Search

Simple Summary: Lymphatic (LI), microvascular (VI) and perineural invasion (PnI) have been determined as indicators for aggressive tumor behavior and worse outcome in many solid tumors. In neuroendocrine tumors of the small intestine (siNET), some prognosis-defining factors have been well established, but the role of LI, VI and PnI remains incompletely understood so far. The aim of our retrospective study was to elucidate the role of lymphatic, microvascular and perineural invasion in the oncological outcome in siNET. We found that lymphatic, microvascular and perineural invasion led to earlier disease recurrence and postoperative disease progression. We therefore promote the routine description of these histopathological parameters for considerations on adjuvant treatment and follow-up. For the histopathological work-up of resected neuroendocrine tumors of the small intestine (siNET), the determination of lymphatic (LI), microvascular (VI) and perineural (PnI) invasion is recommended. Their association with poorer prognosis has already been demonstrated in many tumor entities. However, the influence of LI, VI and PnI in siNET has not been sufficiently described yet. A retrospective analysis of all patients treated for siNET at the ENETS Center of Excellence Charité–Universitätsmedizin Berlin, from 2010 to 2020 was performed (n = 510). Patients who did not undergo primary resection or had G3 tumors were excluded. In the entire cohort (n = 161), patients with LI, VI and PnI status had more distant metastases (48.0% vs. 71.4%, p = 0.005; 47.1% vs. 84.4%, p < 0.001; 34.2% vs. 84.7%, p < 0.001) and had lower rates of curative surgery (58.0% vs. 21.0%, p < 0.001; 48.3% vs. 16.7%, p < 0.001; 68.4% vs. 14.3%, p < 0.001). Progression-free survival was significantly reduced in patients with LI, VI or PnI compared to patients without. This was also demonstrated in patients who underwent curative surgery. Lymphatic, vascular and perineural invasion were associated with disease progression and recurrence in patients with siNET, and these should therefore be included in postoperative treatment considerations. [ABSTRACT FROM AUTHOR]

Simple Summary: Intrahepatic cholangiocarcinoma is a disease with increasing incidence and poor prognosis. The clinicians have a limited capability to predict tumor behavior because the strongest predictors of survival are the pathology data that, unfortunately, can be determined only after surgery. Recently, radiomics, i.e., the mathematical analysis of imaging modalities, led to a major improvement in the non-invasive prediction of microscopic characteristics of several tumors. In this multicenter study, we collected a large number of patients affected by intrahepatic cholangiocarcinoma and we demonstrated that the radiomic data of the tumor and peritumoral tissue extracted from the computed tomography at diagnosis have a strong association with tumor grading and microscopic vascular invasion, which are two major biomarkers of tumor aggressiveness. The combination of radiomic and clinical data maximizes the accuracy of prediction. The integration of radiomics into clinical decision processes is probably one of the following steps toward a precision medicine approach in patients affected by intrahepatic cholangiocarcinoma. Standard imaging cannot assess the pathology details of intrahepatic cholangiocarcinoma (ICC). We investigated whether CT-based radiomics may improve the prediction of tumor characteristics. All consecutive patients undergoing liver resection for ICC (2009-2019) in six high-volume centers were evaluated for inclusion. On the preoperative CT, we segmented the ICC (Tumor-VOI, i.e., volume-of-interest) and a 5-mm parenchyma rim around the tumor (Margin-VOI). We considered two types of pathology data: tumor grading (G) and microvascular invasion (MVI). The predictive models were internally validated. Overall, 244 patients were analyzed: 82 (34%) had G3 tumors and 139 (57%) had MVI. For G3 prediction, the clinical model had an AUC = 0.69 and an Accuracy = 0.68 at internal cross-validation. The addition of radiomic features extracted from the portal phase of CT improved the model performance (Clinical data+Tumor-VOI: AUC = 0.73/Accuracy = 0.72; +Tumor-/Margin-VOI: AUC = 0.77/Accuracy = 0.77). Also for MVI prediction, the addition of portal phase radiomics improved the model performance (Clinical data: AUC = 0.75/Accuracy = 0.70; +Tumor-VOI: AUC = 0.82/Accuracy = 0.73; +Tumor-/Margin-VOI: AUC = 0.82/Accuracy = 0.75). The permutation tests confirmed that a combined clinical–radiomic model outperforms a purely clinical one (p < 0.05). The addition of the textural features extracted from the arterial phase had no impact. In conclusion, the radiomic features of the tumor and peritumoral tissue extracted from the portal phase of preoperative CT improve the prediction of ICC grading and MVI. [ABSTRACT FROM AUTHOR]

