Generalisable Cardiac Structure Segmentation via Attentional and Stacked Image Adaptation

TL;DR

This paper introduces a novel cardiac image segmentation framework that uses adversarial training and image augmentation to improve generalization across diverse multi-centre, multi-vendor datasets, achieving high accuracy.

Contribution

The study presents a new segmentation approach combining GAN-based image translation with stacked data augmentation to address domain shifts in cardiac imaging.

Findings

Achieved average Dice scores of 90.3% for LV, 85.9% for myocardium, 86.5% for RV.

Significantly reduced domain shift effects in multi-vendor datasets.

Demonstrated robustness across unseen domains with high segmentation accuracy.

Abstract

Tackling domain shifts in multi-centre and multi-vendor data sets remains challenging for cardiac image segmentation. In this paper, we propose a generalisable segmentation framework for cardiac image segmentation in which multi-centre, multi-vendor, multi-disease datasets are involved. A generative adversarial networks with an attention loss was proposed to translate the images from existing source domains to a target domain, thus to generate good-quality synthetic cardiac structure and enlarge the training set. A stack of data augmentation techniques was further used to simulate real-world transformation to boost the segmentation performance for unseen domains.We achieved an average Dice score of 90.3% for the left ventricle, 85.9% for the myocardium, and 86.5% for the right ventricle on the hidden validation set across four vendors. We show that the domain shifts in heterogeneous cardiac imaging datasets can be drastically reduced by two aspects: 1) good-quality synthetic data by learning the underlying target domain distribution, and 2) stacked classical image processing techniques for data augmentation.