Screening and diagnosis of cardiovascular disease using artificial intelligence-enabled cardiac magnetic resonance imaging

被引：54

作者：

Wang, Yan-Ran ^{[1
]}

Yang, Kai ^{[2
,3
]}

Wen, Yi ^{[4
]}

Wang, Pengcheng ^{[5
]}

Hu, Yuepeng ^{[6
]}

Lai, Yongfan ^{[7
]}

Wang, Yufeng ^{[8
]}

Zhao, Kankan ^{[9
]}

Tang, Siyi ^{[1
,10
]}

Zhang, Angela ^{[1
,11
]}

Zhan, Huayi ^{[4
]}

Lu, Minjie ^{[2
,3
]}

Chen, Xiuyu ^{[2
,3
]}

Yang, Shujuan ^{[2
,3
]}

Dong, Zhixiang ^{[2
,3
]}

Wang, Yining ^{[12
]}

Liu, Hui ^{[13
]}

Zhao, Lei ^{[14
]}

Huang, Lu ^{[15
]}

Li, Yunling ^{[16
]}

Wu, Lianming ^{[17
]}

Chen, Zixian ^{[18
]}

Luo, Yi ^{[19
]}

Liu, Dongbo ^{[4
]}

Zhao, Pengbo ^{[20
]}

Lin, Keldon ^{[21
]}

Wu, Joseph C. ^{[1
,11
]}

Zhao, Shihua ^{[2
,3
]}

机构：

[1] Stanford Univ, Sch Med, Stanford, CA 94305 USA

[2] Chinese Acad Med Sci & Peking Union Med Coll, Fuwai Hosp, Dept Magnet Resonance Imaging, Beijing, Peoples R China

[3] Chinese Acad Med Sci & Peking Union Med Coll, Natl Ctr Cardiovasc Dis, Beijing, Peoples R China

[4] Sichuan Changhong Elect Holding Grp, Changhong Res CHAIR, Mianyang, Sichuan, Peoples R China

[5] Univ Southern Calif, Dept Biomed Engn, Los Angeles, CA USA

[6] Duke Univ, Dept Elect & Comp Engn, Durham, NC USA

[7] Univ Sci & Technol China, Sch Engn, Hefei, Peoples R China

[8] SUNY Stony Brook, Dept Comp Sci, New York, NY USA

[9] Chinese Acad Sci, Shenzhen Inst Adv Technol, Paul C Lauterbur Res Ctr Biomed Imaging, Shenzhen, Peoples R China

[10] Stanford Univ, Dept Elect Engn, Stanford, CA USA

[11] Stanford Univ, Stanford Cardiovasc Inst, Sch Med, Div Cardiol, Stanford, CA USA

[12] Peking Union Med Coll Hosp, Beijing, Peoples R China

[13] Guangdong Prov Peoples Hosp, Guangzhou, Guangdong, Peoples R China

[14] Beijing Anzhen Hosp, Beijing, Peoples R China

[15] Tongji Hosp, Wuhan, Peoples R China

[16] Harbin Med Univ, Affiliated Hosp 2, Harbin, Peoples R China

[17] Renji Hosp, Shanghai, Peoples R China

[18] Lanzhou Univ, Hosp 1, Lanzhou, Peoples R China

[19] Univ Sci & Technol China, Div Life Sci & Med, USTC, Affiliated Hosp 1, Hefei, Peoples R China

[20] Northwestern Univ, Dept Elect & Comp Engn, Evanston, IL USA

[21] Mayo Clin, Alix Sch Med, Phoenix, AZ USA

来源：

NATURE MEDICINE | 2024年 / 30卷 / 05期

基金：

国家重点研发计划;

关键词：

RIGHT HEART CATHETERIZATION; CARDIOLOGY WORKING GROUP; EUROPEAN-SOCIETY; PULMONARY-HYPERTENSION; POSITION STATEMENT; TASK-FORCE; CARDIOMYOPATHY; CLASSIFICATION; MYOCARDITIS; MANAGEMENT;

D O I：

10.1038/s41591-024-02971-2

中图分类号：

Q5 [生物化学]; Q7 [分子生物学];

学科分类号：

071010 ; 081704 ;

摘要：

Cardiac magnetic resonance imaging (CMR) is the gold standard for cardiac function assessment and plays a crucial role in diagnosing cardiovascular disease (CVD). However, its widespread application has been limited by the heavy resource burden of CMR interpretation. Here, to address this challenge, we developed and validated computerized CMR interpretation for screening and diagnosis of 11 types of CVD in 9,719 patients. We propose a two-stage paradigm consisting of noninvasive cine-based CVD screening followed by cine and late gadolinium enhancement-based diagnosis. The screening and diagnostic models achieved high performance (area under the curve of 0.988 +/- 0.3% and 0.991 +/- 0.0%, respectively) in both internal and external datasets. Furthermore, the diagnostic model outperformed cardiologists in diagnosing pulmonary arterial hypertension, demonstrating the ability of artificial intelligence-enabled CMR to detect previously unidentified CMR features. This proof-of-concept study holds the potential to substantially advance the efficiency and scalability of CMR interpretation, thereby improving CVD screening and diagnosis.

引用

页码：1471 / +

页数：33