用自监督视觉模型DINOv3提升非增强CT的卒中分析能力
Benchmarking DINOv3 for Multi-Task Stroke Analysis on Non-Contrast CT
- 基于DINOv3提取多任务特征，统一处理卒中图像分析
- 在多个数据集上实现病灶分割与分类的先进性能
- 适合医学影像自动化诊断研究者参考
非增强计算机断层扫描（NCCT）对快速卒中诊断至关重要，但受限于低对比度和信噪比。我们利用当前最先进的自监督视觉变压器DINOv3，生成强大的特征表示，用于全面的卒中分析任务。评估涵盖梗死与出血分割、异常分类（正常 vs. 卒中，正常 vs. 梗死 vs. 出血）、出血亚型分类（EDH、SDH、SAH、IPH、IVH）以及二值化ASPECTS分类（≤6 vs. >6），在多个公开和私有数据集上进行。本研究为这些任务建立了强基准，并展示了先进自监督模型在提高从NCCT自动诊断卒中方面的潜力，同时清晰分析了该方法的优势与现有局限。代码已开源：https://github.com/Zzz0251/DINOv3-stroke。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。