Diffuse-UDA: Addressing Unsupervised Domain Adaptation in Medical Image Segmentation with Appearance and Structure Aligned Diffusion Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909284695015424 |
|---|---|
| author | Gong, Haifan Wang, Yitao Wang, Yihan Xiao, Jiashun Wan, Xiang Li, Haofeng |
| author_facet | Gong, Haifan Wang, Yitao Wang, Yihan Xiao, Jiashun Wan, Xiang Li, Haofeng |
| contents | The scarcity and complexity of voxel-level annotations in 3D medical imaging present significant challenges, particularly due to the domain gap between labeled datasets from well-resourced centers and unlabeled datasets from less-resourced centers. This disparity affects the fairness of artificial intelligence algorithms in healthcare. We introduce Diffuse-UDA, a novel method leveraging diffusion models to tackle Unsupervised Domain Adaptation (UDA) in medical image segmentation. Diffuse-UDA generates high-quality image-mask pairs with target domain characteristics and various structures, thereby enhancing UDA tasks. Initially, pseudo labels for target domain samples are generated. Subsequently, a specially tailored diffusion model, incorporating deformable augmentations, is trained on image-label or image-pseudo-label pairs from both domains. Finally, source domain labels guide the diffusion model to generate image-label pairs for the target domain. Comprehensive evaluations on several benchmarks demonstrate that Diffuse-UDA outperforms leading UDA and semi-supervised strategies, achieving performance close to or even surpassing the theoretical upper bound of models trained directly on target domain data. Diffuse-UDA offers a pathway to advance the development and deployment of AI systems in medical imaging, addressing disparities between healthcare environments. This approach enables the exploration of innovative AI-driven diagnostic tools, improves outcomes, saves time, and reduces human error. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_05985 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diffuse-UDA: Addressing Unsupervised Domain Adaptation in Medical Image Segmentation with Appearance and Structure Aligned Diffusion Models Gong, Haifan Wang, Yitao Wang, Yihan Xiao, Jiashun Wan, Xiang Li, Haofeng Computer Vision and Pattern Recognition The scarcity and complexity of voxel-level annotations in 3D medical imaging present significant challenges, particularly due to the domain gap between labeled datasets from well-resourced centers and unlabeled datasets from less-resourced centers. This disparity affects the fairness of artificial intelligence algorithms in healthcare. We introduce Diffuse-UDA, a novel method leveraging diffusion models to tackle Unsupervised Domain Adaptation (UDA) in medical image segmentation. Diffuse-UDA generates high-quality image-mask pairs with target domain characteristics and various structures, thereby enhancing UDA tasks. Initially, pseudo labels for target domain samples are generated. Subsequently, a specially tailored diffusion model, incorporating deformable augmentations, is trained on image-label or image-pseudo-label pairs from both domains. Finally, source domain labels guide the diffusion model to generate image-label pairs for the target domain. Comprehensive evaluations on several benchmarks demonstrate that Diffuse-UDA outperforms leading UDA and semi-supervised strategies, achieving performance close to or even surpassing the theoretical upper bound of models trained directly on target domain data. Diffuse-UDA offers a pathway to advance the development and deployment of AI systems in medical imaging, addressing disparities between healthcare environments. This approach enables the exploration of innovative AI-driven diagnostic tools, improves outcomes, saves time, and reduces human error. |
| title | Diffuse-UDA: Addressing Unsupervised Domain Adaptation in Medical Image Segmentation with Appearance and Structure Aligned Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.05985 |