Mayo Clinic study shows AI can reveal brain tumor risks without costly genetic testing

Mayo Clinic researchers and collaborators utilized artificial intelligence (AI) to analyze routine pathology slides for classifying meningiomas, the most common primary brain tumor in adults, and to predict tumor recurrence risk.
The study, published in The Lancet Digital Health, demonstrates that deep learning models can extract molecular and prognostic information from H&E slides, traditionally used for standard clinical care without the need for advanced genetic testing.
Deep learning can perform diagnostics and predict outcomes similarly to DNA methylation profiling, which is often costly, time-consuming, and unavailable in many hospitals.
The AI models trained on data from 672 patients revealed patterns of tumor heterogeneity that might explain differences in tumor behavior and treatment response, potentially guiding personalized treatment decisions.
The findings suggest that AI could help clinicians obtain detailed tumor information, possibly eliminating the need for expensive and complex molecular testing, which may improve access to advanced diagnostic care globally.

You may have missed