Temporal Encoded Deep Learning Radiomics Model for Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma

Purpose A novel deep learning radiomics model was developed to predict microvascular invasion (MVI) based on preoperative multiphase CT images. Concurrently, the study delves into the clinical value of temporal dynamic changes between multiphase images in the preoperative prediction of MVI in patients with hepatocellular carcinoma (HCC).Methods Between June 2019 and January 2023, we retrospectively included patients with pathologically proven HCC, including a training cohort of 100 HCC patients and a validation cohort of 42 HCC patients. Our model consists of a feature extractor based on convolutional neural networks (CNNs), a temporal encoder, and a classifier based on a multilayer perceptron (MLP). We evaluated the performance of our model using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Finally, we conducted comparative experiments based on traditional classification models, such as logistic regression (LR), random forest (RF), and support vector machines (SVM), and performed an ablation study on the temporal encoder module.Results Compared to other models, our model achieved AUCs of 0.912 (95% confidence interval (CI), 0.939-0.995) and 0.866 (95% CI 0.715-0.970) on the training and validation cohorts, respectively, demonstrating its superior performance in predicting MVI.Conclusion The proposed model accounts for the temporal characteristics of multiphase images, demonstrating its superior capability in characterizing MVI. This model holds the potential to aid clinicians in making accurate preoperative treatment decisions.