通过动态贴图增强，提升多中心T1加权脑卒中病灶分割准确率
Native-Space 3D CarveMix for Multi-Site T1w Stroke Segmentation
- 训练时动态将真实病灶块贴入健康脑区生成合成数据
- 在55个中心的1453张图像上达到0.648的平均Dice分数
- 特别改善了急性期病灶分割，适合临床多中心应用
在未进行强度标准化的多中心T1w MRI上分割缺血性脑卒中病灶极具挑战，因病灶微弱且与脑脊液强度相似。现有深度学习模型在多中心数据上表现受限，平均Dice仅为0.66，尤其急性期（发病7天内）病灶因样本稀缺而表现更差。本文结合MedNeXt-L（k=5）主干网络与实时3D CarveMix增强技术，在训练过程中动态将真实病灶区域贴入健康脑组织，实现无需预存副本的多样化病灶分布模拟。采用受试者级划分隔离策略，确保每轮交叉验证中数据独立。在ISLES 2026挑战赛的55个临床中心共1453例原生T1w扫描数据上评估，模型在500轮训练后取得平均5折交叉验证Dice为0.648，较同训练预算下的MedNeXt-L基线（0.630）提升0.018。
原文摘要 · Abstract (English)
Segmenting ischemic stroke lesions on T1-weighted (T1w) MRI acquired across different scanners and protocols without intensity standardization is difficult because lesions are subtle and share intensity characteristics with cerebrospinal fluid. Standard deep learning architectures trained across multiple centers plateau around Dice 0.66, with acute lesions ($\le 7$ days post-stroke) performing substantially worse due to severe sample scarcity. We combine a MedNeXt-L ($k=5$) backbone with on-the-fly 3D CarveMix augmentation that pastes real lesion patches into healthy brain regions during training. By generating synthetic lesion placements dynamically within each fold with subject-level split isolation, the model sees more diverse lesion patterns without requiring pre-generated copies on disk. We evaluate on 1,453 native T1w scans from 55 clinical centers in the ISLES 2026 challenge. Our method achieves a mean 5-fold cross-validation Dice of 0.648 at 500 epochs, a +0.018 improvement over the MedNeXt-L backbone at a matched training budget (0.630)
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。