DRL-STNet: Unsupervised Domain Adaptation for Cross-modality Medical Image Segmentation via Disentangled Representation Learning
This addresses the problem of reducing manual annotation needs for medical image segmentation across different imaging modalities, though it appears incremental as it builds on existing UDA and GAN methods.
The paper tackled cross-modality medical image segmentation by proposing DRL-STNet, a framework using disentangled representation learning and self-training, which achieved a 11.4% improvement in Dice similarity coefficient and 13.1% in Normalized Surface Dice on the FLARE dataset.
Unsupervised domain adaptation (UDA) is essential for medical image segmentation, especially in cross-modality data scenarios. UDA aims to transfer knowledge from a labeled source domain to an unlabeled target domain, thereby reducing the dependency on extensive manual annotations. This paper presents DRL-STNet, a novel framework for cross-modality medical image segmentation that leverages generative adversarial networks (GANs), disentangled representation learning (DRL), and self-training (ST). Our method leverages DRL within a GAN to translate images from the source to the target modality. Then, the segmentation model is initially trained with these translated images and corresponding source labels and then fine-tuned iteratively using a combination of synthetic and real images with pseudo-labels and real labels. The proposed framework exhibits superior performance in abdominal organ segmentation on the FLARE challenge dataset, surpassing state-of-the-art methods by 11.4% in the Dice similarity coefficient and by 13.1% in the Normalized Surface Dice metric, achieving scores of 74.21% and 80.69%, respectively. The average running time is 41 seconds, and the area under the GPU memory-time curve is 11,292 MB. These results indicate the potential of DRL-STNet for enhancing cross-modality medical image segmentation tasks.