Clinically applicable histopathological diagnosis system for gastric cancer detection using deep learning

TLDR

Early detection and accurate histopathological diagnosis of gastric cancer improve treatment success, yet a global shortage of pathologists limits diagnostic capacity. The study aims to develop a clinically applicable deep learning system for gastric cancer diagnosis using a convolutional neural network trained on 2,123 annotated H&E whole‑slide images. The system employs a deep convolutional neural network trained on 2,123 pixel‑level annotated H&E‑stained whole‑slide images. The model achieved nearly 100 % sensitivity and 80.6 % specificity on a real‑world test set of 3,212 images, improved pathologist accuracy, and performed robustly on 1,582 images from two other centers, demonstrating feasibility and benefits of AI assistance in routine practice.

Abstract

Abstract The early detection and accurate histopathological diagnosis of gastric cancer increase the chances of successful treatment. The worldwide shortage of pathologists offers a unique opportunity for the use of artificial intelligence assistance systems to alleviate the workload and increase diagnostic accuracy. Here, we report a clinically applicable system developed at the Chinese PLA General Hospital, China, using a deep convolutional neural network trained with 2,123 pixel-level annotated H&E-stained whole slide images. The model achieves a sensitivity near 100% and an average specificity of 80.6% on a real-world test dataset with 3,212 whole slide images digitalized by three scanners. We show that the system could aid pathologists in improving diagnostic accuracy and preventing misdiagnoses. Moreover, we demonstrate that our system performs robustly with 1,582 whole slide images from two other medical centres. Our study suggests the feasibility and benefits of using histopathological artificial intelligence assistance systems in routine practice scenarios.