CDDSA: Contrastive Domain Disentanglement and Style Augmentation for
Generalizable Medical Image Segmentation
- URL: http://arxiv.org/abs/2211.12081v1
- Date: Tue, 22 Nov 2022 08:25:35 GMT
- Title: CDDSA: Contrastive Domain Disentanglement and Style Augmentation for
Generalizable Medical Image Segmentation
- Authors: Ran Gu, Guotai Wang, Jiangshan Lu, Jingyang Zhang, Wenhui Lei, Yinan
Chen, Wenjun Liao, Shichuan Zhang, Kang Li, Dimitris N. Metaxas, Shaoting
Zhang
- Abstract summary: We propose an efficient Contrastive Domain Disentanglement and Style Augmentation (CDDSA) framework for generalizable medical image segmentation.
First, a disentangle network is proposed to decompose an image into a domain-invariant anatomical representation and a domain-specific style code.
Second, to achieve better disentanglement, a contrastive loss is proposed to encourage the style codes from the same domain and different domains to be compact and divergent.
- Score: 38.44458104455557
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Generalization to previously unseen images with potential domain shifts and
different styles is essential for clinically applicable medical image
segmentation, and the ability to disentangle domain-specific and
domain-invariant features is key for achieving Domain Generalization (DG).
However, existing DG methods can hardly achieve effective disentanglement to
get high generalizability. To deal with this problem, we propose an efficient
Contrastive Domain Disentanglement and Style Augmentation (CDDSA) framework for
generalizable medical image segmentation. First, a disentangle network is
proposed to decompose an image into a domain-invariant anatomical
representation and a domain-specific style code, where the former is sent to a
segmentation model that is not affected by the domain shift, and the
disentangle network is regularized by a decoder that combines the anatomical
and style codes to reconstruct the input image. Second, to achieve better
disentanglement, a contrastive loss is proposed to encourage the style codes
from the same domain and different domains to be compact and divergent,
respectively. Thirdly, to further improve generalizability, we propose a style
augmentation method based on the disentanglement representation to synthesize
images in various unseen styles with shared anatomical structures. Our method
was validated on a public multi-site fundus image dataset for optic cup and
disc segmentation and an in-house multi-site Nasopharyngeal Carcinoma Magnetic
Resonance Image (NPC-MRI) dataset for nasopharynx Gross Tumor Volume (GTVnx)
segmentation. Experimental results showed that the proposed CDDSA achieved
remarkable generalizability across different domains, and it outperformed
several state-of-the-art methods in domain-generalizable segmentation.
Related papers
- Medical Image Segmentation via Single-Source Domain Generalization with Random Amplitude Spectrum Synthesis [13.794335166617063]
The field of medical image segmentation is challenged by domain generalization (DG) due to domain shifts in clinical datasets.
Traditional single-source domain generalization methods rely on stacking data augmentation techniques to minimize domain discrepancies.
We propose Random Amplitude Spectrum Synthesis (RASS) as a training augmentation for medical images.
arXiv Detail & Related papers (2024-09-07T08:58:04Z) - SMC-UDA: Structure-Modal Constraint for Unsupervised Cross-Domain Renal
Segmentation [100.86339246424541]
We propose a novel Structure-Modal Constrained (SMC) UDA framework based on a discriminative paradigm and introduce edge structure as a bridge between domains.
With the structure-constrained self-learning and progressive ROI, our methods segment the kidney by locating the 3D spatial structure of the edge.
experiments show that our proposed SMC-UDA has a strong generalization and outperforms generative UDA methods.
arXiv Detail & Related papers (2023-06-14T02:57:23Z) - Multi-Scale Multi-Target Domain Adaptation for Angle Closure
Classification [50.658613573816254]
We propose a novel Multi-scale Multi-target Domain Adversarial Network (M2DAN) for angle closure classification.
Based on these domain-invariant features at different scales, the deep model trained on the source domain is able to classify angle closure on multiple target domains.
arXiv Detail & Related papers (2022-08-25T15:27:55Z) - Generalizable Medical Image Segmentation via Random Amplitude Mixup and
Domain-Specific Image Restoration [17.507951655445652]
We present a novel generalizable medical image segmentation method.
To be specific, we design our approach as a multi-task paradigm by combining the segmentation model with a self-supervision domain-specific image restoration module.
We demonstrate the performance of our method on two public generalizable segmentation benchmarks in medical images.
arXiv Detail & Related papers (2022-08-08T03:56:20Z) - Contrastive Domain Disentanglement for Generalizable Medical Image
Segmentation [12.863227646939563]
We propose Contrastive Disentangle Domain (CDD) network for generalizable medical image segmentation.
We first introduce a disentangle network to decompose medical images into an anatomical representation factor and a modality representation factor.
We then propose a domain augmentation strategy that can randomly generate new domains for model generalization training.
arXiv Detail & Related papers (2022-05-13T10:32:41Z) - Domain Composition and Attention for Unseen-Domain Generalizable Medical
Image Segmentation [12.412110592754729]
We propose a Domain Composition and Attention-based network (DCA-Net) to improve the ability of domain representation and generalization.
First, we present a domain composition method that represents one certain domain by a linear combination of a set of basis representations.
Second, a novel plug-and-play parallel domain is proposed to learn these basis representations.
Third, a domain attention module is proposed to learn the linear combination coefficients of the basis representations.
arXiv Detail & Related papers (2021-09-18T06:42:47Z) - Cross-Modality Brain Tumor Segmentation via Bidirectional
Global-to-Local Unsupervised Domain Adaptation [61.01704175938995]
In this paper, we propose a novel Bidirectional Global-to-Local (BiGL) adaptation framework under a UDA scheme.
Specifically, a bidirectional image synthesis and segmentation module is proposed to segment the brain tumor.
The proposed method outperforms several state-of-the-art unsupervised domain adaptation methods by a large margin.
arXiv Detail & Related papers (2021-05-17T10:11:45Z) - Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to
Unseen Domains [68.73614619875814]
We present a novel shape-aware meta-learning scheme to improve the model generalization in prostate MRI segmentation.
Experimental results show that our approach outperforms many state-of-the-art generalization methods consistently across all six settings of unseen domains.
arXiv Detail & Related papers (2020-07-04T07:56:02Z) - Unsupervised Bidirectional Cross-Modality Adaptation via Deeply
Synergistic Image and Feature Alignment for Medical Image Segmentation [73.84166499988443]
We present a novel unsupervised domain adaptation framework, named as Synergistic Image and Feature Alignment (SIFA)
Our proposed SIFA conducts synergistic alignment of domains from both image and feature perspectives.
Experimental results on two different tasks demonstrate that our SIFA method is effective in improving segmentation performance on unlabeled target images.
arXiv Detail & Related papers (2020-02-06T13:49:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.