Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network

TL;DR

This paper introduces an unsupervised domain adaptation approach for multi-sequence cardiac MRI segmentation, improving accuracy across different MRI modalities by aligning features at multiple levels.

Contribution

It proposes a novel adversarial domain alignment method with multi-level feature and output space adaptation, plus a group-wise feature recalibration module for fine-grained semantic alignment.

Findings

Significant segmentation improvements over baseline models.

Effective domain shift mitigation across MRI modalities.

Validated on multi-sequence cardiac MRI datasets.

Abstract

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, \emph{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.