Fully Automated Left Atrium Cavity Segmentation from 3D GE-MRI by Multi-Atlas Selection and Registration

TL;DR

This paper introduces a fully automated multi-step method for segmenting the left atrial cavity from 3D GE-MRI scans, combining preprocessing, atlas selection, registration, fusion, and refinement, achieving high accuracy.

Contribution

It presents a novel automated segmentation approach using multi-atlas selection and registration, improving accuracy over manual annotation.

Findings

Achieved an average Dice overlap index of 0.88.

Validated on MICCAI 2018 STACOM Challenge dataset.

Demonstrated effectiveness of multi-atlas registration and fusion.

Abstract

This paper presents a fully automated method to segment the complex left atrial (LA) cavity, from 3D Gadolinium-enhanced magnetic resonance imaging (GE-MRI) scans. The proposed method consists of four steps: (1) preprocessing to convert the original GE-MRI to a probability map, (2) atlas selection to match the atlases to the target image, (3) multi-atlas registration and fusion, and (4) level-set refinement. The method was evaluated on the datasets provided by the MICCAI 2018 STACOM Challenge with 100 dataset for training. Compared to manual annotation, the proposed method achieved an average Dice overlap index of 0.88.