Search

Simple Summary: Diagnosing glioblastoma multiforme (GBM), solitary brain metastases (SBM), and primary central nervous system lymphoma (PCNSL) in malignant tumors of the central nervous system using multi-modal magnetic resonance imaging (MRI) is significantly important in helping physicians develop treatment plans and enhance patient prognosis. In this paper, MFFC-Net is developed and validated using deep learning methods to predict these three tumor categories from multi-modal MRI without the manual region of interest (ROI). MFFC-Net first uses a multi-encoder with DenseBlocks to extract deep features from multi-modal MRI. Then, the feature fusion layer fuses the deep information between different modalities and tissues. Finally, the spatial-channel attention module suppresses redundant new information and activates tumor classification-related features. Compared with radiomics models, MFFC-Net demonstrated higher accuracy. In addition, the results in the different sequences provide important references for future clinical work on MRI image acquisition. We believe that MFFC-Net has the potential to assist in the diagnosis and treatment of brain tumors in the future. (1) Background: Diagnosis of glioblastoma (GBM), solitary brain metastases (SBM), and primary central nervous system lymphoma (PCNSL) plays a decisive role in the development of personalized treatment plans. Constructing a deep learning classification network to diagnose GBM, SBM, and PCNSL with multi-modal MRI is important and necessary. (2) Subjects: GBM, SBM, and PCNSL were confirmed by histopathology with the multi-modal MRI examination (study from 1225 subjects, average age 53 years, 671 males), 3.0 T T2 fluid-attenuated inversion recovery (T2-Flair), and Contrast-enhanced T1-weighted imaging (CE-T1WI). (3) Methods: This paper introduces MFFC-Net, a classification model based on the fusion of multi-modal MRIs, for the classification of GBM, SBM, and PCNSL. The network architecture consists of parallel encoders using DenseBlocks to extract features from different modalities of MRI images. Subsequently, an L 1 − n o r m feature fusion module is applied to enhance the interrelationships among tumor tissues. Then, a spatial-channel self-attention weighting operation is performed after the feature fusion. Finally, the classification results are obtained using the full convolutional layer (FC) and Soft-max. (4) Results: The ACC of MFFC-Net based on feature fusion was 0.920, better than the radiomics model (ACC of 0.829). There was no significant difference in the ACC compared to the expert radiologist (0.920 vs. 0.924, p = 0.774). (5) Conclusions: Our MFFC-Net model could distinguish GBM, SBM, and PCNSL preoperatively based on multi-modal MRI, with a higher performance than the radiomics model and was comparable to radiologists. [ABSTRACT FROM AUTHOR]

High-grade serous ovarian cancer (HGSOC) is the most lethal tumor of the female genital tract. Despite extensive studies and the identification of some precursor lesions like serous tubal intraepithelial cancer (STIC) or the deviated mutational status of the patients (BRCA germinal mutation), the pathophysiology of HGSOC and the existence of particular risk factors is still a puzzle. Moreover, a lack of screening programs results in delayed diagnosis, which is accompanied by a secondary chemo-resistance of the tumor and usually results in a high recurrence rate after the primary therapy. Therefore, there is an urgent need to identify the substantial risk factors for both predisposed and low-risk populations of women, as well as to create an economically and clinically justified screening program. This paper reviews the classic and novel risk factors for HGSOC and methods of diagnosis and prediction, including serum biomarkers, the liquid biopsy of circulating tumor cells or circulating tumor DNA, epigenetic markers, exosomes, and genomic and proteomic biomarkers. The novel future complex approach to ovarian cancer diagnosis should be devised based on these findings, and the general outcome of such an approach is proposed and discussed in the paper. [ABSTRACT FROM AUTHOR]

Cancer is a significant global public health issue with increasing morbidity and mortality rates. To address this challenge, novel drug carriers such as nano-materials, liposomes, hydrogels, fibers, and microspheres have been extensively researched and utilized in oncology. Among them, polymer microspheres are gaining popularity due to their ease of preparation, excellent performance, biocompatibility, and drug-release capabilities. This paper categorizes commonly used materials for polymer microsphere preparation, summarizes various preparation methods (emulsification, phase separation, spray drying, electrospray, microfluidics, and membrane emulsification), and reviews the applications of polymer microspheres in cancer diagnosis, therapy, and postoperative care. The current status and future development directions of polymer microspheres in cancer treatment are analyzed, highlighting their importance and potential for improving patient outcomes. [ABSTRACT FROM AUTHOR]

