发表机构
Vanderbilt University; Mayo Clinic（范德堡大学; 梅奥诊所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出以数据为中心的LISynSeg方法，通过标签到图像合成结合真实图像训练，在不改变nnU-Net架构的情况下改善跨模态全心分割，对MRI的提升更显著。
AI 中文摘要
计算机断层扫描（CT）和磁共振成像（MRI）中的全心分割（WHS）受采集偏移和异质性心脏标注的影响。现有WHS系统结合架构设计、迁移学习以及通用空间或强度增强。我们研究在保持分割架构不变的情况下，改变数据增强和训练监督能否改善跨模态WHS。我们提出LISynSeg，一种以数据为中心的方法，用标签到图像合成增强真实图像的nnU-Net训练。合成体积通过对心脏标签图应用针对训练队列校准的对比度和采集扰动生成，随后与真实图像混合以保留标签（及合成图像）中缺失的胸部上下文。我们通过心肌壁厚的受控变化和不确定血管端点的部分监督来建模心脏标签变化。在CARE全心基准上，仅用合成数据训练的性能差于真实图像nnU-Net基线，而校准的真实-合成混合训练在不改变架构的情况下改善了跨模态分割；对MRI的改善大于对CT的改善。结果表明，修改训练数据策略可有益于异质性心脏数据的模型开发。代码和训练权重将在此httpsURL发布。
英文摘要
Whole-heart segmentation (WHS) in computed tomography (CT) and magnetic resonance imaging (MRI) is affected by acquisition shifts and heterogeneous cardiac annotations. Existing WHS systems combine architectural design, transfer learning, and generic spatial or intensity augmentation. We investigate whether changes to data augmentation and training supervision can improve cross-modality WHS while the segmentation architecture is held constant. We present LISynSeg, a data-centric approach that augments real-image nnU-Net training with label-to-image synthesis. Synthetic volumes are generated from cardiac label maps using contrast and acquisition perturbations calibrated to the training cohort, then mixed with real images to retain thoracic context absent from the labels (and thus the synthesized images). We model cardiac label variation through controlled changes in myocardial wall thickness and partial supervision of uncertain vessel endpoints. On the CARE Whole-Heart benchmark, synthetic-only training performs worse than the real-image nnU-Net baseline, whereas calibrated real-synthetic training improves cross-modality segmentation without changing the architecture; the improvement is larger for MRI than for CT. The results show that modifying the training data strategy can benefit model development for heterogeneous cardiac data. Code and trained weights will be released at https://github.com/MedICL-VU/Care26_LISynSeg.
Comments12 pages, 4 figures
