Novel Deep Learning Radiomics Model for Preoperative Evaluation of Hepatocellular Carcinoma Differentiation Based on Computed Tomography Data

Abstract

Introduction: The evaluation of tumor differentiation is an urgent clinical issue that would facilitate the establishment of individualized therapeutic strategies. Our aims were to develop a deep learning radiomics model based on computed tomography(CT) data for preoperative evaluation of hepatocellular carcinoma(HCC) differentiation(low vs high grade), and to preliminarily explore the biological basis of the radiomics model. Methods: A total of 1234 HCC patients with contrast-enhanced CT images were recruited from two institutions. Radiomics features were extracted from preoperative venous-phase CT data and selected in terms of reproducibility, relevance and redundancy. The random forest(RF) algorithm was applied to establish a radiomics signature. The deep learning model was constructed based on a VGG network. Clinical characteristics of the subjects were used to construct a clinical model. The fused model integrated a tripartite prediction based on a logistic regression algorithm. Analysis was performed to explore the association between radiomics features and biological variables based on multiomics levels. Results: The radiomics signature established with the RF algorithm comprised 25 radiomics features. The AUCs in the training, internal validation, and independent test cohorts were 0.82, 0.76 and 0.75 respectively for the radiomics signature; 0.85, 0.81 and 0.75 respectively for the deep learning model; and 0.89, 0.83 and 0.80 respectively for the fused model. Multiomics analysis showed the selected radiomics features contained abundant biological information was related to tumor differentiation. Conclusions: Our deep learning radiomics model can serve as a noninvasive tool of preoperative HCC differentiation evaluation to guide clinical decision-making and prognostic stratification.