Reconstruction-free segmentation from undersampled k-space using transformers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914140106260480 |
|---|---|
| author | Zhang, Yundi Stolt-Ansó, Nil Pan, Jiazhen Huang, Wenqi Hammernik, Kerstin Rueckert, Daniel |
| author_facet | Zhang, Yundi Stolt-Ansó, Nil Pan, Jiazhen Huang, Wenqi Hammernik, Kerstin Rueckert, Daniel |
| contents | Motivation: High acceleration factors place a limit on MRI image reconstruction. This limit is extended to segmentation models when treating these as subsequent independent processes.
Goal: Our goal is to produce segmentations directly from sparse k-space measurements without the need for intermediate image reconstruction.
Approach: We employ a transformer architecture to encode global k-space information into latent features. The produced latent vectors condition queried coordinates during decoding to generate segmentation class probabilities.
Results: The model is able to produce better segmentations across high acceleration factors than image-based segmentation baselines.
Impact: Cardiac segmentation directly from undersampled k-space samples circumvents the need for an intermediate image reconstruction step. This allows the potential to assess myocardial structure and function on higher acceleration factors than methods that rely on images as input. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_03762 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reconstruction-free segmentation from undersampled k-space using transformers Zhang, Yundi Stolt-Ansó, Nil Pan, Jiazhen Huang, Wenqi Hammernik, Kerstin Rueckert, Daniel Image and Video Processing Motivation: High acceleration factors place a limit on MRI image reconstruction. This limit is extended to segmentation models when treating these as subsequent independent processes. Goal: Our goal is to produce segmentations directly from sparse k-space measurements without the need for intermediate image reconstruction. Approach: We employ a transformer architecture to encode global k-space information into latent features. The produced latent vectors condition queried coordinates during decoding to generate segmentation class probabilities. Results: The model is able to produce better segmentations across high acceleration factors than image-based segmentation baselines. Impact: Cardiac segmentation directly from undersampled k-space samples circumvents the need for an intermediate image reconstruction step. This allows the potential to assess myocardial structure and function on higher acceleration factors than methods that rely on images as input. |
| title | Reconstruction-free segmentation from undersampled k-space using transformers |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2511.03762 |