Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.23132 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916974113587200 |
|---|---|
| author | Zhang, Donghao Chen, Yimin Duarte, Kauê TN Aslan, Taha AlShamrani, Mohamed Karmur, Brij Wan, Yan Chen, Shengcai Hu, Bo Menon, Bijoy K Qiu, Wu |
| author_facet | Zhang, Donghao Chen, Yimin Duarte, Kauê TN Aslan, Taha AlShamrani, Mohamed Karmur, Brij Wan, Yan Chen, Shengcai Hu, Bo Menon, Bijoy K Qiu, Wu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23132 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Benchmarking DINOv3 for Multi-Task Stroke Analysis on Non-Contrast CT Zhang, Donghao Chen, Yimin Duarte, Kauê TN Aslan, Taha AlShamrani, Mohamed Karmur, Brij Wan, Yan Chen, Shengcai Hu, Bo Menon, Bijoy K Qiu, Wu Computer Vision and Pattern Recognition 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. |
| title | Benchmarking DINOv3 for Multi-Task Stroke Analysis on Non-Contrast CT |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.23132 |