Building prospective, pan‑cancer pathology AI models
Development and Clinical Application of Deep Learning-Based Prospective Pathology Foundation Models
This project will test whether AI models trained on new pathology images and clinical data can help improve diagnosis and treatment guidance for adults with cancer.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 2000 (estimated) |
| Ages | 18 Years to 75 Years |
| Sex | All |
| Sponsor | Nanfang Hospital, Southern Medical University Academic / other |
| Drugs / interventions | chemotherapy |
| Locations | 2 sites (Guangzhou, Guangdong and 1 other locations) |
| Trial ID | NCT07157618 on ClinicalTrials.gov |
What this trial studies
The project prospectively collects histopathology slides and linked clinical data across multiple cancer types to train large deep‑learning 'foundation' pathology models. These models are intended to support tasks such as tumor grading, histo‑molecular classification, and intelligent chemotherapy guidance by learning from real-world, forward‑looking clinical samples. The approach uses standardized quality control of specimens and centralized model development using data from participating hospitals. The goal is to produce models that are validated on prospectively acquired data rather than only on retrospective archives.
Who should consider this trial
Good fit: Adults aged 18–75 with complete pathological slides and linked clinical information for their cancer are ideal candidates.
Not a fit: Patients outside the 18–75 age range or those with missing data or specimens that fail quality control are unlikely to benefit from participation.
Why it matters
Potential benefit: If successful, these models could speed up and improve diagnostic accuracy, provide additional molecular and treatment guidance from routine slides, and reduce workload on pathologists.
How similar studies have performed: Retrospective deep‑learning studies on histopathology have shown promising results, but prospectively validated, pan‑disease foundation pathology models remain largely novel and unproven.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: 1. Aged 18-75 years old. 2. Patients with complete pathological slides and clinical information. Exclusion Criteria: 1.Patients with missing data or specimens not meeting quality control requirements for analysis.
Where this trial is running
Guangzhou, Guangdong and 1 other locations
- Nanfang Hospital, Southern Medical University — Guangzhou, Guangdong, China (Recruiting)
- Qianfoshan Hospital — Jinan, Shandong, China (Recruiting)
Study contacts
- Study coordinator: Zhengyu Zhang
- Email: zzyusmu@163.com
- Phone: +8613837365993
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.