GliomaAI-Astro23: MRI-Based Detection of IDH Mutant Astrocytoma (Grade 2 and 3)

NCT07673666 — Completed, 1372 participants, Deep Learning Institute of Radiological Sciences

ClinicalTrials Daily · Areas · Conditions · Drugs · Sponsors ·

GliomaAI-Astro23: Non-Invasive MRI-Based Detection of IDH Mutant Astrocytoma (Grade 2 and 3) Using Artificial Intelligence

Registry	NCT07673666, acronym GliomaAI-A23
Status	Completed
Study type	Observational
Enrollment	1372 (Actual)
Sponsor	Deep Learning Institute of Radiological Sciences (Other)
Conditions	Glioma, Glioma (Diagnosis), Astrocytoma, Astrocytoma of Brain, Astrocytoma, Grade II, Astrocytoma, IDH-Mutant, Grade 2, Astrocytoma, IDH-Mutant, Grade 3
Interventions	GliomaAI-Astro23 (Device)
Dates	start 2017-03-14, primary completion 2021-03-09, completion 2021-07-16, first posted 2026-06-29, last updated 2026-06-29
Locations	1 site in India

-Summary

The goal of this observational study is to learn whether an artificial intelligence system called GliomaAI-Astro23 can help detect a specific molecular type of brain tumour called IDH mutant Astrocytoma (grade 2 and 3) using routine MRI scans. The study uses previously collected and fully anonymised MRI data from 1,372 patients from 13 institutions in the Cancer Imaging Archive (TCIA).

The main questions it aims to answer are:

* How accurately can GliomaAI-Astro23 identify IDH mutant Astrocytoma (grade 2 and 3) from MRI scans?
* How well does the system perform across data from different hospitals and patient groups?

Researchers will use existing MRI scans and clinical information to train and test the AI system. No new scans, treatments, or hospital visits are required for participants, and all data used is fully anonymised and obtained from an existing research database.

Participants will not be asked to do anything, as this study only uses previously collected imaging data.

Expand all sections · Collapse all

+Arms and interventions

GliomaAI-Astro23 (Device): Software as Medical Device (SaMD) for predicting astrocytoma (grade 2 and 3)

+Outcome measures

Primary outcomes

Diagnostic performance of GliomaAI-Astro23 for identification of IDH mutant Astrocytoma (grade 2 and 3) from MRI, measured by accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the ROC [Perioperative]: The diagnostic performance of the GliomaAI-Astro23 artificial intelligence model will be assessed by comparing pre-operative MRI-based predictions of IDH mutant Astrocytoma (grade 2 and 3) status against post-operative (biopsy or surgery) molecular/genetic profiling results as the reference standard. Performance metrics including accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and AUC will be calculated.

+Eligibility

Sex: All, ages: 18 Years to any

Inclusion Criteria:

* Adult (>=18 years of age)
* Having pre op MRI scan
* Having biopsy / surgery
* Having post biopsy/ surgery histology diagnosis and genetic analysis.

Exclusion Criteria:

* MRI scan significantly degraded by motion or other artefact
* Incomplete genetic analysis
* Prior treatment (e.g., radiotherapy or chemotherapy) before baseline MRI

+Locations (1)

Facility	City	Country	Status
Deep Learning Institute of Radiological Sciences	Mumbai	India