Back to all news
AI Model Improves Differentiation of Brain Tumor Progression from Radiation Necrosis on MRI
A York University-led study shows a novel AI using advanced MRI can distinguish between progressive brain tumors and radiation necrosis more accurately than human assessment.
Key Details
- 1AI model uses attention-guided deep learning with chemical exchange saturation transfer (CEST) MRI.
- 2Study included over 90 patients with brain metastases treated by stereotactic radiosurgery (SRS).
- 3AI achieved over 85% accuracy in distinguishing tumor progression from necrosis, compared to ~60% for standard MRI and ~70% for advanced MRI alone.
- 4Published December 2025 in International Journal of Radiation Oncology, Biology, Physics.
- 5A crucial clinical challenge as treatment decisions for tumor progression vs necrosis are substantially different.
Why It Matters
Differentiating tumor progression from radiation necrosis on MRI post-therapy is a major clinical challenge, as each requires different treatments. AI that improves diagnosis accuracy could substantially impact patient management and outcomes in neuro-oncology.
Source
EurekAlert
Related News
•EurekAlert
AutoML Model Accurately Differentiates Brain Tumors on MRI
Thomas Jefferson University researchers developed an AutoML model that distinguishes pituitary macroadenomas from parasellar meningiomas on MRI with over 97% accuracy.
•EurekAlert
AI Model Accurately Flags Brain MRI Abnormalities, Eases Radiologist Burden
A new AI model can accurately flag brain abnormalities in MRI scans, potentially streamlining triage and diagnosis for radiologists.
•EurekAlert
UCLA Researchers Present AI, Blood Biomarker Advances at SABCS 2025
UCLA Health researchers unveil major advances in breast cancer AI pathology, liquid biopsy, and biomarker strategies at the 2025 SABCS.