Prospective Pathology Foundation Models

Histopathology remains the gold standard for disease diagnosis, yet faces challenges including pathologist shortages and diagnostic model limitations. This underscores the critical need to develop deep learning-based pathology foundation models integrating prospective imaging and clinical data. Such models would enhance diagnostic accuracy and efficiency, enabling tumor grading, histo-molecular classification, and intelligent chemotherapy guidance - ultimately optimizing clinical workflows. However, a critical gap remains: the absence of prospectively validated, pan-disease pathology foundation models. Developing clinically validated models is therefore imperative.

NCT Number	NCT07157618
Lead Sponsor	Nanfang Hospital, Southern Medical University Collaborators: Qianfoshan Hospital, Zhejiang University, The First Affiliated Hospital of Zhengzhou University, First Affiliated Hospital of Shantou University Medical College, Zhujiang Hospital, Air Force Military Medical University, China
Conditions	Pancancer
Enrollment	2,000 participants
Start Date	2025-08-28
Primary Completion	2028-07 (estimated)
Study Completion	2028-08 (estimated)
Updated on ClinicalTrials.gov	2026-04-23