Left Atrial Segmentation with nnU-Net Using MRI

TL;DR

This paper demonstrates that nnU-Net, an automated deep learning framework, effectively segments the left atrium from cardiac MRI with high accuracy, outperforming traditional methods and showing robustness across diverse data variations.

Contribution

The study applies nnU-Net to left atrial MRI segmentation, showcasing its automated configuration and superior performance over existing approaches.

Findings

Achieved a mean Dice score of 93.5

Outperformed traditional segmentation methods

Demonstrated robustness across data variations

Abstract

Accurate segmentation of the left atrium (LA) from cardiac MRI is critical for guiding atrial fibrillation (AF) ablation and constructing biophysical cardiac models. Manual delineation is time-consuming, observer-dependent, and impractical for large-scale or time-sensitive clinical workflows. Deep learning methods, particularly convolutional architectures, have recently demonstrated superior performance in medical image segmentation tasks. In this study, we applied the nnU-Net framework, an automated, self-configuring deep learning segmentation architecture, to the Left Atrial Segmentation Challenge 2013 dataset. The dataset consists of thirty MRI scans with corresponding expert-annotated masks. The nnU-Net model automatically adapted its preprocessing, network configuration, and training pipeline to the characteristics of the MRI data. Model performance was quantitatively evaluated using the Dice similarity coefficient (DSC), and qualitative results were compared against expert segmentations. The proposed nnUNet model achieved a mean Dice score of 93.5, demonstrating high overlap with expert annotations and outperforming several traditional segmentation approaches reported in previous studies. The network exhibited robust generalization across variations in left atrial shape, contrast, and image quality, accurately delineating both the atrial body and proximal pulmonary veins.