Loading [a11y]/accessibility-menu.js
Rethinking Disentanglement in Unsupervised Domain Adaptation for Medical Image Segmentation | IEEE Conference Publication | IEEE Xplore

Rethinking Disentanglement in Unsupervised Domain Adaptation for Medical Image Segmentation


Abstract:

Domain adaptation has become an important topic because the trained neural networks from the source domain generally perform poorly in the target domain due to domain shi...Show More

Abstract:

Domain adaptation has become an important topic because the trained neural networks from the source domain generally perform poorly in the target domain due to domain shifts, especially for medical image analysis. Previous DA methods mainly focus on disentangling domain features. However, it is based on feature independence, which often can not be guaranteed in reality. In this work, we present a new DA approach called Dimension-based Disentangled Dilated Domain Adaptation (D4A) to disentangle the storage locations between the features to tackle the problem of domain shift for medical image segmentation tasks without the annotations of the target domain. We use Adaptive Instance Normalization (AdaIN) to encourage the content information to be stored in the spatial dimension, and the style information to be stored in the channel dimension. In addition, we apply dilated convolution to preserve anatomical information avoiding the loss of information due to downsampling. We validate the proposed method for cross-modality medical image segmentation tasks on two public datasets, and the comparison experiments and ablation studies demonstrate the effectiveness of our method, which outperforms the state-of-the-art methods.
Date of Conference: 24-27 July 2023
Date Added to IEEE Xplore: 11 December 2023
ISBN Information:

ISSN Information:

PubMed ID: 38082792
Conference Location: Sydney, Australia

Funding Agency:


References

References is not available for this document.