An AI tool using stimulated Raman histology can predict sites of glioblastoma recurrence before they appear on MRI.
Key Details
- 1AI model combines imaging, clinical, and molecular data to predict glioblastoma recurrence locations.
- 2Developed using 300 samples from 60 patients; validated on 100 samples from 20 patients.
- 3Utilizes stimulated Raman histology (SRH) to produce rapid, dye-free microscopic images of brain tissue.
- 4AI-based tumor infiltration score matched conventional pathology in predicting recurrences.
- 5Combined model outperformed individual methods, distinguishing tissue likely to recur within 5-10mm accuracy.
- 6Findings published in Science Advances by UC San Francisco and University of Michigan.
Why It Matters
Early and accurate prediction of glioblastoma recurrence sites enables more targeted therapies and may improve patient outcomes. This research highlights the growing synergy between rapid intraoperative imaging and AI for real-time decision-making in neuro-oncology.
Source
EurekAlert
Related News
•EurekAlert
AI Combines CT and Pathology to Predict Esophageal Cancer Survival
A new AI framework (MENISA) combines CT scans, digital pathology, and tumor microenvironment data to predict survival risk for esophageal squamous cell carcinoma.
•EurekAlert
AI Now Drives Major Advances Across Scientific Fields, Report Finds
A comprehensive global analysis reveals AI as a cross-disciplinary engine, notably powering radiology and diagnostic innovations.
•EurekAlert
Photonic Encoder Transforms Medical Signals for Ultrafast AI Diagnosis
Researchers created a fiber-compatible, all-optical biomimetic spike encoder enabling rapid, precise conversion of medical signals for neuromorphic analysis.