CAR: Contrast-Agnostic Deformable Medical Image Registration with Contrast-Invariant Latent Regularization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911983704473600 |
|---|---|
| author | Wang, Yinsong Du, Siyi Zheng, Shaoming Luo, Xinzhe Qin, Chen |
| author_facet | Wang, Yinsong Du, Siyi Zheng, Shaoming Luo, Xinzhe Qin, Chen |
| contents | Multi-contrast image registration is a challenging task due to the complex intensity relationships between different imaging contrasts. Conventional image registration methods are typically based on iterative optimizations for each input image pair, which is time-consuming and sensitive to contrast variations. While learning-based approaches are much faster during the inference stage, due to generalizability issues, they typically can only be applied to the fixed contrasts observed during the training stage. In this work, we propose a novel contrast-agnostic deformable image registration framework that can be generalized to arbitrary contrast images, without observing them during training. Particularly, we propose a random convolution-based contrast augmentation scheme, which simulates arbitrary contrasts of images over a single image contrast while preserving their inherent structural information. To ensure that the network can learn contrast-invariant representations for facilitating contrast-agnostic registration, we further introduce contrast-invariant latent regularization (CLR) that regularizes representation in latent space through a contrast invariance loss. Experiments show that CAR outperforms the baseline approaches regarding registration accuracy and also possesses better generalization ability to unseen imaging contrasts. Code is available at \url{https://github.com/Yinsong0510/CAR}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_05341 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CAR: Contrast-Agnostic Deformable Medical Image Registration with Contrast-Invariant Latent Regularization Wang, Yinsong Du, Siyi Zheng, Shaoming Luo, Xinzhe Qin, Chen Computer Vision and Pattern Recognition Artificial Intelligence Multi-contrast image registration is a challenging task due to the complex intensity relationships between different imaging contrasts. Conventional image registration methods are typically based on iterative optimizations for each input image pair, which is time-consuming and sensitive to contrast variations. While learning-based approaches are much faster during the inference stage, due to generalizability issues, they typically can only be applied to the fixed contrasts observed during the training stage. In this work, we propose a novel contrast-agnostic deformable image registration framework that can be generalized to arbitrary contrast images, without observing them during training. Particularly, we propose a random convolution-based contrast augmentation scheme, which simulates arbitrary contrasts of images over a single image contrast while preserving their inherent structural information. To ensure that the network can learn contrast-invariant representations for facilitating contrast-agnostic registration, we further introduce contrast-invariant latent regularization (CLR) that regularizes representation in latent space through a contrast invariance loss. Experiments show that CAR outperforms the baseline approaches regarding registration accuracy and also possesses better generalization ability to unseen imaging contrasts. Code is available at \url{https://github.com/Yinsong0510/CAR}. |
| title | CAR: Contrast-Agnostic Deformable Medical Image Registration with Contrast-Invariant Latent Regularization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2408.05341 |