Simple Summary: For early-stage hepatocellular carcinoma (HCC) (size ≤ 5 cm), the prediction of microvascular invasion (MVI) before operation is important for the therapeutic strategy. This study aimed to construct deep learning (DL) models based only on the venous phase (VP) of contrast-enhanced computed tomography (CECT), and to evaluate the performance of these models for preoperative prediction of MVI. A novel transformer-based end-to-end DL model is proposed for the first time, named MVI-TR, to capture features automatically from radiomics and to perform MVI preoperative assessments. For patient cohorts, it achieved superior outcomes in six performance measures of MVI predication status: accuracy, precision, receiver operating characteristic (ROC), area under the curve (AUC), recalling rate, and F1-score. In this study, we considered preoperative prediction of microvascular invasion (MVI) status with deep learning (DL) models for patients with early-stage hepatocellular carcinoma (HCC) (tumor size ≤ 5 cm). Two types of DL models based only on venous phase (VP) of contrast-enhanced computed tomography (CECT) were constructed and validated. From our hospital (First Affiliated Hospital of Zhejiang University, Zhejiang, P.R. China), 559 patients, who had histopathological confirmed MVI status, participated in this study. All preoperative CECT were collected, and the patients were randomly divided into training and validation cohorts at a ratio of 4:1. We proposed a novel transformer-based end-to-end DL model, named MVI-TR, which is a supervised learning method. MVI-TR can capture features automatically from radiomics and perform MVI preoperative assessments. In addition, a popular self-supervised learning method, the contrastive learning model, and the widely used residual networks (ResNets family) were constructed for fair comparisons. With an accuracy of 99.1%, a precision of 99.3%, an area under the curve (AUC) of 0.98, a recalling rate of 98.8%, and an F1-score of 99.1% in the training cohort, MVI-TR achieved superior outcomes. Additionally, the validation cohort's MVI status prediction had the best accuracy (97.2%), precision (97.3%), AUC (0.935), recalling rate (93.1%), and F1-score (95.2%). MVI-TR outperformed other models for predicting MVI status, and showed great preoperative predictive value for early-stage HCC patients. [ABSTRACT FROM AUTHOR]

Simple Summary: Surgical resection is the optimal treatment for hepatocellular carcinoma (HCC), despite a high risk of recurrence. We performed a retrospective analysis of survival after recurrence (SAR) of HCC after liver resection. Time to recurrence and treatment at recurrence are major prognostic factors of SAR. However, after curative treatment at recurrence, Overall survival is not significantly different between patients who recurred or not, whatever the time of recurrence. Surgical resection is the optimal treatment for HCC, despite a high risk of recurrence. Few data are available on patient's survival after resection. This is a retrospective study of tumor recurrence occurring after hepatectomy for HCC from 2000 to 2016. Univariate and multivariate analyses were performed to identify prognostic factors of survival after recurrence (SAR). Among 387 patients, 226 recurred (58.4%) with a median SAR of 26 months. Curative treatments (liver transplantation, repeat hepatectomy, thermal ablation) were performed for 44.7% of patients. Independent prognostic factors for SAR were micro-vascular invasion on the primary surgical specimen, size of the initial tumor >5 cm, preoperative AFP, albumin and platelet levels, male gender, number, size and localization of tumors at recurrence, time to recurrence, Child–Pugh score and treatment at recurrence. In subgroup analysis, early recurrence (46%) was associated with a decrease in SAR, by contrast with late recurrence. However, the overall survival (OS) of patients with early recurrence and curative treatment did not significantly differ from that of non-recurring patients. For late recurrence, OS did not significantly differ from that of non-recurring patients, regardless of the proposed treatment. Aggressive and repeat treatments are therefore key to improve prognosis of patients with HCC. [ABSTRACT FROM AUTHOR]