Breast cancer remains the most prevalent cancer among women worldwide, necessitating advancements in diagnostic methods. The integration of artificial intelligence (AI) into mammography has shown promise in enhancing diagnostic accuracy. However, understanding patient perspectives, particularly considering the psychological impact of breast cancer diagnoses, is crucial. This narrative review synthesizes literature from 2000 to 2023 to examine breast cancer patients' attitudes towards AI in breast imaging, focusing on trust, acceptance, and demographic influences on these views. Methodologically, we employed a systematic literature search across databases such as PubMed, Embase, Medline, and Scopus, selecting studies that provided insights into patients' perceptions of AI in diagnostics. Our review included a sample of seven key studies after rigorous screening, reflecting varied patient trust and acceptance levels towards AI. Overall, we found a clear preference among patients for AI to augment rather than replace the diagnostic process, emphasizing the necessity of radiologists' expertise in conjunction with AI to enhance decision-making accuracy. This paper highlights the importance of aligning AI implementation in clinical settings with patient needs and expectations, emphasizing the need for human interaction in healthcare. Our findings advocate for a model where AI augments the diagnostic process, underlining the necessity for educational efforts to mitigate concerns and enhance patient trust in AI-enhanced diagnostics. [ABSTRACT FROM AUTHOR]

Overhydration (OH) is a prevalent medical problem that occurs in patients with kidney failure, but a specific marker has still not been found. Patients requiring kidney replacement therapy suffer from a water imbalance, which is correlated with mortality rates in this population. Currently, clinicians employ techniques such as bioimpedance spectroscopy (BIS) and ultrasound (USG) markers of overhydration or markers of heart and kidney function, namely NT-pro-BNP, GFR, or creatinine levels. New serum markers, including but not limited to Ca-125, galectin-3 (Gal-3), adrenomedullin (AMD), and urocortin-2 (UCN-2), are presently under research and have displayed promising results. Ca-125, which is a protein mainly used in ovarian cancer diagnoses, holds great potential to become an OH marker. It is currently being investigated by cardiologists as it corresponds to the volume status in heart failure (HF) and ventricular hypertrophy, which are also associated with OH. The need to ascertain a more precise marker of overhydration is urgent mainly because physical examinations are exceptionally inaccurate. The signs and symptoms of overhydration, such as edema or a gradual increase in body mass, are not always present, notably in patients with chronic kidney disease. Metabolic disruptions and cachexia can give a false picture of the hydration status. This review paper summarizes the existing knowledge on the assessment of a patient's hydration status, focusing specifically on kidney diseases and the role of Ca-125. [ABSTRACT FROM AUTHOR]

Accurate diagnosis of the localization of prostate cancer (PCa) on magnetic resonance imaging (MRI) remains a challenge. We aimed to assess discrepancy between the location of PCa pathologically diagnosed using surgical specimens and lesions indicated as possible PCa by the Prostate Imaging Reporting and Data System on MRI. The primary endpoint was the concordance rate between the site of probable clinically significant PCa (csPCa) identified using biparametric MRI (bpMRI) and location of PCa in the surgical specimen obtained using robot-assisted total prostatectomy. Among 85 lesions identified in 30 patients; 42 (49.4%) were identified as possible PCa on MRI. The 85 PCa lesions were divided into positive and negative groups based on the bpMRI results. None of the patients had missed csPCa. Although the diagnostic accuracy of bpMRI was relatively high for PCas located in the middle of the prostate (p = 0.029), it was relatively low for PCa located at the base of the prostate, all of which were csPCas. Although current modalities can accurately diagnose PCa, the possibility that PCa is present with multiple lesions in the prostate should be considered, even if MRI does not detect PCa. [ABSTRACT FROM AUTHOR]

