LA-CaRe-CNN: Cascading Refinement CNN for Left Atrial Scar Segmentation

2025-08-06

AI Summary

This study addresses the challenge of accurate segmentation of the left atrium (LA) and LA scar tissue in late gadolinium enhancement magnetic resonance (LGE-MR) images. We propose an end-to-end trainable two-stage 3D cascaded CNN: the first stage performs coarse LA segmentation, while the second stage refines scar segmentation by jointly leveraging raw input images and intermediate features. To enhance generalizability and robustness, we introduce intensity-spatial joint data augmentation and a five-fold ensemble strategy. Evaluated on a public benchmark dataset, our method achieves 89.21% Dice similarity coefficient (DSC) and 1.697 mm average surface distance (ASSD) for LA segmentation, and 64.59% DSC with 91.80% global DSC (G-DSC) for scar segmentation. These results establish a high-precision, clinically translatable foundation for personalized ablation planning and digital twin heart modeling in atrial fibrillation patients.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Atrial fibrillation (AF) represents the most prevalent type of cardiac arrhythmia for which treatment may require patients to undergo ablation therapy. In this surgery cardiac tissues are locally scarred on purpose to prevent electrical signals from causing arrhythmia. Patient-specific cardiac digital twin models show great potential for personalized ablation therapy, however, they demand accurate semantic segmentation of healthy and scarred tissue typically obtained from late gadolinium enhanced (LGE) magnetic resonance (MR) scans. In this work we propose the Left Atrial Cascading Refinement CNN (LA-CaRe-CNN), which aims to accurately segment the left atrium as well as left atrial scar tissue from LGE MR scans. LA-CaRe-CNN is a 2-stage CNN cascade that is trained end-to-end in 3D, where Stage 1 generates a prediction for the left atrium, which is then refined in Stage 2 in conjunction with the original image information to obtain a prediction for the left atrial scar tissue. To account for domain shift towards domains unknown during training, we employ strong intensity and spatial augmentation to increase the diversity of the training dataset. Our proposed method based on a 5-fold ensemble achieves great segmentation results, namely, 89.21% DSC and 1.6969 mm ASSD for the left atrium, as well as 64.59% DSC and 91.80% G-DSC for the more challenging left atrial scar tissue. Thus, segmentations obtained through LA-CaRe-CNN show great potential for the generation of patient-specific cardiac digital twin models and downstream tasks like personalized targeted ablation therapy to treat AF.

Problem

• Segment left atrium and scar tissue from LGE MR scans.
• Improve accuracy for patient-specific cardiac digital twin models.
• Address domain shift with strong data augmentation techniques.

Innovation

• 2-stage CNN cascade for left atrial segmentation
• 3D end-to-end training with refinement
• Strong intensity and spatial augmentation