Multi-Stage Bi-Atrial Segmentation Framework from 3D Late Gadolinium-Enhanced MRI using V-Net Family Models

TL;DR

This paper introduces a multi-stage V-Net based framework for precise bi-atrial segmentation from 3D LGE MRI, involving preprocessing, coarse, and fine segmentation steps with asymmetric loss optimization.

Contribution

The novel multi-stage pipeline combines preprocessing and dual V-Net models for improved bi-atrial segmentation accuracy from 3D MRI.

Findings

Effective preprocessing with MCLAHE enhances segmentation quality.

Two-stage V-Net approach improves segmentation precision.

Asymmetric loss optimizes model performance.

Abstract

We report our multi-stage framework designed for the problem of multi-class bi-atrial segmentation from 3D late gadolinium-enhanced (LGE) MRI of the human heart. The pipeline consists of a preprocessing step using multidimensional contrast limited adaptive histogram equalization (MCLAHE); coarse region segmentation from MCLAHE-enhanced and down-sampled MRI using a V-Net family model; and fine segmentation from the coarse region using another V-Net model. Asymmetric loss is adopted to optimize the model weights.