Simple Summary: Identifying the genetic cause of a retinoblastoma tumour can help doctors determine any future cancer risk for the patient or their family. Somatic testing has historically used DNA from the tumour, after the eye has been removed. We and others have previously shown cell-free DNA (cfDNA) from the tumour is present in the eye fluid of retinoblastoma patients. In this study we tested eye fluid from 68 patients, collected at different points in their treatment. Measurable levels of cfDNA were found in all 11 samples of eye fluid taken from patients who had received less than three cycles of chemotherapy, and 95% (21/22) of causal genetic variants were identified. Eye fluid collected later in the treatment had 150 times less cfDNA and only 46% of genetic variants (25/54) could be detected. Eye fluid sampling early in treatment is therefore likely to be required for successful somatic testing in retinoblastoma patients undergoing eye conservation treatment. The identification of somatic RB1 variation is crucial to confirm the heritability of retinoblastoma. We and others have previously shown that, when tumour DNA is unavailable, cell-free DNA (cfDNA) derived from aqueous humour (AH) can be used to identify somatic RB1 pathogenic variation. Here we report RB1 pathogenic variant detection, as well as cfDNA concentration in an extended cohort of 75 AH samples from 68 patients. We show cfDNA concentration is highly variable and significantly correlated with the collection point of the AH. Cell-free DNA concentrations above 5 pg/µL enabled the detection of 93% of known or expected RB1 pathogenic variants. In AH samples collected during intravitreal chemotherapy treatment (Tx), the yield of cfDNA above 5 pg/µL and subsequent variant detection was low (≤46%). However, AH collected by an anterior chamber tap after one to three cycles of primary chemotherapy (Dx1+) enabled the detection of 75% of expected pathogenic variants. Further limiting our analysis to Dx1+ samples taken after ≤2 cycles (Dx ≤ 2) provided measurable levels of cfDNA in all cases, and a subsequent variant detection rate of 95%. Early AH sampling is therefore likely to be important in maximising cfDNA concentration and the subsequent detection of somatic RB1 pathogenic variants in retinoblastoma patients undergoing conservative treatment. [ABSTRACT FROM AUTHOR]

Enhancing lung cancer diagnosis requires precise early detection methods. This study introduces an automated diagnostic system leveraging computed tomography (CT) scans for early lung cancer identification. The main approach is the integration of three distinct feature analyses: the novel 3D-Local Octal Pattern (LOP) descriptor for texture analysis, the 3D-Convolutional Neural Network (CNN) for extracting deep features, and geometric feature analysis to characterize pulmonary nodules. The 3D-LOP method innovatively captures nodule texture by analyzing the orientation and magnitude of voxel relationships, enabling the distinction of discriminative features. Simultaneously, the 3D-CNN extracts deep features from raw CT scans, providing comprehensive insights into nodule characteristics. Geometric features and assessing nodule shape further augment this analysis, offering a holistic view of potential malignancies. By amalgamating these analyses, our system employs a probability-based linear classifier to deliver a final diagnostic output. Validated on 822 Lung Image Database Consortium (LIDC) cases, the system's performance was exceptional, with measures of 97.84 % , 98.11 % , 94.73 % , and 0.9912 for accuracy, sensitivity, specificity, and Area Under the ROC Curve (AUC), respectively. These results highlight the system's potential as a significant advancement in clinical diagnostics, offering a reliable, non-invasive tool for lung cancer detection that promises to improve patient outcomes through early diagnosis. [ABSTRACT FROM AUTHOR]

Breast cancer results from a disruption of certain cells in breast tissue that undergo uncontrolled growth and cell division. These cells most often accumulate and form a lump called a tumor, which may be benign (non-cancerous) or malignant (cancerous). Malignant tumors can spread quickly throughout the body, forming tumors in other areas, which is called metastasis. Standard screening techniques are insufficient in the case of metastasis; therefore, new and advanced techniques based on artificial intelligence (AI), machine learning, and regression models have been introduced, the primary aim of which is to automatically diagnose breast cancer through the use of advanced techniques, classifiers, and real images. Real fine-needle aspiration (FNA) images were collected from Wisconsin, and four classifiers were used, including three machine learning models and one regression model: the support vector machine (SVM), naive Bayes (NB), k-nearest neighbors (k-NN), and decision tree (DT)-C4.5. According to the accuracy, sensitivity, and specificity results, the SVM algorithm had the best performance; it was the most powerful computational classifier with a 97.13% accuracy and 97.5% specificity. It also had around a 96% sensitivity for the diagnosis of breast cancer, unlike the models used for comparison, thereby providing an exact diagnosis on the one hand and a clear classification between benign and malignant tumors on the other hand. As a future research prospect, more algorithms and combinations of features can be considered for the precise, rapid, and effective classification and diagnosis of breast cancer images for imperative decisions. [ABSTRACT FROM AUTHOR]

