Multicenter Prospective Study on MRI AI Model for Midline Glioma Subtyping and Prognosis:

Application of MRI-Based Artificial Intelligence Models for Preoperative Molecular Subtyping and Prognostic Assessment of Midline Gliomas: A Multicenter Prospective Clinical Study

A vision-language model using preoperative MRI and clinical variables has been developed to simultaneously predict three key molecular markers in midline gliomas: H3K27M, IDH, and 1p/19q. This prospective multicenter study will validate the model's accuracy in preoperative molecular subtyping and its value in prognostic assessment and clinical decision-making across multiple neurosurgical centers.

Study Overview

• Status: Recruiting
• Conditions: Gliomas; Glioma, Diffuse Midline, H3K27M-mutant; Glioma of Brainstem; Glioma Glioblastoma Multiforme; Glioma : Oligodendroglioma or Astrocytoma; Gliomas Harboring IDH1 and/or IDH2 Mutations

Detailed Description

This study aims to validate the clinical value of an MRI-based artificial intelligence model for personalized diagnosis and treatment in patients with midline gliomas. The model integrates preoperative MRI features with clinical variables (e.g., age, sex, and other relevant patient characteristics) to predict both molecular subtypes and patient prognosis.

Model workflow. The model takes as input tumor-containing slices from preoperative MRI sequences, along with patient age and sex. By recognizing information within the MRI sequences, the model outputs the predicted molecular diagnosis for the patient.

Primary objective. To evaluate the model's accuracy in preoperative molecular subtyping of midline gliomas (H3K27M, IDH, and 1p/19q status) by comparing its predictions with the gold standard of postoperative or post-biopsy pathology. Diagnostic performance will be assessed using sensitivity, specificity, accuracy, F1 score, and area under the receiver operating characteristic curve (AUC).

Secondary objective. To assess the model's prognostic capability by integrating imaging features with clinical variables to predict patient survival outcomes and treatment response. Prognostic performance will be evaluated using time-dependent AUC and calibration metrics.

Exploratory objective. To explore the model's added value in clinical decision-making, including its potential to guide preoperative treatment planning and risk stratification.

This prospective, multicenter study will be conducted across several tertiary neurosurgical centers in China. The findings are expected to provide high-level evidence supporting non-invasive, precise diagnosis and personalized management of midline gliomas.

• Study Type: Observational
• Enrollment (Estimated): 500

Contacts and Locations

• Study Contact: Name: Gong Xuan, MD.; Phone Number: 0086-731-8975-3037; Email: gong.xuan@csu.edu.cn
• Study Contact Backup: Name: Shuwen Kuang, MD.; Phone Number: 0086-13367494221; Email: 228102171@csu.edu.cn

Study Locations

• China
  • Hunan
    • Changsha, Hunan, China, 410008
      • Recruiting
      • Xiangya Hospital of Central South University
      • Contact: Shuwen Kuang, MD.; Phone Number: 0086-13367494221; Email: 228102171@csu.edu.cn
      • Contact: Xuan Gong, MD.; Phone Number: 0086-731-8975-3037; Email: gong.xuan@csu.edu.cn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: N/A

• Sampling Method: Non-Probability Sample

Study Population

Patients with diffuse gliomas located in the intracranial midline.

Description

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.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic accuracy for midline glioma molecular subtypes	Model predictions compared with postoperative histopathology and molecular testing (gold standard). Performance metrics include AUC, F1 score, sensitivity, specificity, and accuracy.	Perioperative

Collaborators and Investigators

• Sponsor: Xiangya Hospital of Central South University

Study record dates

Study Major Dates

• Study Start (Estimated): May 10, 2026
• Primary Completion (Estimated): December 31, 2030
• Study Completion (Estimated): December 31, 2030

Study Registration Dates

• First Submitted: May 7, 2026
• First Submitted That Met QC Criteria: May 25, 2026
• First Posted (Actual): May 27, 2026

Study Record Updates

• Last Update Posted (Actual): May 27, 2026
• Last Update Submitted That Met QC Criteria: May 25, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Keywords: Molecular diagnosis; Prognosis prediction; Midline gliomas; Foundation model
• Additional Relevant MeSH Terms: Neoplasms; Neoplasms by Histologic Type; Neoplasms, Glandular and Epithelial; Neoplasms, Neuroepithelial; Neuroectodermal Tumors; Neoplasms, Germ Cell and Embryonal; Neoplasms, Nerve Tissue; Glioblastoma; Glioma; Astrocytoma
• Other Study ID Numbers: 2026040726

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No