Bookmark Saya

arXiv Open Access 2025

Enabling Ultra-Fast Cardiovascular Imaging Across Heterogeneous Clinical Environments with a Generalist Foundation Model and Multimodal Database

Zi Wang Mingkai Huang Zhang Shi Hongjie Hu Lan Lan +59 lainnya
Lihat Sumber

Abstrak

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 and heterogeneity across medical environments. This underscores the urgent need for a generalist reconstruction foundation model for ultra-fast CMR imaging, one 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, 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 in the internal centers and exhibits strong zero-shot generalization to unseen external settings. Even at imaging acceleration up to 24x, CardioMM reliably preserves key cardiac phenotypes, quantitative myocardial biomarkers, and diagnostic image quality, enabling a substantial increase in CMR examination throughput without compromising clinical integrity. Together, our open-access MMCMR-427K database and CardioMM framework establish a scalable pathway toward high-throughput, high-quality, and clinically accessible cardiovascular imaging.

Topik & Kata Kunci

eess.IV cs.AI physics.med-ph

Penulis (64)

Z

Zi Wang

M

Mingkai Huang

Z

Zhang Shi

H

Hongjie Hu

L

Lan Lan

H

Hui Zhang

Y

Yan Li

X

Xi Hu

Q

Qing Lu

Z

Zongming Zhu

Q

Qiong Yao

Y

Yuxiang Dai

F

Fanwen Wang

Y

Yinzhe Wu

J

Jun Lyu

Q

Qianqian Gao

G

Guangming Xu

Z

Zhenxuan Zhang

H

Haosen Zhang

Q

Qing Li

G

Guangming Wang

T

Tianxing He

L

Lizhen Lan

S

Siyue Li

L

Le Xue

M

Mengting Sun

Y

Yuntong Lyu

J

Junpu Hu

J

Jiayu Zhu

R

Rizwan Ahmad

Z

Zhengyu Bu

X

Xianling Qian

G

Guanke Cai

R

Ruiyu Cao

W

Weirui Cai

C

Chang Xu

Y

Yuyang Ren

F

Feidan Yu

S

Siying Ma

Z

Ziqiang Xu

X

Xinran Chen

S

Sha Hua

D

Daniel Kim

Y

Yajing Zhang

C

Chen Ouyang

W

Wenjia Bai

J

Jing Qin

Y

Yucheng Yang

D

Daniel Rueckert

H

He Wang

Q

Qian Tao

C

Claudia Prieto

M

Michael Markl

A

Alistair Young

L

Lianming Wu

S

Shuo Wang

C

Chen Qin

M

Mengsu Zeng

X

Xihong Hu

H

Haibo Xu

X

Xiaobo Qu

H

Hao Li

G

Guang Yang

C

Chengyan Wang

Format Sitasi

APA MLA BibTeX
Wang, Z., Huang, M., Shi, Z., Hu, H., Lan, L., Zhang, H. et al. (2025). Enabling Ultra-Fast Cardiovascular Imaging Across Heterogeneous Clinical Environments with a Generalist Foundation Model and Multimodal Database. https://arxiv.org/abs/2512.21652

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