lymph nodes. There were no significant differences in pre-operative calcitonin and CEA values between N0 and N1a patients, whereas they were significantly higher in N1b patients. Pre-operative cut-off levels distinguishing N0/N1a from N1b patients were 90 pg/mL for calcitonin (sensitivity 100%, specificity 59.3%, AUC = 0.82) and 17 ng/mL for CEA (sensitivity 100%, specificity 75%, AUC = 0.89). Conclusions: in patients with MTC, pre-operative serum calcitonin and CEA levels may drive the decision-making process to better define the extent of surgery. [ABSTRACT FROM AUTHOR]

Simple Summary: Many patients undergoing major abdominal surgery experience changes in their albumin levels, but the impact of this on their recovery is not well understood. Our research focused on patients who had cytoreductive surgery and a special chemotherapy treatment during surgery. We looked at how albumin levels changed from the time of surgery until three days after surgery and whether these changes were linked to major complications. We found that patients whose albumin levels dropped significantly during surgery were more likely to have serious complications. By tracking albumin levels, we might better predict and manage complications after this type of surgery. Our findings suggest that monitoring albumin could improve patient outcomes in the future. The clinical consequences of perioperative albumin extravasation accompanying major abdominal surgery remain underexplored. We retrospectively reviewed the data of patients who underwent cytoreductive surgery (CRS) and hyperthermic intraoperative peritoneal chemotherapy (HIPEC). Parameters of albumin kinetics, including serum albumin concentration decrease (∆Alb) and extravasated albumin level (Albshift), were assessed from surgery until postoperative day (POD) 3. Logistic regression analysis identified factors associated with major complications. The association of albumin kinetics with major complications was evaluated using receiver operating characteristic (ROC) curve analysis. Serum albumin levels decreased during surgery and subsequently increased. Of the 121 analyzed patients, 25 (21%) developed major complications. The ∆Alb and Albshift during surgery and on POD 3 were greater in patients who developed major complications than in those who did not (12 ± 12 vs. 6 ± 14, p = 0.032, and 127.5 (71.9) vs. 48.5 (44.9), p < 0.001, respectively). Perioperative ∆Alb and Albshift were associated with major complications. The areas under the ROC curve of Albshift during the 3 days post-surgery and Albshift on POD 3 were 0.843 and 0.910, respectively. Albshift during the 3 days post-surgery and Albshift on POD 3 were correlated with complications (p < 0.05). In conclusion, perioperative albumin loss was associated with major complications in patients undergoing CRS and HIPEC. Albshift was associated with serious complications. [ABSTRACT FROM AUTHOR]