AI prediction of glioma molecular markers from pathology images
Official title: A Prospective Real-World Study of Pathology Artificial Intelligence for Predicting Molecular Alterations in Gliomas
Run by Nanfang Hospital, Southern Medical University · NCT07263711 · Data updated 2026-11-12
This project will test whether an AI model can use routine pathology images to predict key molecular changes in adults with glioma.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years to 100 Years |
| Sex | All |
| Enrollment | 2000 (estimated) |
| Sponsor | Nanfang Hospital, Southern Medical University Academic / other |
| Locations | 1 site (Guangzhou, Guangdong) |
| Status | Recruiting |
| Started | September 1, 2025 |
| Main results expected | September 1, 2030 |
| Study ends | September 1, 2030 |
| Registry record updated | December 4, 2025 |
| Trial ID | NCT07263711 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults (age 18 and over) with a histologically suspected diffuse glioma who have usable H&E whole-slide images and available postoperative molecular pathology results are ideal candidates.
✕Probably not a fit
Patients under 18, those without postoperative molecular test results, or those with poor-quality or insufficient pathology slides are unlikely to benefit from participation.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
Researchers will collect hematoxylin-and-eosin whole-slide pathology images and the corresponding postoperative molecular test results from participating hospitals. An AI model will generate predictions of key glioma molecular alterations from the digital slides. Those AI predictions will be compared directly with standard laboratory molecular testing to measure accuracy and timing. No extra treatments or procedures are required beyond standard clinical care.
Why it matters
Potential benefit: If successful, the AI tool could provide faster and lower-cost molecular diagnoses to help guide glioma treatment decisions.
How similar studies have gone: Retrospective studies have shown encouraging results for predicting some glioma markers from histology, but prospective real-world validation remains limited.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Participant (or legally authorized representative) has voluntarily signed the informed consent form. * Age ≥ 18 years at the time of enrollment. * Histologically suspected diffuse glioma based on biopsy or surgical resection. * Availability of complete clinical information and usable digital pathology slides with hematoxylin and eosin (H\&E) staining. * Postoperative molecular pathology results available for comparison. Exclusion Criteria: * Poor-quality pathology samples (e.g., insufficient tissue, large folding or contamination of slides, or substandard digital scanning quality). * Determined by the investigator to be unsuitable for participation in the study for any reason.
Where it's running
-
Nanfang Hospital, Southern Medical University
Guangzhou, Guangdong, China Recruiting
Study contacts
- Study coordinator: Danyi Li
- Email: lidanyi26@163.com
- Phone: +8613538308634
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
YN003 injection in glioma patients
This phase 1 study tests whether YN003 injected IV is safe and tolerable for adults with recurrent or progressive glioma, and to explore how the drug behaves in the body and any early signs of activity.
-
Brain connectome project in adults with brain glioma undergoing surgery
This registry collects MRI data and clinical information from adults with glioma to see how brain networks relate to surgery and recovery.
-
Proton vs. Photon Radiation for Certain Grade 2–3 Gliomas
This study tests whether proton therapy can better preserve thinking and memory than photon therapy for adults with IDH-mutated grade 2–3 gliomas who need radiation.
-
Connectome-guided network planning for brain tumor surgery in eloquent areas
This study tests whether using patient-specific brain network maps from diffusion MRI can help surgeons plan and guide brain tumor removal in eloquent areas.
-
AI-powered analysis of brain MRI to help glioma care
Doctors will use AI to study existing MRI scans and patient data from adults with glioma to see if it can help with non-invasive diagnosis and treatment planning.
-
Safusidenib in IDH1-mutant glioma after vorasidenib progression
This trial tests safusidenib in people with IDH1-mutant glioma who progressed on vorasidenib and did not need immediate chemo or radiation.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.