Vessels encapsulating tumor cluster (VETC) is a critical prognostic factor and therapeutic predictor of hepatocellular carcinoma (HCC). However, noninvasive evaluation of VETC remains challenging. To develop and validate a deep learning radiomic (DLR) model of dynamic contrast-enhanced MRI (DCE-MRI) for the preoperative discrimination of VETC and prognosis of HCC. Retrospective. A total of 221 patients with histologically confirmed HCC and stratified this cohort into training set (n = 154) and time-independent validation set (n = 67). A 1.5 T and 3.0 T; DCE imaging with T1-weighted three-dimensional fast spoiled gradient echo. Histological specimens were used to evaluate VETC status. VETC+ cases had a visible pattern (≥5% tumor area), while cases without any pattern were VETC-. The regions of intratumor and peritumor were segmented manually in the arterial, portal-venous and delayed phase (AP, PP, and DP, respectively) of DCE-MRI and reproducibility of segmentation was evaluated. Deep neural network and machine learning (ML) classifiers (logistic regression, decision tree, random forest, SVM, KNN, and Bayes) were used to develop nine DLR, 54 ML and clinical-radiological (CR) models based on AP, PP, and DP of DCE-MRI for evaluating VETC status and association with recurrence. The Fleiss kappa, intraclass correlation coefficient, receiver operating characteristic curve, area under the curve (AUC), Delong test and Kaplan-Meier survival analysis. P value <0.05 was considered as statistical significance. Pathological VETC+ were confirmed in 68 patients (training set: 46, validation set: 22). In the validation set, DLR model based on peritumor PP (peri-PP) phase had the best performance (AUC: 0.844) in comparison to CR (AUC: 0.591) and ML (AUC: 0.672) models. Significant differences in recurrence rates between peri-PP DLR model-predicted VETC+ and VETC- status were found. The DLR model provides a noninvasive method to discriminate VETC status and prognosis of HCC patients preoperatively. 4. Stage 2.
Read full abstract