A deep learning model for gastric diffuse-type adenocarcinoma classification in whole slide images
This work addresses the diagnostic challenge of distinguishing diffuse-type adenocarcinoma from non-neoplastic lesions in gastric cancer, potentially aiding pathologists in clinical workflows.
The study tackled the classification of gastric diffuse-type adenocarcinoma in whole slide images using deep learning models, achieving ROC AUCs between 0.95 and 0.99 across five test sets.
Gastric diffuse-type adenocarcinoma represents a disproportionately high percentage of cases of gastric cancers occurring in the young, and its relative incidence seems to be on the rise. Usually it affects the body of the stomach, and presents shorter duration and worse prognosis compared with the differentiated (intestinal) type adenocarcinoma. The main difficulty encountered in the differential diagnosis of gastric adenocarcinomas occurs with the diffuse-type. As the cancer cells of diffuse-type adenocarcinoma are often single and inconspicuous in a background desmoplaia and inflammation, it can often be mistaken for a wide variety of non-neoplastic lesions including gastritis or reactive endothelial cells seen in granulation tissue. In this study we trained deep learning models to classify gastric diffuse-type adenocarcinoma from WSIs. We evaluated the models on five test sets obtained from distinct sources, achieving receiver operator curve (ROC) area under the curves (AUCs) in the range of 0.95-0.99. The highly promising results demonstrate the potential of AI-based computational pathology for aiding pathologists in their diagnostic workflow system.