Multi-Modality Pathology Segmentation Framework: Application to Cardiac Magnetic Resonance Images

TL;DR

This paper introduces an automatic multi-modality CMR image segmentation framework that combines anatomical and pathological region segmentation with neural networks, improving myocardial pathology detection accuracy.

Contribution

It proposes a novel cascade framework with a structure segmentation network and a pathology segmentation network, incorporating a denoising auto-encoder and channel attention for better multi-modality fusion.

Findings

Achieved promising results on MyoPS2020 dataset

Effective fusion of multi-modality CMR images for pathology segmentation

Improved shape plausibility in segmentation results

Abstract

Multi-sequence of cardiac magnetic resonance (CMR) images can provide complementary information for myocardial pathology (scar and edema). However, it is still challenging to fuse these underlying information for pathology segmentation effectively. This work presents an automatic cascade pathology segmentation framework based on multi-modality CMR images. It mainly consists of two neural networks: an anatomical structure segmentation network (ASSN) and a pathological region segmentation network (PRSN). Specifically, the ASSN aims to segment the anatomical structure where the pathology may exist, and it can provide a spatial prior for the pathological region segmentation. In addition, we integrate a denoising auto-encoder (DAE) into the ASSN to generate segmentation results with plausible shapes. The PRSN is designed to segment pathological region based on the result of ASSN, in which a fusion block based on channel attention is proposed to better aggregate multi-modality information from multi-modality CMR images. Experiments from the MyoPS2020 challenge dataset show that our framework can achieve promising performance for myocardial scar and edema segmentation.