Right Ventricular Segmentation from Short- and Long-Axis MRIs via Information Transition

TL;DR

This paper introduces an automatic right ventricular segmentation method from MRI that leverages information from long-axis views to enhance short-axis view segmentation, addressing challenges like heterogeneous intensities and complex shapes.

Contribution

The novel framework utilizes information transition from LA to SA views, improving segmentation accuracy especially at challenging basal and apical slices.

Findings

Improved segmentation accuracy with LA view assistance.

Effective removal of ambiguous regions in SA views.

Validated on a diverse multi-center dataset.

Abstract

Right ventricular (RV) segmentation from magnetic resonance imaging (MRI) is a crucial step for cardiac morphology and function analysis. However, automatic RV segmentation from MRI is still challenging, mainly due to the heterogeneous intensity, the complex variable shapes, and the unclear RV boundary. Moreover, current methods for the RV segmentation tend to suffer from performance degradation at the basal and apical slices of MRI. In this work, we propose an automatic RV segmentation framework, where the information from long-axis (LA) views is utilized to assist the segmentation of short-axis (SA) views via information transition. Specifically, we employed the transformed segmentation from LA views as a prior information, to extract the ROI from SA views for better segmentation. The information transition aims to remove the surrounding ambiguous regions in the SA views. %, such as the tricuspid valve regions. We tested our model on a public dataset with 360 multi-center, multi-vendor and multi-disease subjects that consist of both LA and SA MRIs. Our experimental results show that including LA views can be effective to improve the accuracy of the SA segmentation. Our model is publicly available at https://github.com/NanYoMy/MMs-2.