Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning
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_ | 1866913383733788672 |
|---|---|
| author | Wang, Xin Song, Zhiyun Zhu, Yitao Wang, Sheng Zhang, Lichi Shen, Dinggang Wang, Qian |
| author_facet | Wang, Xin Song, Zhiyun Zhu, Yitao Wang, Sheng Zhang, Lichi Shen, Dinggang Wang, Qian |
| contents | In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for both image visualization and subsequent analysis tasks, which often require isotropic voxel spacing. To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated. However, most current solutions require a substantial number of paired high-resolution and low-resolution images for supervised training, which are typically unavailable in real-world scenarios. In this work, we propose a self-supervised super-resolution framework for inter-slice super-resolution of MR images. Our framework is first featured by pre-training on video dataset, as temporal correlation of videos is found beneficial for modeling the spatial relation among MR slices. Then, we use public high-quality MR dataset to fine-tune our pre-trained model, for enhancing awareness of our model to medical data. Finally, given a target dataset at hand, we utilize self-supervised fine-tuning to further ensure our model works well with user-specific super-resolution tasks. The proposed method demonstrates superior performance compared to other self-supervised methods and also holds the potential to benefit various downstream applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_05974 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning Wang, Xin Song, Zhiyun Zhu, Yitao Wang, Sheng Zhang, Lichi Shen, Dinggang Wang, Qian Image and Video Processing Computer Vision and Pattern Recognition In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for both image visualization and subsequent analysis tasks, which often require isotropic voxel spacing. To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated. However, most current solutions require a substantial number of paired high-resolution and low-resolution images for supervised training, which are typically unavailable in real-world scenarios. In this work, we propose a self-supervised super-resolution framework for inter-slice super-resolution of MR images. Our framework is first featured by pre-training on video dataset, as temporal correlation of videos is found beneficial for modeling the spatial relation among MR slices. Then, we use public high-quality MR dataset to fine-tune our pre-trained model, for enhancing awareness of our model to medical data. Finally, given a target dataset at hand, we utilize self-supervised fine-tuning to further ensure our model works well with user-specific super-resolution tasks. The proposed method demonstrates superior performance compared to other self-supervised methods and also holds the potential to benefit various downstream applications. |
| title | Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.05974 |