用临床解剖先验提升脑卒中梗死区分割精度
Clinically-aligned ischemic stroke segmentation and ASPECTS scoring on NCCT imaging using a slice-gated loss on foundation representations
- 基于DINOv3骨架+轻量解码器，引入区域感知门控损失
- 在AISD数据集上达Dice 0.6385，ASPECTS数据集提升0.069
- 适合需要精准临床评分的医学影像分析场景
非增强CT（NCCT）上的快速梗死评估对急性缺血性卒中管理至关重要。现有深度学习方法多为像素级分割，未建模ASPECTS评分背后的结构化解剖逻辑，而基底节（BG）与皮层下（SG）区域需协同判断。本文提出一种临床对齐框架，采用冻结的DINOv3主干网络与轻量解码器，并引入区域感知门控损失（TAGL），在训练中强制BG-SG一致性。该方法不增加推理开销。在AISD数据集上，模型取得0.6385的Dice分数，优于先前的CNN与基础模型。在自有ASPECTS数据集上，平均Dice从0.698提升至0.767。结果表明，融合基础表征与结构化临床先验可显著提升NCCT卒中分割与ASPECTS判读性能。
原文摘要 · Abstract (English)
Rapid infarct assessment on non-contrast CT (NCCT) is essential for acute ischemic stroke management. Most deep learning methods perform pixel-wise segmentation without modeling the structured anatomical reasoning underlying ASPECTS scoring, where basal ganglia (BG) and supraganglionic (SG) levels are clinically interpreted in a coupled manner. We propose a clinically aligned framework that combines a frozen DINOv3 backbone with a lightweight decoder and introduce a Territory-Aware Gated Loss (TAGL) to enforce BG-SG consistency during training. This anatomically informed supervision adds no inference-time complexity. Our method achieves a Dice score of 0.6385 on AISD, outperforming prior CNN and foundation-model baselines. On a proprietary ASPECTS dataset, TAGL improves mean Dice from 0.698 to 0.767. These results demonstrate that integrating foundation representations with structured clinical priors improves NCCT stroke segmentation and ASPECTS delineation.
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。