Studying Robustness of Semantic Segmentation under Domain Shift in cardiac MRI

TL;DR

This paper investigates the robustness of deep learning models for cardiac MRI segmentation across different domains, focusing on domain transfer challenges and proposing strategies to enhance generalizability, validated by winning a multi-center challenge.

Contribution

It systematically studies domain transfer issues in cardiac MRI segmentation and offers practical guidelines to improve model robustness using data augmentation and batch normalization.

Findings

Proposed methods ranked first in a multi-center challenge.

Identified key techniques to enhance domain generalizability.

Provided general guidelines for improving deep learning robustness.

Abstract

Cardiac magnetic resonance imaging (cMRI) is an integral part of diagnosis in many heart related diseases. Recently, deep neural networks have demonstrated successful automatic segmentation, thus alleviating the burden of time-consuming manual contouring of cardiac structures. Moreover, frameworks such as nnU-Net provide entirely automatic model configuration to unseen datasets enabling out-of-the-box application even by non-experts. However, current studies commonly neglect the clinically realistic scenario, in which a trained network is applied to data from a different domain such as deviating scanners or imaging protocols. This potentially leads to unexpected performance drops of deep learning models in real life applications. In this work, we systematically study challenges and opportunities of domain transfer across images from multiple clinical centres and scanner vendors. In order to maintain out-of-the-box usability, we build upon a fixed U-Net architecture configured by the nnU-net framework to investigate various data augmentation techniques and batch normalization layers as an easy-to-customize pipeline component and provide general guidelines on how to improve domain generalizability abilities in existing deep learning methods. Our proposed method ranked first at the Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image Segmentation Challenge (M&Ms).