Compositional Segmentation of Cardiac Images Leveraging Metadata

TL;DR

This paper introduces a novel multitask compositional segmentation method for cardiac images that improves accuracy by localizing the heart and segmenting its parts, enhanced with a cross-modal feature integration module that leverages metadata.

Contribution

The paper presents a new compositional segmentation approach combined with a cross-modal feature integration module that utilizes metadata, demonstrating improved results on MRI and ultrasound datasets.

Findings

Better segmentation accuracy than direct methods

Effective use of metadata through CMFI module

Validated on multiple public datasets

Abstract

Cardiac image segmentation is essential for automated cardiac function assessment and monitoring of changes in cardiac structures over time. Inspired by coarse-to-fine approaches in image analysis, we propose a novel multitask compositional segmentation approach that can simultaneously localize the heart in a cardiac image and perform part-based segmentation of different regions of interest. We demonstrate that this compositional approach achieves better results than direct segmentation of the anatomies. Further, we propose a novel Cross-Modal Feature Integration (CMFI) module to leverage the metadata related to cardiac imaging collected during image acquisition. We perform experiments on two different modalities, MRI and ultrasound, using public datasets, Multi-disease, Multi-View, and Multi-Centre (M&Ms-2) and Multi-structure Ultrasound Segmentation (CAMUS) data, to showcase the efficiency of the proposed compositional segmentation method and Cross-Modal Feature Integration module incorporating metadata within the proposed compositional segmentation network. The source code is available: https://github.com/kabbas570/CompSeg-MetaData.