Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.18593 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915508414054400 |
|---|---|
| author | Wu, Xiaoman Gan, Lubin Wu, Siying Zhang, Jing Ou, Yunwei Sun, Xiaoyan |
| author_facet | Wu, Xiaoman Gan, Lubin Wu, Siying Zhang, Jing Ou, Yunwei Sun, Xiaoyan |
| contents | Multi-contrast Magnetic Resonance Imaging super-resolution (MC-MRI SR) aims to enhance low-resolution (LR) contrasts leveraging high-resolution (HR) references, shortening acquisition time and improving imaging efficiency while preserving anatomical details. The main challenge lies in maintaining spatial-semantic consistency, ensuring anatomical structures remain well-aligned and coherent despite structural discrepancies and motion between the target and reference images. Conventional methods insufficiently model spatial-semantic consistency and underuse frequency-domain information, which leads to poor fine-grained alignment and inadequate recovery of high-frequency details. In this paper, we propose the Spatial-Semantic Consistent Model (SSCM), which integrates a Dynamic Spatial Warping Module for inter-contrast spatial alignment, a Semantic-Aware Token Aggregation Block for long-range semantic consistency, and a Spatial-Frequency Fusion Block for fine structure restoration. Experiments on public and private datasets show that SSCM achieves state-of-the-art performance with fewer parameters while ensuring spatially and semantically consistent reconstructions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18593 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution Wu, Xiaoman Gan, Lubin Wu, Siying Zhang, Jing Ou, Yunwei Sun, Xiaoyan Computer Vision and Pattern Recognition Multi-contrast Magnetic Resonance Imaging super-resolution (MC-MRI SR) aims to enhance low-resolution (LR) contrasts leveraging high-resolution (HR) references, shortening acquisition time and improving imaging efficiency while preserving anatomical details. The main challenge lies in maintaining spatial-semantic consistency, ensuring anatomical structures remain well-aligned and coherent despite structural discrepancies and motion between the target and reference images. Conventional methods insufficiently model spatial-semantic consistency and underuse frequency-domain information, which leads to poor fine-grained alignment and inadequate recovery of high-frequency details. In this paper, we propose the Spatial-Semantic Consistent Model (SSCM), which integrates a Dynamic Spatial Warping Module for inter-contrast spatial alignment, a Semantic-Aware Token Aggregation Block for long-range semantic consistency, and a Spatial-Frequency Fusion Block for fine structure restoration. Experiments on public and private datasets show that SSCM achieves state-of-the-art performance with fewer parameters while ensuring spatially and semantically consistent reconstructions. |
| title | SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.18593 |