Background and Objectives: Endometrial carcinoma is one of the most common gynecological cancers, and benign lesions such as endometrial hyperplasia, polyps, adenomyosis and leiomyomas should be included in the differential diagnosis. Magnetic resonance imaging has an important role in evaluating endometrial cancer and assessing the depth of myometrial invasion, and it closely correlates with the prognosis of the patient. The purpose of this study is to evaluate the MRI semiology of the endometrial carcinomas that mimic benign lesions, the main factors that may affect the correct diagnosis and the feasibility of magnetic resonance imaging to evaluate the depth of the myometrial invasion of endometrial cancer. Materials and Methods: This is a retrospective analysis of 45 patients that underwent MRI examinations and the lesions were pathologically diagnosed as endometrial carcinoma after surgical resection. This study evaluated the staging accuracy of T2-weighted imaging, diffusion-weighted imaging (DWI), ADC mapping and T1-weighted imaging with fat saturation before and after gadolinium injection. Results: In 36 of the 45 cases, the MRI of the lesion showed the characteristics of endometrial cancer and the diagnosis was certain. Nine lesions (20%) were described as unequivocal and had unspecific MR appearance. In eight of the nine cases (89%), the histopathologic report revealed the presence of leiomyomas and two of these cases (22%) were also associated with adenomyosis. The cause of underestimation in these patients was coexisting lesions exhibiting heterogenous intensity and contrast enhancement, which made it difficult to detect the margins of the lesions. The depth of the myometrial invasion was underestimated in nine cases and overestimated in three cases. The staging accuracy with MRI was 74%. There was a significant correlation between MR imaging and histopathologic finding in the assessment of myometrial invasion (p < 0.001). Cervical extension was noted in eight cases (18%), but was missed on MR imaging in two patients and overstaged in none. Six of them were associated with myometrial invasion in more than 50% of the thickness. There was a significant correlation between MR imaging and histopathologic finding in the assessment of cervical extension (p < 0.001). Conclusions: Our data confirm the high accuracy of MRI in the diagnosis and local staging of endometrial carcinoma. The information provided by MRI has an important role in planning the treatment and the prognosis of the patients. [ABSTRACT FROM AUTHOR]

Background: The aim of this review is to explore the role of artificial intelligence in the diagnosis of colorectal cancer, how it impacts CRC morbidity and mortality, and why its role in clinical medicine is limited. Methods: A targeted, non-systematic review of the published literature relating to colorectal cancer diagnosis was performed with PubMed databases that were scouted to help provide a more defined understanding of the recent advances regarding artificial intelligence and their impact on colorectal-related morbidity and mortality. Articles were included if deemed relevant and including information associated with the keywords. Results: The advancements in artificial intelligence have been significant in facilitating an earlier diagnosis of CRC. In this review, we focused on evaluating genomic biomarkers, the integration of instruments with artificial intelligence, MR and hyperspectral imaging, and the architecture of neural networks. We found that these neural networks seem practical and yield positive results in initial testing. Furthermore, we explored the use of deep-learning-based majority voting methods, such as bag of words and PAHLI, in improving diagnostic accuracy in colorectal cancer detection. Alongside this, the autonomous and expansive learning ability of artificial intelligence, coupled with its ability to extract increasingly complex features from images or videos without human reliance, highlight its impact in the diagnostic sector. Despite this, as most of the research involves a small sample of patients, a diversification of patient data is needed to enhance cohort stratification for a more sensitive and specific neural model. We also examined the successful application of artificial intelligence in predicting microsatellite instability, showcasing its potential in stratifying patients for targeted therapies. Conclusions: Since its commencement in colorectal cancer, artificial intelligence has revealed a multitude of functionalities and augmentations in the diagnostic sector of CRC. Given its early implementation, its clinical application remains a fair way away, but with steady research dedicated to improving neural architecture and expanding its applicational range, there is hope that these advanced neural software could directly impact the early diagnosis of CRC. The true promise of artificial intelligence, extending beyond the medical sector, lies in its potential to significantly influence the future landscape of CRC's morbidity and mortality. [ABSTRACT FROM AUTHOR]

The present review aims to analyze the application of infrared thermal imaging, aided by bio-heat models, as a tool for the diagnosis of skin and breast cancers. The state of the art of the related technical procedures, bio-heat transfer modeling, and thermogram post-processing methods is comprehensively reviewed. Once the thermal signatures of different malignant diseases are described, the updated thermographic techniques (steady-state and dynamic) used for cancer diagnosis are discussed in detail, along with the recommended best practices to ensure the most significant thermal contrast observable between the cancerous and healthy tissues. Regarding the dynamic techniques, particular emphasis is placed on innovative methods, such as lock-in thermography, thermal wave imaging, and rotational breast thermography. Forward and inverse modeling techniques for the bio-heat transfer in skin and breast tissues, supporting the thermographic examination and providing accurate data for training artificial intelligence (AI) algorithms, are reported with a special focus on real breast geometry-based 3D models. In terms of inverse techniques, different data processing algorithms to retrieve thermophysical parameters and growth features of tumor lesions are mentioned. Post-processing of infrared images is also described, citing both conventional processing procedures and applications of AI algorithms for tumor detection. [ABSTRACT FROM AUTHOR]