Enabling Ultra-Fast Cardiovascular Imaging Across Heterogeneous Clinical Environments with A Generalist Foundation Model and Multimodal Database
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908963778330624 |
|---|---|
| author | Wang, Zi Huang, Mingkai Shi, Zhang Hu, Hongjie Lan, Lan Zhang, Hui Li, Yan Hu, Xi Lu, Qing Zhu, Zongming Yao, Qiong Dai, Yuxiang Wang, Fanwen Wu, Yinzhe Lyu, Jun Gao, Qianqian Xu, Guangming Zhang, Zhenxuan Zhang, Haosen Li, Qing Wang, Guangming He, Tianxing Lan, Lizhen Li, Siyue Xue, Le Sun, Mengting Lyu, Yuntong Hu, Junpu Zhu, Jiayu Ahmad, Rizwan Bu, Zhengyu Qian, Xianling Cai, Guanke Cao, Ruiyu Cai, Weirui Xu, Chang Ren, Yuyang Yu, Feidan Ma, Siying Xu, Ziqiang Chen, Xinran Hua, Sha Kim, Daniel Zhang, Yajing Ouyang, Chen Bai, Wenjia Qin, Jing Yang, Yucheng Rueckert, Daniel Wang, He Tao, Qian Prieto, Claudia Markl, Michael Young, Alistair Wu, Lianming Wang, Shuo Qin, Chen Zeng, Mengsu Hu, Xihong Xu, Haibo Qu, Xiaobo Li, Hao Yang, Guang Wang, Chengyan |
| author_facet | Wang, Zi Huang, Mingkai Shi, Zhang Hu, Hongjie Lan, Lan Zhang, Hui Li, Yan Hu, Xi Lu, Qing Zhu, Zongming Yao, Qiong Dai, Yuxiang Wang, Fanwen Wu, Yinzhe Lyu, Jun Gao, Qianqian Xu, Guangming Zhang, Zhenxuan Zhang, Haosen Li, Qing Wang, Guangming He, Tianxing Lan, Lizhen Li, Siyue Xue, Le Sun, Mengting Lyu, Yuntong Hu, Junpu Zhu, Jiayu Ahmad, Rizwan Bu, Zhengyu Qian, Xianling Cai, Guanke Cao, Ruiyu Cai, Weirui Xu, Chang Ren, Yuyang Yu, Feidan Ma, Siying Xu, Ziqiang Chen, Xinran Hua, Sha Kim, Daniel Zhang, Yajing Ouyang, Chen Bai, Wenjia Qin, Jing Yang, Yucheng Rueckert, Daniel Wang, He Tao, Qian Prieto, Claudia Markl, Michael Young, Alistair Wu, Lianming Wang, Shuo Qin, Chen Zeng, Mengsu Hu, Xihong Xu, Haibo Qu, Xiaobo Li, Hao Yang, Guang Wang, Chengyan |
| contents | Multimodal cardiovascular magnetic resonance (CMR) imaging provides comprehensive and non-invasive insights into cardiovascular disease (CVD) diagnosis and underlying mechanisms. Despite decades of advancements, its widespread clinical adoption remains constrained by prolonged scan times, inconsistent image quality, and heterogeneity across medical environments. This underscores the urgent need for a generalist reconstruction foundation model for ultra-fast CMR imaging, one formulated for physics-constrained inverse problems in the sensor (k-space) domain, capable of adapting across diverse imaging scenarios and serving as the essential substrate for all downstream analyses. To enable this goal, we curate MMCMR-427K, the largest and most comprehensive multimodal CMR k-space database to date, comprising 427,465 multi-coil k-space data paired with structured metadata across 13 international centers, 12 CMR modalities, 15 scanners spanning four field strengths, and 17 CVD categories in populations across three continents. Building on this unprecedented resource, we introduce CardioMM, a generalist reconstruction foundation model capable of dynamically adapting to heterogeneous fast CMR imaging scenarios. CardioMM unifies semantic contextual understanding with physics-informed data consistency to deliver robust reconstructions across varied scanners, protocols, and patient presentations. Comprehensive evaluations demonstrate that CardioMM achieves state-of-the-art performance across internal centers and exhibits strong zero-shot generalization to unseen external settings. Importantly, CardioMM supports acceleration up