Simple Summary: Microvascular invasion is an important indicator for reflecting the prognosis of hepatocellular carcinoma, but the traditional diagnosis requires a postoperative pathological examination. This study is the first to propose an end-to-end deep learning architecture for predicting microvascular invasion in hepatocellular carcinoma by collecting retrospective data. This method can achieve noninvasive, accurate and efficient preoperative prediction only through the patient's radiomic data, which is very beneficial to doctors for clinical decision making in HCC patients. Microvascular invasion (MVI) in hepatocellular carcinoma (HCC) directly affects a patient's prognosis. The development of preoperative noninvasive diagnostic methods is significant for guiding optimal treatment plans. In this study, we investigated 138 patients with HCC and presented a novel end-to-end deep learning strategy based on computed tomography (CT) radiomics (MVI-Mind), which integrates data preprocessing, automatic segmentation of lesions and other regions, automatic feature extraction, and MVI prediction. A lightweight transformer and a convolutional neural network (CNN) were proposed for the segmentation and prediction modules, respectively. To demonstrate the superiority of MVI-Mind, we compared the framework's performance with that of current, mainstream segmentation, and classification models. The test results showed that MVI-Mind returned the best performance in both segmentation and prediction. The mean intersection over union (mIoU) of the segmentation module was 0.9006, and the area under the receiver operating characteristic curve (AUC) of the prediction module reached 0.9223. Additionally, it only took approximately 1 min to output a prediction for each patient, end-to-end using our computing device, which indicated that MVI-Mind could noninvasively, efficiently, and accurately predict the presence of MVI in HCC patients before surgery. This result will be helpful for doctors to make rational clinical decisions. [ABSTRACT FROM AUTHOR]

Surgical resection is the optimal treatment for HCC, despite a high risk of recurrence. Few data are available on patient’s survival after resection. This is a retrospective study of tumor recurrence occurring after hepatectomy for HCC from 2000 to 2016. Univariate and multivariate analyses were performed to identify prognostic factors of survival after recurrence (SAR). Among 387 patients, 226 recurred (58.4%) with a median SAR of 26 months. Curative treatments (liver transplantation, repeat hepatectomy, thermal ablation) were performed for 44.7% of patients. Independent prognostic factors for SAR were micro-vascular invasion on the primary surgical specimen, size of the initial tumor >5 cm, preoperative AFP, albumin and platelet levels, male gender, number, size and localization of tumors at recurrence, time to recurrence, Child−Pugh score and treatment at recurrence. In subgroup analysis, early recurrence (46%) was associated with a decrease in SAR, by contrast with late recurrence. However, the overall survival (OS) of patients with early recurrence and curative treatment did not significantly differ from that of non-recurring patients. For late recurrence, OS did not significantly differ from that of non-recurring patients, regardless of the proposed treatment. Aggressive and repeat treatments are therefore key to improve prognosis of patients with HCC.

Simple Summary: Microvascular invasion (MVI) is the most consistently reported risk factor for recurrence after curative treatment in hepatocellular carcinoma (HCC), but the preoperative prediction of MVI is still challenging. We retrospectively collected 1153 patients who underwent liver resection for HCC, and our multivariate analysis revealed preoperative total tumor volume (TTV) and alpha-fetoprotein (AFP) to be independent risk factors for MVI. We used both factors to build a risk score model that is easy to calculate and objective, with minimal user bias. The preoperative prediction of MVI can guide the treatment plan of HCC, including surgical planning, criteria for transplantation, and adjuvant or neoadjuvant therapy. Our risk score model is easily and widely applicable with moderate performance, which optimizes clinical practice and helps study design in the future. Microvascular invasion (MVI) is a significant risk factor for the recurrence of hepatocellular carcinoma, but it is a histological feature that needs to be confirmed after hepatectomy or liver transplantation. The preoperative prediction of MVI can optimize the treatment plan of HCC, but an easy and widely applicable model is still lacking. The aim of our study was to predict the risk of MVI using objective preoperative factors. We retrospectively collected 1153 patients who underwent liver resection for HCC, and MVI was found to be associated with significantly poor disease-free survival. The patients were randomly split in a 3:1 ratio into training (n = 864) and validation (n = 289) datasets. The multivariate analysis of the training dataset found preoperative total tumor volume (TTV) and alpha-fetoprotein (AFP) to be independent risk factors for MVI. We built a risk score model with cutoff points of TTV at 30, 60, and 300 cm3 and AFP at 160 and 2000 ng/mL, and the model stratified the risk of MVI into low risk (14.1%), intermediate risk (36.4%), and high risk (60.5%). The validation of the risk score model with the validation dataset showed moderate performance (the concordance statistic: 0.731). The model comprised simple and objective preoperative factors with good applicability, which can help to guide treatment plans for HCC and future study design. [ABSTRACT FROM AUTHOR]

