Abstract
BackgroundAn accurate pathological diagnosis of hepatocellular carcinoma (HCC), one of the malignant tumors with the highest mortality rate, is time-consuming and heavily reliant on the experience of a pathologist. 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.MethodsWe collected a whole-slide image of hematoxylin and eosin-stained pathological slides from 592 HCC patients at the First Affiliated Hospital, College of Medicine, Zhejiang University between 2015 and 2020. We propose a noise-specific deep learning model. The model was trained initially with 137 cases cropped into multiple-scaled datasets. Patch screening and dynamic label smoothing strategies are adopted to handle the 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.ResultsExhaustive experiments demonstrated that our two-step method achieved 87.81% pixel-level accuracy and 98.77% slide-level accuracy in the test dataset. Furthermore, the generalization performance of our model was also verified using The Cancer Genome Atlas dataset, which contains 157 HCC pathological slides, and achieved an accuracy of 87.90%.ConclusionsThe noise-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.
Highlights
Hepatocellular carcinoma (HCC) is one of the most commonly diagnosed cancers, ranking fifth in incidence rate and second in fatality rate in male individuals worldwide [1]
One representative hematoxylin and eosin (H&E)-stained digital slide was available for each HCC case, which included HCC tissues and the adjacent surrounding liver tissues
An expert liver pathologist made the rough annotations of the tumor regions, including 20 slides which were elaborately annotated for pixel-level evaluation
Summary
Hepatocellular carcinoma (HCC) is one of the most commonly diagnosed cancers, ranking fifth in incidence rate and second in fatality rate in male individuals worldwide [1]. The current practice of pathological diagnosis of HCC is time-consuming and completely relies on the subjective experience of a pathologist, which varies substantially. AI-driven approaches for pathological images can assist pathologists in diagnosis and provide clinicians with prognostic stratification and prediction of treatment response. Previous studies of HCC based on convolutional neural network (CNN) mainly focused on radiology images, including CT scans, ultrasound, and MRI scans [17]. An accurate pathological diagnosis of hepatocellular carcinoma (HCC), one of the malignant tumors with the highest mortality rate, is time-consuming and heavily reliant on the experience of a pathologist. We proposed a deep learning model that required minimal noise reduction or manual annotation by an experienced pathologist for HCC diagnosis and classification
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have