to 24x, providing the first evidence that such extreme acquisition speed can preserve key cardiac phenotypes, quantitative myocardial biomarkers, and diagnostic image quality without compromising clinical integrity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_21652 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enabling Ultra-Fast Cardiovascular Imaging Across Heterogeneous Clinical Environments with A Generalist Foundation Model and Multimodal Database Wang, Zi Huang, Mingkai Shi, Zhang Hu, Hongjie Lan, Lan Zhang, Hui Li, Yan Hu, Xi Lu, Qing Zhu, Zongming Yao, Qiong Dai, Yuxiang Wang, Fanwen Wu, Yinzhe Lyu, Jun Gao, Qianqian Xu, Guangming Zhang, Zhenxuan Zhang, Haosen Li, Qing Wang, Guangming He, Tianxing Lan, Lizhen Li, Siyue Xue, Le Sun, Mengting Lyu, Yuntong Hu, Junpu Zhu, Jiayu Ahmad, Rizwan Bu, Zhengyu Qian, Xianling Cai, Guanke Cao, Ruiyu Cai, Weirui Xu, Chang Ren, Yuyang Yu, Feidan Ma, Siying Xu, Ziqiang Chen, Xinran Hua, Sha Kim, Daniel Zhang, Yajing Ouyang, Chen Bai, Wenjia Qin, Jing Yang, Yucheng Rueckert, Daniel Wang, He Tao, Qian Prieto, Claudia Markl, Michael Young, Alistair Wu, Lianming Wang, Shuo Qin, Chen Zeng, Mengsu Hu, Xihong Xu, Haibo Qu, Xiaobo Li, Hao Yang, Guang Wang, Chengyan Image and Video Processing Artificial Intelligence Medical Physics Multimodal cardiovascular magnetic resonance (CMR) imaging provides comprehensive and non-invasive insights into cardiovascular disease (CVD) diagnosis and underlying mechanisms. Despite decades of advancements, its widespread clinical adoption remains constrained by prolonged scan times, inconsistent image quality, and heterogeneity across medical environments. This underscores the urgent need for a generalist reconstruction foundation model for ultra-fast CMR imaging, one formulated for physics-constrained inverse problems in the sensor (k-space) domain, capable of adapting across diverse imaging scenarios and serving as the essential substrate for all downstream analyses. To enable this goal, we curate MMCMR-427K, the largest and most comprehensive multimodal CMR k-space database to date, comprising 427,465 multi-coil k-space data paired with structured metadata across 13 international centers, 12 CMR modalities, 15 scanners spanning four field strengths, and 17 CVD categories in populations across three continents. Building on this unprecedented resource, we introduce CardioMM, a generalist reconstruction foundation model capable of dynamically adapting to heterogeneous fast CMR imaging scenarios. CardioMM unifies semantic contextual understanding with physics-informed data consistency to deliver robust reconstructions across varied scanners, protocols, and patient presentations. Comprehensive evaluations demonstrate that CardioMM achieves state-of-the-art performance across internal centers and exhibits strong zero-shot generalization to unseen external settings. Importantly, CardioMM supports acceleration up to 24x, providing the first evidence that such extreme acquisition speed can preserve key cardiac phenotypes, quantitative myocardial biomarkers, and diagnostic image quality without compromising clinical integrity. |
| title | Enabling Ultra-Fast Cardiovascular Imaging Across Heterogeneous Clinical Environments with A Generalist Foundation Model and Multimodal Database |
| topic | Image and Video Processing Artificial Intelligence Medical Physics |
| url | https://arxiv.org/abs/2512.21652 |