Presented abstract AHS 2026 annual meeting @ Orlando, FL

In this study, we developed and evaluated a foundation-model-based deep learning framework for classifying acute post-traumatic headache from structural brain MRI. The work showed that training with more disease-specific examples and preserving complete brain information improved the model’s ability to distinguish patients from healthy individuals. These findings highlight the importance of high-quality labeled medical data and comprehensive brain representations for building more reliable AI tools for neurological diagnosis.

Jun 4, 2026 1:00 PM — 3:00 PM