Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.00947 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909242229784576 |
|---|---|
| author | Gao, Fei Wang, Siwen Zhang, Fandong Zhou, Hong-Yu Wang, Yizhou Wang, Churan Yu, Gang Yu, Yizhou |
| author_facet | Gao, Fei Wang, Siwen Zhang, Fandong Zhou, Hong-Yu Wang, Yizhou Wang, Churan Yu, Gang Yu, Yizhou |
| contents | Medical image analysis suffers from a shortage of data, whether annotated or not. This becomes even more pronounced when it comes to 3D medical images. Self-Supervised Learning (SSL) can partially ease this situation by using unlabeled data. However, most existing SSL methods can only make use of data in a single dimensionality (e.g. 2D or 3D), and are incapable of enlarging the training dataset by using data with differing dimensionalities jointly. In this paper, we propose a new cross-dimensional SSL framework based on a pseudo-3D transformation (CDSSL-P3D), that can leverage both 2D and 3D data for joint pre-training. Specifically, we introduce an image transformation based on the im2col algorithm, which converts 2D images into a format consistent with 3D data. This transformation enables seamless integration of 2D and 3D data, and facilitates cross-dimensional self-supervised learning for 3D medical image analysis. We run extensive experiments on 13 downstream tasks, including 2D and 3D classification and segmentation. The results indicate that our CDSSL-P3D achieves superior performance, outperforming other advanced SSL methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00947 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cross-Dimensional Medical Self-Supervised Representation Learning Based on a Pseudo-3D Transformation Gao, Fei Wang, Siwen Zhang, Fandong Zhou, Hong-Yu Wang, Yizhou Wang, Churan Yu, Gang Yu, Yizhou Computer Vision and Pattern Recognition Medical image analysis suffers from a shortage of data, whether annotated or not. This becomes even more pronounced when it comes to 3D medical images. Self-Supervised Learning (SSL) can partially ease this situation by using unlabeled data. However, most existing SSL methods can only make use of data in a single dimensionality (e.g. 2D or 3D), and are incapable of enlarging the training dataset by using data with differing dimensionalities jointly. In this paper, we propose a new cross-dimensional SSL framework based on a pseudo-3D transformation (CDSSL-P3D), that can leverage both 2D and 3D data for joint pre-training. Specifically, we introduce an image transformation based on the im2col algorithm, which converts 2D images into a format consistent with 3D data. This transformation enables seamless integration of 2D and 3D data, and facilitates cross-dimensional self-supervised learning for 3D medical image analysis. We run extensive experiments on 13 downstream tasks, including 2D and 3D classification and segmentation. The results indicate that our CDSSL-P3D achieves superior performance, outperforming other advanced SSL methods. |
| title | Cross-Dimensional Medical Self-Supervised Representation Learning Based on a Pseudo-3D Transformation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.00947 |