Enhancing Cardiac MRI Segmentation via Classifier-Guided Two-Stage Network and All-Slice Information Fusion Transformer

TL;DR

This paper introduces a novel classifier-guided two-stage network with an all-slice fusion transformer to improve cardiac MRI segmentation accuracy, especially in challenging basal and apical slices, demonstrating superior performance and more realistic segmentation shapes.

Contribution

It presents a new two-stage network with an all-slice transformer that enhances segmentation accuracy and shape quality in cardiac MRI analysis, addressing challenges in irregular heart shapes.

Findings

Achieved higher Dice scores than previous models.

Produced more realistic and complete segmentation shapes.

Improved segmentation in difficult basal and apical slices.

Abstract

Cardiac Magnetic Resonance imaging (CMR) is the gold standard for assessing cardiac function. Segmenting the left ventricle (LV), right ventricle (RV), and LV myocardium (MYO) in CMR images is crucial but time-consuming. Deep learning-based segmentation methods have emerged as effective tools for automating this process. However, CMR images present additional challenges due to irregular and varying heart shapes, particularly in basal and apical slices. In this study, we propose a classifier-guided two-stage network with an all-slice fusion transformer to enhance CMR segmentation accuracy, particularly in basal and apical slices. Our method was evaluated on extensive clinical datasets and demonstrated better performance in terms of Dice score compared to previous CNN-based and transformer-based models. Moreover, our method produces visually appealing segmentation shapes resembling human annotations and avoids common issues like holes or fragments in other models' segmentations.