AI-assisted diagnosis for malignant brain tumors

Research on AI-assisted Diagnosis of Common Malignant Brain Tumors Based on Magnetic Resonance Imaging

Observational Second Affiliated Hospital, School of Medicine, Zhejiang University · NCT07198256

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.

Quick facts

Study typeObservational
Enrollment3000 (estimated)
Ages18 Years to 100 Years
SexAll
SponsorSecond Affiliated Hospital, School of Medicine, Zhejiang University Academic / other
Locations2 sites (Hangzhou, Zhejiang and 1 other locations)
Trial IDNCT07198256 on ClinicalTrials.gov

What this trial studies

This retrospective, multi-center effort will build a large MRI database of about 3,000 adults with histologically confirmed malignant brain tumors (gliomas, brain metastases, and lymphomas) using preoperative CE-T1WI and T2-FLAIR images acquired on 1.5T or 3.0T scanners. Data are collected at two major centers in Hangzhou and will be used to train deep learning models for lesion segmentation and multi-subtype tumor classification. The work focuses on improving accuracy of non-invasive preoperative diagnosis across multiple tumor types and complex lesion anatomies by addressing prior small-sample and single-center limitations. The ultimate aim is an image-based AI-assisted diagnostic tool that can reduce unnecessary biopsies and support clinical decision making.

Who should consider this trial

Good fit: Adults (18 years or older) with histopathologically confirmed glioma, brain metastasis, or brain lymphoma who had complete preoperative CE-T1WI and T2-FLAIR MRI are the ideal candidates for inclusion.

Not a fit: Patients with poor image quality, a history of prior brain surgery or radiotherapy, other concurrent intracranial lesions, or under 18 years old are unlikely to benefit from this dataset or model development.

Why it matters

Potential benefit: If successful, the AI system could improve the accuracy of non-invasive preoperative diagnosis of malignant brain tumors and reduce the need for diagnostic biopsies.

How similar studies have performed: Deep learning methods for brain tumor segmentation and some subtype classification have shown promising results (for example in BraTS and other research), but prior work has been limited by smaller or single-center datasets and variable classification performance.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Patients diagnosed with glioma, brain metastases, and brain lymphoma by pathology, with the patient being at least 18 years old; preoperative MRI was complete.

Exclusion Criteria:

* Poor image quality; history of previous brain surgery or radiotherapy; accompanied by other intracranial lesions.

Where this trial is running

Hangzhou, Zhejiang and 1 other locations

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions GliomasBrain Metastases, AdultLymphomaBrain Tumor Adultbrain tumorgliomabrain metastaseslymphoma
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.