Few-Shot Left Atrial Wall Segmentation in 3D LGE MRI via Meta-Learning

TL;DR

This paper introduces a meta-learning approach for few-shot 3D left atrial wall segmentation in MRI, improving accuracy with minimal labeled data and demonstrating robustness across different datasets.

Contribution

The study proposes a novel MAML-based framework with boundary-aware loss for low-shot atrial wall segmentation, enhancing performance over traditional supervised methods.

Findings

MAML achieved higher Dice scores than supervised fine-tuning at 5-shot.

Performance approached fully supervised results at 20-shot.

Model remained robust under unseen domain shifts and on local cohorts.

Abstract

Segmenting the left atrial wall from late gadolinium enhancement magnetic resonance images (MRI) is challenging due to the wall's thin geometry, low contrast, and the scarcity of expert annotations. We propose a Model-Agnostic Meta-Learning (MAML) framework for K-shot (K = 5, 10, 20) 3D left atrial wall segmentation that is meta-trained on the wall task together with auxiliary left atrial and right atrial cavity tasks and uses a boundary-aware composite loss to emphasize thin-structure accuracy. We evaluated MAML segmentation performance on a hold-out test set and assessed robustness under an unseen synthetic shift and on a distinct local cohort. On the hold-out test set, MAML appeared to improve segmentation performance compared to the supervised fine-tuning model, achieving a Dice score (DSC) of 0.64 vs. 0.52 and HD95 of 5.70 vs. 7.60 mm at 5-shot, and approached the fully supervised reference at 20-shot (0.69 vs. 0.71 DSC). Under unseen shift, performance degraded but remained robust: at 5-shot, MAML attained 0.59 DSC and 5.99 mm HD95 on the unseen domain shift and 0.57 DSC and 6.01 mm HD95 on the local cohort, with consistent gains as K increased. These results suggest that more accurate and reliable thin-wall boundaries are achievable in low-shot adaptation, potentially enabling clinical translation with minimal additional labeling for the assessment of atrial remodeling.