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
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.