A Two Stage Pipeline for Left Atrial Wall Constrained Scar Segmentation and Localization from LGE-MR Images

TL;DR

This paper presents a two-stage nnUNet-based framework for precise segmentation and localization of left atrial scars in LGE-MRI, incorporating anatomy-aware inputs and specialized loss functions to improve accuracy.

Contribution

The method introduces a geometry-aware, anatomy-conditioned approach with a novel loss strategy to enhance scar segmentation and localization in challenging LGE-MRI data.

Findings

Achieved a Dice score of 61.1% on LAScarQS 2022 dataset.

Reduced false positives far from the atrial wall.

Improved stability and accuracy of scar segmentation.

Abstract

Accurate segmentation and localization of left atrial (LA) ablation scars from Late gadolinium enhancement (LGE)-MRI is essential for assessing the lesion completeness and guiding ablation therapy. Incomplete or discontinuous lesions can increase the recurrence rate of the therapy and inaccurate localization can misguide treatment planning. However, reliable quantification and localization of scar in LGE-MRI is challenging. The severely class imbalanced scar voxels, thin structure of the LA wall, and weak tissue contrast often lead to unrealistic scar predictions. In this paper, we propose a two stage nnUNet based framework that takes LA anatomy into account to help with more precise scar localization and segmentation. In the first stage, an nnUNet model is trained to segment the LA cavity. In the second stage, patient specific cavity and wall signed distance maps (SDMs) are derived from the predicted anatomy to use as geometry aware inputs, and explicitly encode each voxel's signed spatial relationship to the atrial cavity and wall. This approach transforms scar segmentation from a solely intensity-based classification into anatomy-conditioned localization task, providing a continuous spatial prior that stabilizes learning for the thin atrial wall and suppresses topologically invalid predictions. To further address boundary ambiguity, we introduce a wall ROI-masked weighted loss combined with boundary uncertainty-aware supervision strategy that restricts learning to the atrial wall, while accounting for severe class imbalance. We evaluated our approach on the LAScarQS 2022 dataset and achieved a Dice of 61.1% and ASSD of 1.711mm. Our reliable and effective framework improves scar segmentation and localization accuracy by enforcing anatomical validity through geometry-aware supervision, and lowering the false positive detections far away from the atrial wall.