C2W-Tune: Cavity-to -Wall Transfer Learning for Thin Atrial Wall Segmentation in 3D Late Gadolinium-enhanced Magnetic Resonance

2026-03-25

AI Summary

This work addresses the challenge of segmenting the thin left atrial wall in 3D late gadolinium enhancement MRI, where low contrast and complex anatomy hinder accurate delineation. To overcome this, the authors propose an anatomy-aware, two-stage transfer learning framework that leverages chamber-level annotations as anatomical priors. A 3D U-Net architecture—equipped with a ResNeXt encoder and instance normalization—is first pretrained on chamber masks and subsequently fine-tuned for wall segmentation using a progressive layer unfreezing strategy. Evaluated on the 2018 Left Atrial Segmentation Challenge dataset, the method significantly improves wall segmentation performance, increasing the Dice coefficient from 0.623 to 0.814 and reducing the 95th percentile Hausdorff distance (HD95) to 2.55 mm. Notably, even with only 70 training cases, the approach achieves a Dice score of 0.78, outperforming current benchmarks.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Hardware-aware ML
• Natural Language Processing: (Large) Language Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate segmentation of the left atrial (LA) wall in 3D late gadolinium-enhanced MRI (LGE-MRI) is essential for wall thickness mapping and fibrosis quantification, yet it remains challenging due to the wall's thinness, complex anatomy, and low contrast. We propose C2W-Tune, a two-stage cavity-to-wall transfer framework that leverages a high-accuracy LA cavity model as an anatomical prior to improve thin-wall delineation. Using a 3D U-Net with a ResNeXt encoder and instance normalization, Stage 1 pre-trains the network to segment the LA cavity, learning robust atrial representations. Stage 2 transfers these weights and adapts the network to LA wall segmentation using a progressive layer-unfreezing schedule to preserve endocardial features while enabling wall-specific refinement. Experiments on the 2018 LA Segmentation Challenge dataset demonstrate substantial gains over an architecture-matched baseline trained from scratch: wall Dice improves from 0.623 to 0.814, and Surface Dice at 1 mm improves from 0.553 to 0.731. Boundary errors were substantially reduced, with the 95th-percentile Hausdorff distance (HD95) decreasing from 2.95 mm to 2.55 mm and the average symmetric surface distance (ASSD) from 0.71 mm to 0.63 mm. Furthermore, even with reduced supervision (70 training volumes sampled from the same training pool), C2W-Tune achieved a Dice score of 0.78 and an HD95 of 3.15 mm, maintaining competitive performance and exceeding multi-class benchmarks that typically report Dice values around 0.6-0.7. These results show that anatomically grounded task transfer with controlled fine-tuning improves boundary accuracy for thin LA wall segmentation in 3D LGE-MRI.

Problem

• left atrial wall segmentation
• 3D LGE-MRI
• thin wall
• low contrast
• anatomical complexity

Innovation

• transfer learning
• left atrial wall segmentation
• 3D LGE-MRI
• progressive layer-unfreezing
• anatomical prior