# Domain-Adversarial Learning for Multi-Centre, Multi-Vendor, and Multi-Disease Cardiac MR Image Segmentation

arXiv: https://arxiv.org/abs/2008.11776 · HTML: https://mlsanity.com/paper/2008.11776/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2020.

## Built on by (most cited first, 6 of 6)

- [Robust White Matter Hyperintensity Segmentation on Unseen Domain](https://mlsanity.com/paper/2102.06650/) (2021)
- [Domain generalization in deep learning for contrast-enhanced imaging](https://mlsanity.com/paper/2110.07360/) (2021)
- [The Impact of Domain Shift on Left and Right Ventricle Segmentation in Short Axis Cardiac MR Images](https://mlsanity.com/paper/2109.13230/) (2021)
- [How good nnU-Net for Segmenting Cardiac MRI: A Comprehensive Evaluation](https://mlsanity.com/paper/2408.06358/) (2024)
- [CardiSort: a convolutional neural network for cross vendor automated sorting of cardiac MR images](https://mlsanity.com/paper/2109.08479/) (2021)
- [Automatic Segmentation of Left Ventricle in Cardiac Magnetic Resonance Images](https://mlsanity.com/paper/2201.12805/) (2022)

## Abstract (arXiv)

Cine cardiac magnetic resonance (CMR) has become the gold standard for the non-invasive evaluation of cardiac function. In particular, it allows the accurate quantification of functional parameters including the chamber volumes and ejection fraction. Deep learning has shown the potential to automate the requisite cardiac structure segmentation. However, the lack of robustness of deep learning models has hindered their widespread clinical adoption. Due to differences in the data characteristics, neural networks trained on data from a specific scanner are not guaranteed to generalise well to data acquired at a different centre or with a different scanner. In this work, we propose a principled solution to the problem of this domain shift. Domain-adversarial learning is used to train a domain-invariant 2D U-Net using labelled and unlabelled data. This approach is evaluated on both seen and unseen domains from the M&Ms challenge dataset and the domain-adversarial approach shows improved performance as compared to standard training. Additionally, we show that the domain information cannot be recovered from the learned features.