通过优化预处理提升脑卒中病灶分割精度
How We Won the ISLES'24 Challenge by Preprocessing
- 采用深度学习颅骨剥离与自定义窗宽增强图像质量
- 在仅用CT输入条件下实现28.5的平均Dice分数
- 适合关注医学图像预处理与临床实用性的研究者
脑卒中是全球三大致死病因之一，准确识别病灶边界对诊断和治疗至关重要。监督式深度学习已成为脑卒中病灶分割的主流方法，但需大量多样且标注完整的数据集。ISLES'24挑战赛提供了纵向脑卒中影像数据，包括入院时的CT扫描及入院后2-9天的随访MRI，标注基于随访MRI生成。值得注意的是，提交模型仅使用CT输入，需预测在初始CT上不可见的病灶进展情况。我们的获胜方案表明，精心设计的预处理流程——包括基于深度学习的颅骨剥离与定制化强度窗宽处理——显著提升了分割准确性。结合标准的大残差nnU-Net架构，该方法在测试集上取得28.5的平均Dice分数，标准差为21.27。
原文摘要 · Abstract (English)
Stroke is among the top three causes of death worldwide, and accurate identification of stroke lesion boundaries is critical for diagnosis and treatment. Supervised deep learning methods have emerged as the leading solution for stroke lesion segmentation but require large, diverse, and annotated datasets. The ISLES'24 challenge addresses this need by providing longitudinal stroke imaging data, including CT scans taken on arrival to the hospital and follow-up MRI taken 2-9 days from initial arrival, with annotations derived from follow-up MRI. Importantly, models submitted to the ISLES'24 challenge are evaluated using only CT inputs, requiring prediction of lesion progression that may not be visible in CT scans for segmentation. Our winning solution shows that a carefully designed preprocessing pipeline including deep-learning-based skull stripping and custom intensity windowing is beneficial for accurate segmentation. Combined with a standard large residual nnU-Net architecture for segmentation, this approach achieves a mean test Dice of 28.5 with a standard deviation of 21.27.
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。