Cross-Domain Distribution Alignment for Segmentation of Private Unannotated 3D Medical Images
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929538494103552 |
|---|---|
| author | Sun, Ruitong Rostami, Mohammad |
| author_facet | Sun, Ruitong Rostami, Mohammad |
| contents | Manual annotation of 3D medical images for segmentation tasks is tedious and time-consuming. Moreover, data privacy limits the applicability of crowd sourcing to perform data annotation in medical domains. As a result, training deep neural networks for medical image segmentation can be challenging. We introduce a new source-free Unsupervised Domain Adaptation (UDA) method to address this problem. Our idea is based on estimating the internally learned distribution of a relevant source domain by a base model and then generating pseudo-labels that are used for enhancing the model refinement through self-training. We demonstrate that our approach leads to SOTA performance on a real-world 3D medical dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_09210 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cross-Domain Distribution Alignment for Segmentation of Private Unannotated 3D Medical Images Sun, Ruitong Rostami, Mohammad Computer Vision and Pattern Recognition Manual annotation of 3D medical images for segmentation tasks is tedious and time-consuming. Moreover, data privacy limits the applicability of crowd sourcing to perform data annotation in medical domains. As a result, training deep neural networks for medical image segmentation can be challenging. We introduce a new source-free Unsupervised Domain Adaptation (UDA) method to address this problem. Our idea is based on estimating the internally learned distribution of a relevant source domain by a base model and then generating pseudo-labels that are used for enhancing the model refinement through self-training. We demonstrate that our approach leads to SOTA performance on a real-world 3D medical dataset. |
| title | Cross-Domain Distribution Alignment for Segmentation of Private Unannotated 3D Medical Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.09210 |