Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition
9 May 2026 – 14 May 2026 · Cape Town, South Africa
568-01-011 ISMRM Abstract

Slice-Level Attention Aggregation of DINOv2 Features Enables Automated Headache Subtyping from Brain MRI

Primary: Analysis Methods - Classification and Prediction
Secondary: Neuro - Traumatic Brain Injury
568-01-011 · Unconventional Physics and Engineering · Wednesday, 13 May, 8:20 AM–9:15 AM · Digital Posters Row I
Keywords: Brain Headache Deep learning MRI Foundation model
Accepted
Fazle Rafsani1,2, Jay Shah1,2, Catherine Chong2,3, Simona Nikolova3, Dhiego S Andrade 3, Gina Dumkrieger3, Baoxin Li1,2, Teressa Wu1,2, Todd Schwedt2,3
1School of Computing and Augmented intelligence, Arizona State University, Tempe, United States of America
2ASU-Mayo Center for Innovative Imaging, United States of America
3Mayo Clinic Arizona, Phoenix, United States of America
Presenting Author: Dhiego S Andrade

Synopsis

Motivation:
Goals:
Approach:
Results:
Full abstract & presentation

The full text, figures, and any recorded presentation for this abstract are not shown here. Log in if you are a member or registered attendee with access.

Full abstracts, figures, and presentations for Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition are available to registered attendees. This content becomes freely available to the public roughly two years after the meeting.

To request or purchase access, contact the ISMRM Central Office at info@ismrm.org.

Log in

References

1. Rafsani, Fazle, et al. "Using Large-scale Contrastive Language-Image Pre-training to Maximize Brain MRI-Based Headache Classification (P4-12.007)." Neurology. Vol. 104. No. 7_Supplement_1. Hagerstown, MD: Lippincott Williams & Wilkins, 2025.
2. Rahman Siddiquee, Md Mahfuzur, et al. "Headache classification and automatic biomarker extraction from structural MRIs using deep learning." Brain Communications 5.1 (2023): fcac311.
3. Rafsani, Fazle, et al. "Leveraging multi-modal foundation model image encoders to enhance brain MRI-based headache classification." Scientific Reports 15.1 (2025): 33256.
4. Rafsani, Fazle, et al. "DinoAtten3D: Slice-Level Attention Aggregation of DinoV2 for 3D Brain MRI Anomaly Classification." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2025.
5. Oquab, Maxime, et al. "Dinov2: Learning robust visual features without supervision." arXiv preprint arXiv:2304.07193 (2023).

Cite this abstract

http://echo.ismrm.org/p/ISMRM2026/568-01-011