DeepRisk
Description
The DeepRisk network, based on digital pathology signatures (DPS) from whole-slide images, enhances the prognostic accuracy of the tumor, node, and metastasis (TNM) staging system for gastric cancer (GC). Validation across multiple datasets demonstrated that DeepRisk offers superior prognostic value and identifies patients who respond better to neoadjuvant chemotherapy. Additionally, spatial and multi-omics analyses reveal associations between DPS and immune suppression, providing insights into GC pathogenesis and aiding in personalized treatment strategies.
Creator
Zhongshan Hospital, Fudan University, Shanghai University of Traditional Chinese Medicine, The Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai
Information
Pediatrics or Adult
Adult
Speciality
Pathology
Modality
Whole-slide images (WSIs)
Training
1120 gastric cancer (GC) images in the Zhongshan dataset and validated with two external datasets
Github
Publication
FDA