Development of a Deep Learning Model to Assist with Diagnosis of Hepatocellular Carcinoma

Abstract

Background: Accurate pathological diagnosis of hepatocellular carcinoma (HCC), one of the malignant tumors with the highest mortality rate, is time-consuming and heavily reliant on a pathologist’s experience. In this report, we proposed a deep learning model that required minimal noise reduction or manual annotation by an experienced pathologist for HCC diagnosis and classification. \n \nMethods: We collected a whole-slide image (WSI) of haematoxylin and eosin (H&E)-stained pathological slides from 592 HCC patients at the First Affiliated Hospital, College of Medicine, Zhejiang University between 2015 and 2020. We propose a noisy-specific deep learning model. The model was trained initially with 137 cases, cropped into multiple-scaled datasets. The patch screening and label smoothing strategies are adopted to handle histopathological liver image with noise annotation from the perspective of input and output. The model was then tested in an independent cohort of 455 cases, with comparable tumor types and differentiations. \n \nFindings: Exhaustive experiments demonstrated that our two-step method achieved an 87.81% pixel-level accuracy and 98.77% slide-level accuracy in the test dataset. Furthermore, our model’s generalization performance was also verified using the Cancer Genome Atlas (TCGA) dataset, which contains 157 HCC pathological slides, and achieved an accuracy of 87.90%. \n \nInterpretation: The noisy-specific histopathological classification model of HCC based on deep learning is effective for the dataset with noisy annotation and it significantly improved the pixel-level accuracy of the regular convolutional neural network (CNN) model. Moreover, the model also has an advantage in detecting well-differentiated HCC and microvascular invasion (MVI). \n \nFunding: This work was supported by the Natural Science Foundation of Zhejiang Province (LY21H160035), the National Natural Science Foundation of China (81971686). \n \nDeclaration of Interest: None to declare. \n \nEthical Approval: The study was approved by the Ethics Committee of The First Affiliated Hospital, College of Medicine, Zhejiang University.