LISynSeg: Data-Centric Label-to-Image Synthesis for Cross-Modality Whole-Heart Segmentation

2026-08-31

AI Summary

研究通过LISynSeg方法，利用标签到图像合成技术改进跨模态全心分割问题，调整数据增强和训练监督策略以提高模型性能。

Abstract

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.

Problem

• Whole-Heart Segmentation
• Cross-Modality
• Data Augmentation
• Label-to-Image Synthesis

Innovation

• label-to-image synthesis
• data-centric approach
• cross-modality segmentation
• cardiac label variation