Simple Summary: In recent years, functional imaging techniques have been increasingly studied to preoperatively identify the aggressive features in hepatocellular carcinoma (HCC). PET/CT with 2-deoxy-2-[18F]fluoro-d-glucose (FDG) is not routinely used for the diagnosis and staging of an HCC due to its low uptake of this radiopharmaceutical especially in well-differentiated lesions. However, FDG uptake in an HCC seems to relate to biological aggressiveness, being able to predict certain factors such as microvascular invasion. The present work aimed to assess the prognostic value of performing a baseline PET/CT with FDG in patients with an HCC who were subsequently treated with a tumor resection, trying to identify which metabolic parameters may predict the presence of histological factors of a poor prognosis. In our series, an increased SULpeak of the ratio tumor/liver 60 min after an FDG injection (TLRpeak60) seems a promising parameter to predict histological factors of a poor prognosis that could aid decision-making in this group of patients. Hepatocellular carcinoma (HCC) generally presents a low avidity for 2-deoxy-2-[18F]fluoro-d-glucose (FDG) in PET/CT although an increased FDG uptake seems to relate to more aggressive biological factors. To define the prognostic value of PET/CT with FDG in patients with an HCC scheduled for a tumor resection, forty-one patients were prospectively studied. The histological factors of a poor prognosis were determined and FDG uptake in the HCC lesions was analyzed semi-quantitatively (lean body mass-corrected standardized uptake value (SUL) and tumor-to-liver ratio (TLR) at different time points). The PET metabolic parameters were related to the histological characteristics of the resected tumors and to the evolution of patients. Microvascular invasion (MVI) and a poor grade of differentiation were significantly related to a worse prognosis. The SULpeak of the lesion 60 min post-FDG injection was the best parameter to predict MVI while the SULpeak of the TLR at 60 min was better for a poor differentiation. Moreover, the latter parameter was also the best preoperative variable available to predict any of these two histological factors. Patients with an increased TLRpeak60 presented a significantly higher incidence of poor prognostic factors than the rest (75% vs. 28.6%, p = 0.005) and a significantly higher incidence of recurrence at 12 months (38% vs. 0%, p = 0.014). Therefore, a semi-quantitative analysis of certain metabolic parameters on PET/CT can help identify, preoperatively, patients with histological factors of a poor prognosis, allowing an adjustment of the therapeutic strategy for those patients with a higher risk of an early recurrence. [ABSTRACT FROM AUTHOR]

Simple Summary: Microvascular invasion (MVI) is an independent risk factor for postoperative recurrence of hepatocellular carcinoma (HCC). Preoperative knowledge of MVI would assist with tailored surgical strategy making to prolong patient survival. Previous radiological studies proved the role of noninvasive medical imaging in MVI prediction. However, hitherto, deep learning methods remained unexplored for this clinical task. As an end-to-end self-learning strategy, deep learning may not only achieve improved prediction accuracy, but may also visualize high-risk areas of invasion by generating attention maps. In this multicenter study, we developed deep learning models to perform MVI preoperative assessments using two imaging modalities—computed tomography (CT) and gadoxetic acid-enhanced magnetic resonance imaging (EOB-MRI). A head-to-head prospective validation was conducted to verify the validity of deep learning models and achieve a comparison between CT and EOB-MRI for MVI assessment. The findings put forward a better understanding of MVI preoperative prediction in HCC management. Microvascular invasion (MVI) is a critical risk factor for postoperative recurrence of hepatocellular carcinoma (HCC). Preknowledge of MVI would assist tailored surgery planning in HCC management. In this multicenter study, we aimed to explore the validity of deep learning (DL) in MVI prediction using two imaging modalities—contrast-enhanced computed tomography (CE-CT) and gadoxetic acid-enhanced magnetic resonance imaging (EOB-MRI). A total of 750 HCCs were enrolled from five Chinese tertiary hospitals. Retrospective CE-CT (n = 306, collected between March, 2013 and July, 2019) and EOB-MRI (n = 329, collected between March, 2012 and March, 2019) data were used to train two DL models, respectively. Prospective external validation (n = 115, collected between July, 2015 and February, 2018) was performed to assess the developed models. Furthermore, DL-based attention maps were utilized to visualize high-risk MVI regions. Our findings revealed that the EOB-MRI-based DL model achieved superior prediction outcome to the CE-CT-based DL model (area under receiver operating characteristics curve (AUC): 0.812 vs. 0.736, p = 0.038; sensitivity: 70.4% vs. 57.4%, p = 0.015; specificity: 80.3% vs. 86.9%, p = 0.052). DL attention maps could visualize peritumoral high-risk areas with genuine histopathologic confirmation. Both DL models could stratify high and low-risk groups regarding progression free survival and overall survival (p < 0.05). Thus, DL can be an efficient tool for MVI prediction, and EOB-MRI was proven to be the modality with advantage for MVI assessment than CE-CT. [ABSTRACT FROM AUTHOR]