Semi-weakly-supervised neural network training for medical image registration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910334159159296 |
|---|---|
| author | Li, Yiwen Fu, Yunguan Gayo, Iani J. M. B. Yang, Qianye Min, Zhe Saeed, Shaheer U. Yan, Wen Wang, Yipei Noble, J. Alison Emberton, Mark Clarkson, Matthew J. Barratt, Dean C. Prisacariu, Victor A. Hu, Yipeng |
| author_facet | Li, Yiwen Fu, Yunguan Gayo, Iani J. M. B. Yang, Qianye Min, Zhe Saeed, Shaheer U. Yan, Wen Wang, Yipei Noble, J. Alison Emberton, Mark Clarkson, Matthew J. Barratt, Dean C. Prisacariu, Victor A. Hu, Yipeng |
| contents | For training registration networks, weak supervision from segmented corresponding regions-of-interest (ROIs) have been proven effective for (a) supplementing unsupervised methods, and (b) being used independently in registration tasks in which unsupervised losses are unavailable or ineffective. This correspondence-informing supervision entails cost in annotation that requires significant specialised effort. This paper describes a semi-weakly-supervised registration pipeline that improves the model performance, when only a small corresponding-ROI-labelled dataset is available, by exploiting unlabelled image pairs. We examine two types of augmentation methods by perturbation on network weights and image resampling, such that consistency-based unsupervised losses can be applied on unlabelled data. The novel WarpDDF and RegCut approaches are proposed to allow commutative perturbation between an image pair and the predicted spatial transformation (i.e. respective input and output of registration networks), distinct from existing perturbation methods for classification or segmentation. Experiments using 589 male pelvic MR images, labelled with eight anatomical ROIs, show the improvement in registration performance and the ablated contributions from the individual strategies. Furthermore, this study attempts to construct one of the first computational atlases for pelvic structures, enabled by registering inter-subject MRs, and quantifies the significant differences due to the proposed semi-weak supervision with a discussion on the potential clinical use of example atlas-derived statistics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_10728 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Semi-weakly-supervised neural network training for medical image registration Li, Yiwen Fu, Yunguan Gayo, Iani J. M. B. Yang, Qianye Min, Zhe Saeed, Shaheer U. Yan, Wen Wang, Yipei Noble, J. Alison Emberton, Mark Clarkson, Matthew J. Barratt, Dean C. Prisacariu, Victor A. Hu, Yipeng Image and Video Processing Computer Vision and Pattern Recognition For training registration networks, weak supervision from segmented corresponding regions-of-interest (ROIs) have been proven effective for (a) supplementing unsupervised methods, and (b) being used independently in registration tasks in which unsupervised losses are unavailable or ineffective. This correspondence-informing supervision entails cost in annotation that requires significant specialised effort. This paper describes a semi-weakly-supervised registration pipeline that improves the model performance, when only a small corresponding-ROI-labelled dataset is available, by exploiting unlabelled image pairs. We examine two types of augmentation methods by perturbation on network weights and image resampling, such that consistency-based unsupervised losses can be applied on unlabelled data. The novel WarpDDF and RegCut approaches are proposed to allow commutative perturbation between an image pair and the predicted spatial transformation (i.e. respective input and output of registration networks), distinct from existing perturbation methods for classification or segmentation. Experiments using 589 male pelvic MR images, labelled with eight anatomical ROIs, show the improvement in registration performance and the ablated contributions from the individual strategies. Furthermore, this study attempts to construct one of the first computational atlases for pelvic structures, enabled by registering inter-subject MRs, and quantifies the significant differences due to the proposed semi-weak supervision with a discussion on the potential clinical use of example atlas-derived statistics. |
| title | Semi-weakly-supervised neural network training for medical image registration |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.10728 |