Midline glioma MRI AI model: preoperative molecular subtyping and prognosis
Official title: Application of MRI-Based Artificial Intelligence Models for Preoperative Molecular Subtyping and Prognostic Assessment of Midline Gliomas: A Multicenter Prospective Clinical Study
Run by Xiangya Hospital of Central South University · NCT07608003 · Data updated 2026-11-12
This study tests an MRI-based AI model to predict key molecular subtypes and prognosis for patients with midline gliomas before surgery.
Quick facts
| Study type | Observational |
|---|---|
| Sex | All |
| Enrollment | 500 (estimated) |
| Sponsor | Xiangya Hospital of Central South University Academic / other |
| Locations | 1 site (Changsha, Hunan) |
| Status | Recruiting |
| Started | May 10, 2026 |
| Main results expected | December 31, 2030 |
| Study ends | December 31, 2030 |
| Registry record updated | May 27, 2026 |
| Trial ID | NCT07608003 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Patients with intracranial midline diffuse gliomas who have completed preoperative MRI and share complete clinical data.
✕Probably not a fit
patients with non-midline tumors, poor-quality imaging, or incomplete clinical data may not benefit from the model.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This is a multicenter prospective observational study validating an AI model that uses preoperative MRI and basic patient info to predict H3K27M, IDH, and 1p/19q status. The model also estimates prognosis to support clinical decisions. Accuracy will be measured against postoperative pathology using metrics like sensitivity, specificity, accuracy, F1, and AUC, with time-dependent AUC for survival prediction. Exploratory analyses will assess potential impact on preoperative treatment planning and risk stratification.
Why it matters
Potential benefit: If successful, clinicians could tailor preoperative planning and conversations based on predicted molecular subtype and prognosis.
How similar studies have gone: Previous work suggests AI models can extract meaningful molecular and prognostic signals from MRI, but prospective multicenter validation in midline gliomas is still limited.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Patients with diffuse gliomas were pathologically and molecularly diagnosed. * The clinical case data of all patients were complete. * Patients underwent preoperative MRI examination. Exclusion Criteria: * The tumor is not located in the intracranial midline. * Cases in which MRI were incomplete or with significant noise and artifacts.
Where it's running
-
Xiangya Hospital of Central South University
Changsha, Hunan, China Recruiting
Study contacts
- Study coordinator: Gong Xuan, MD.
- Email: gong.xuan@csu.edu.cn
- Phone: 0086-731-8975-3037
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
PET-guided surgery for high-grade glioma
This project will try using 18F-DOPA PET to guide surgeons to remove tumor beyond MRI-visible areas in adults with high-grade glioma to see if it delays progression and extends survival.
-
AI-assisted diagnosis for malignant brain tumors
This project will test an AI system that uses routine preoperative MRI scans to automatically segment and classify malignant brain tumors in adults to help guide diagnosis and care.
-
HMPL-306 treatment for gliomas with IDH1 or IDH2 mutations.
This study will test whether HMPL-306, a drug that blocks mutant IDH1 and IDH2, is safe and shows early benefit in adults with IDH‑mutant gliomas.
-
Testing TNG456 and Abemaciclib in Patients with Solid Tumors Lacking MTAP
This study is testing a new drug called TNG456, alone and with another drug called abemaciclib, to see if it helps people with advanced solid tumors that have lost a specific gene called MTAP.
-
Measuring fluorescence from surgical suction during glioma surgery
This study is testing a new device that measures fluorescence from surgical suction during glioma surgery to see if it helps doctors remove more tumor tissue compared to what they can see with their regular tools.
-
Injection of natural killer cells for treating gliomas
This study is testing whether a new treatment using natural killer cells can help young patients with high-grade gliomas, like glioblastoma, fight their cancer better.
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.