Guardado en:
Detalles Bibliográficos
Autores principales: Al-Sanaani, Yusri, Thornhill, Rebecca, Nery, Pablo, Pena, Elena, deKemp, Robert, Redpath, Calum, Birnie, David, Rajan, Sreeraman
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.24985
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916037625118720
author Al-Sanaani, Yusri
Thornhill, Rebecca
Nery, Pablo
Pena, Elena
deKemp, Robert
Redpath, Calum
Birnie, David
Rajan, Sreeraman
author_facet Al-Sanaani, Yusri
Thornhill, Rebecca
Nery, Pablo
Pena, Elena
deKemp, Robert
Redpath, Calum
Birnie, David
Rajan, Sreeraman
contents Segmenting the left atrial (LA) wall from late gadolinium enhancement magnetic resonance imaging (LGE-MRI) is challenging because of its thin geometry, low contrast, and limited expert annotations. We propose a model-agnostic meta-learning (MAML) framework with a 3D residual U-Net backbone for K-shot (K = 5, 10, 20) LA wall segmentation. The framework is meta-trained on LA wall tasks together with auxiliary LA and right atrial (RA) cavity tasks and uses a boundary-aware composite loss to improve thin-structure delineation. We evaluated MAML on a held-out clean test set and assessed its robustness under an unseen synthetic domain shift and on a local cohort. On the held-out clean test set, MAML outperformed the K-shot fine-tuning baseline at 5-shot, achieving Dice coefficient (DSC) = 0.54 versus 0.48 and Hausdorff distance (HD95) = 4.60 versus 6.40 mm. At 20-shot, MAML approached the fully supervised model trained from scratch, with DSC = 0.59 versus 0.61. Under unseen shifts, performance decreased relative to clean testing but improved consistently as K increased. At 5-shot, MAML achieved DSC = 0.52 and HD95 = 5.02 mm under the unseen synthetic shift, and DSC = 0.50 and HD95 = 5.43 mm on the local cohort. These results suggest that meta-learning can improve thin-wall delineation in low-shot adaptation and may reduce the annotation burden for atrial remodeling assessment.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24985
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Few-Shot Left Atrial Wall Segmentation in 3D LGE MRI via Meta-Learning
Al-Sanaani, Yusri
Thornhill, Rebecca
Nery, Pablo
Pena, Elena
deKemp, Robert
Redpath, Calum
Birnie, David
Rajan, Sreeraman
Computer Vision and Pattern Recognition
Segmenting the left atrial (LA) wall from late gadolinium enhancement magnetic resonance imaging (LGE-MRI) is challenging because of its thin geometry, low contrast, and limited expert annotations. We propose a model-agnostic meta-learning (MAML) framework with a 3D residual U-Net backbone for K-shot (K = 5, 10, 20) LA wall segmentation. The framework is meta-trained on LA wall tasks together with auxiliary LA and right atrial (RA) cavity tasks and uses a boundary-aware composite loss to improve thin-structure delineation. We evaluated MAML on a held-out clean test set and assessed its robustness under an unseen synthetic domain shift and on a local cohort. On the held-out clean test set, MAML outperformed the K-shot fine-tuning baseline at 5-shot, achieving Dice coefficient (DSC) = 0.54 versus 0.48 and Hausdorff distance (HD95) = 4.60 versus 6.40 mm. At 20-shot, MAML approached the fully supervised model trained from scratch, with DSC = 0.59 versus 0.61. Under unseen shifts, performance decreased relative to clean testing but improved consistently as K increased. At 5-shot, MAML achieved DSC = 0.52 and HD95 = 5.02 mm under the unseen synthetic shift, and DSC = 0.50 and HD95 = 5.43 mm on the local cohort. These results suggest that meta-learning can improve thin-wall delineation in low-shot adaptation and may reduce the annotation burden for atrial remodeling assessment.
title Few-Shot Left Atrial Wall Segmentation in 3D LGE MRI via Meta-Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.24985