The Impact of Domain Shift on Left and Right Ventricle Segmentation in Short Axis Cardiac MR Images

TL;DR

This study investigates how differences in MRI scanner types and patient pathologies affect the accuracy of ventricle segmentation in cardiac MRI images, highlighting the importance of multi-scanner training for better generalization.

Contribution

It provides an empirical analysis of domain shift effects on ventricle segmentation and demonstrates that multi-scanner training enhances model robustness across different domains.

Findings

Scanner differences cause greater performance drops than pathology variations.

Right ventricle segmentation is more affected by domain shift than left.

Multi-scanner training improves cross-domain segmentation performance.

Abstract

Domain shift refers to the difference in the data distribution of two datasets, normally between the training set and the test set for machine learning algorithms. Domain shift is a serious problem for generalization of machine learning models and it is well-established that a domain shift between the training and test sets may cause a drastic drop in the model's performance. In medical imaging, there can be many sources of domain shift such as different scanners or scan protocols, different pathologies in the patient population, anatomical differences in the patient population (e.g. men vs women) etc. Therefore, in order to train models that have good generalization performance, it is important to be aware of the domain shift problem, its potential causes and to devise ways to address it. In this paper, we study the effect of domain shift on left and right ventricle blood pool segmentation in short axis cardiac MR images. Our dataset contains short axis images from 4 different MR scanners and 3 different pathology groups. The training is performed with nnUNet. The results show that scanner differences cause a greater drop in performance compared to changing the pathology group, and that the impact of domain shift is greater on right ventricle segmentation compared to left ventricle segmentation. Increasing the number of training subjects increased cross-scanner performance more than in-scanner performance at small training set sizes, but this difference in improvement decreased with larger training set sizes. Training models using data from multiple scanners improved cross-domain performance.