Benchmarking DINOv3 for Multi-Task Stroke Analysis on Non-Contrast CT
This work addresses automated stroke diagnosis from non-contrast CT, which is crucial for rapid clinical assessment, but it is incremental as it applies an existing method to a new medical imaging domain.
The authors tackled the challenge of low image contrast and signal-to-noise ratio in non-contrast CT for stroke diagnosis by applying DINOv3, a self-supervised vision transformer, to generate feature representations for multiple stroke analysis tasks, establishing strong benchmarks across infarct and hemorrhage segmentation, classification, and ASPECTS classification on various datasets.
Non-contrast computed tomography (NCCT) is essential for rapid stroke diagnosis but is limited by low image contrast and signal to noise ratio. We address this challenge by leveraging DINOv3, a state-of-the-art self-supervised vision transformer, to generate powerful feature representations for a comprehensive set of stroke analysis tasks. Our evaluation encompasses infarct and hemorrhage segmentation, anomaly classification (normal vs. stroke and normal vs. infarct vs. hemorrhage), hemorrhage subtype classification (EDH, SDH, SAH, IPH, IVH), and dichotomized ASPECTS classification (<=6 vs. >6) on multiple public and private datasets. This study establishes strong benchmarks for these tasks and demonstrates the potential of advanced self-supervised models to improve automated stroke diagnosis from NCCT, providing a clear analysis of both the advantages and current constraints of the approach. The code is available at https://github.com/Zzz0251/DINOv3-stroke.