# Benchmarking DINOv3 for Multi-Task Stroke Analysis on Non-Contrast CT

arXiv: https://arxiv.org/abs/2509.23132 · HTML: https://mlsanity.com/paper/2509.23132/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision](https://mlsanity.com/paper/2310.18689/) (2023)
- [Vision Foundation Models in Remote Sensing: A Survey](https://mlsanity.com/paper/2408.03464/) (2024)
- [Intracranial Hemorrhage Segmentation Using Deep Convolutional Model](https://mlsanity.com/paper/1910.08643/) (2019)
- [BHSD: A 3D Multi-Class Brain Hemorrhage Segmentation Dataset](https://mlsanity.com/paper/2308.11298/) (2023)
- [SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3](https://mlsanity.com/paper/2509.00833/) (2025)
- [Symmetry-Enhanced Attention Network for Acute Ischemic Infarct Segmentation with Non-Contrast CT Images](https://mlsanity.com/paper/2110.05039/) (2021)
- [ISLES'24 -- A Real-World Longitudinal Multimodal Stroke Dataset](https://mlsanity.com/paper/2408.11142/) (2024)
- [ISLES'24: Final Infarct Prediction with Multimodal Imaging and Clinical Data. Where Do We Stand?](https://mlsanity.com/paper/2408.10966/) (2024)

## Built on by (most cited first, 2 of 2)

- [Clinically-aligned ischemic stroke segmentation and ASPECTS scoring on NCCT imaging using a slice-gated loss on foundation representations](https://mlsanity.com/paper/2602.23961/) (2026)
- [RADIO1D: Elastic Representations for Condensed Vision Modeling](https://mlsanity.com/paper/2607.03624/) (2026)

## Abstract (arXiv)

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.