Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss
This addresses the challenge of expensive medical data annotation by enabling cross-modality adaptation without target labels, though it is incremental as it builds on existing adversarial domain adaptation methods.
The paper tackles the problem of domain shift in biomedical image segmentation by proposing an unsupervised domain adaptation framework with adversarial learning, achieving promising results when adapting a ConvNet from MRI to CT images for cardiac structure segmentation.
Convolutional networks (ConvNets) have achieved great successes in various challenging vision tasks. However, the performance of ConvNets would degrade when encountering the domain shift. The domain adaptation is more significant while challenging in the field of biomedical image analysis, where cross-modality data have largely different distributions. Given that annotating the medical data is especially expensive, the supervised transfer learning approaches are not quite optimal. In this paper, we propose an unsupervised domain adaptation framework with adversarial learning for cross-modality biomedical image segmentations. Specifically, our model is based on a dilated fully convolutional network for pixel-wise prediction. Moreover, we build a plug-and-play domain adaptation module (DAM) to map the target input to features which are aligned with source domain feature space. A domain critic module (DCM) is set up for discriminating the feature space of both domains. We optimize the DAM and DCM via an adversarial loss without using any target domain label. Our proposed method is validated by adapting a ConvNet trained with MRI images to unpaired CT data for cardiac structures segmentations, and achieved very promising results.