# Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network

arXiv: https://arxiv.org/abs/1910.12514 · HTML: https://mlsanity.com/paper/1910.12514/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2019.

## Built on by (most cited first, 7 of 7)

- [Multi-Modality Cardiac Image Computing: A Survey](https://mlsanity.com/paper/2208.12881/) (2022)
- [Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimisation for Multi-modal Cardiac Image Segmentation](https://mlsanity.com/paper/2103.08219/) (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)
- [Unsupervised Adaptation of Polyp Segmentation Models via Coarse-to-Fine Self-Supervision](https://mlsanity.com/paper/2308.06665/) (2023)
- [Multi-Modality Cardiac Image Analysis with Deep Learning](https://mlsanity.com/paper/2111.04736/) (2021)
- [Style Transfer and Self-Supervised Learning Powered Myocardium Infarction Super-Resolution Segmentation](https://mlsanity.com/paper/2309.15485/) (2023)
- [Unsupervised Domain Adaptation via Similarity-based Prototypes for Cross-Modality Segmentation](https://mlsanity.com/paper/2510.20596/) (2025)

## Abstract (arXiv)

Automatic and accurate segmentation of the ventricles and myocardium from multi-sequence cardiac MRI (CMR) is crucial for the diagnosis and treatment management for patients suffering from myocardial infarction (MI). However, due to the existence of domain shift among different modalities of datasets, the performance of deep neural networks drops significantly when the training and testing datasets are distinct. In this paper, we propose an unsupervised domain alignment method to explicitly alleviate the domain shifts among different modalities of CMR sequences, e.g., bSSFP, LGE, and T2-weighted. Our segmentation network is attention U-Net with pyramid pooling module, where multi-level feature space and output space adversarial learning are proposed to transfer discriminative domain knowledge across different datasets. Moreover, we further introduce a group-wise feature recalibration module to enforce the fine-grained semantic-level feature alignment that matching features from different networks but with the same class label. We evaluate our method on the multi-sequence cardiac MR Segmentation Challenge 2019 datasets, which contain three different modalities of MRI sequences. Extensive experimental results show that the proposed methods can obtain significant segmentation improvements compared with the baseline models.