1
|
Wang YRJ, Yang K, Wen Y, Wang P, Hu Y, Lai Y, Wang Y, Zhao K, Tang S, Zhang A, Zhan H, Lu M, Chen X, Yang S, Dong Z, Wang Y, Liu H, Zhao L, Huang L, Li Y, Wu L, Chen Z, Luo Y, Liu D, Zhao P, Lin K, Wu JC, Zhao S. Screening and diagnosis of cardiovascular disease using artificial intelligence-enabled cardiac magnetic resonance imaging. Nat Med 2024; 30:1471-1480. [PMID: 38740996 PMCID: PMC11108784 DOI: 10.1038/s41591-024-02971-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Accepted: 04/03/2024] [Indexed: 05/16/2024]
Abstract
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.
Collapse
Affiliation(s)
| | - Kai Yang
- Department of Magnetic Resonance Imaging, Fuwai Hospital and National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Yi Wen
- Changhong AI Research (CHAIR), Sichuan Changhong Electronics Holding Group, Mianyang, China
| | - Pengcheng Wang
- Department of Biomedical Engineering, University of Southern California, Los Angeles, CA, USA
| | - Yuepeng Hu
- Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA
| | - Yongfan Lai
- School of Engineering, University of Science and Technology of China, Hefei, China
| | - Yufeng Wang
- Department of Computer Science, Stony Brook University, New York, NY, USA
| | - Kankan Zhao
- Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
| | - Siyi Tang
- School of Medicine, Stanford University, Stanford, CA, USA
- Department of Electrical Engineering, Stanford University, Stanford, CA, USA
| | - Angela Zhang
- School of Medicine, Stanford University, Stanford, CA, USA
- Stanford Cardiovascular Institute, School of Medicine (Division of Cardiology), Stanford University, Stanford, CA, USA
| | - Huayi Zhan
- Changhong AI Research (CHAIR), Sichuan Changhong Electronics Holding Group, Mianyang, China
| | - Minjie Lu
- Department of Magnetic Resonance Imaging, Fuwai Hospital and National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Xiuyu Chen
- Department of Magnetic Resonance Imaging, Fuwai Hospital and National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Shujuan Yang
- Department of Magnetic Resonance Imaging, Fuwai Hospital and National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Zhixiang Dong
- Department of Magnetic Resonance Imaging, Fuwai Hospital and National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Yining Wang
- Peking Union Medical College Hospital, Beijing, China
| | - Hui Liu
- Guangdong Provincial People's Hospital, Guangzhou, China
| | - Lei Zhao
- Beijing Anzhen Hospital, Beijing, China
| | | | - Yunling Li
- The Second Affiliated Hospital of Harbin Medical University, Harbin, China
| | | | - Zixian Chen
- The First Hospital of Lanzhou University, Lanzhou, China
| | - Yi Luo
- The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China
| | - Dongbo Liu
- Changhong AI Research (CHAIR), Sichuan Changhong Electronics Holding Group, Mianyang, China
| | - Pengbo Zhao
- Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL, USA
| | - Keldon Lin
- Mayo Clinic Alix School of Medicine, Phoenix, AZ, USA
| | - Joseph C Wu
- School of Medicine, Stanford University, Stanford, CA, USA
- Stanford Cardiovascular Institute, School of Medicine (Division of Cardiology), Stanford University, Stanford, CA, USA
| | - Shihua Zhao
- Department of Magnetic Resonance Imaging, Fuwai Hospital and National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
| |
Collapse
|
3
|
Qian WL, Jiang Y, Liu X, Guo YK, Li Y, Tang X, Yang ZG. Distinguishing cardiac myxomas from cardiac thrombi by a radiomics signature based on cardiovascular contrast-enhanced computed tomography images. BMC Cardiovasc Disord 2021; 21:152. [PMID: 33765929 PMCID: PMC7993472 DOI: 10.1186/s12872-021-01961-3] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2020] [Accepted: 03/18/2021] [Indexed: 02/08/2023] Open
Abstract
Background Cardiac myxomas (CMs) and thrombi are associated with high morbidity and mortality. These two conditions need totally different treatments. However, they are difficult to distinguish using naked eye. In clinical, misdiagnoses occur now and then. This study aimed to compare the characteristics of CMs and cardiac thrombi and investigate the value of a radiomics signature in distinguishing CMs from cardiac thrombi, based on cardiovascular contrast-enhanced computed tomography (CECT) images. Methods A total of 109 patients who had CMs (n = 59) and cardiac thrombi (n = 50) were enrolled in this retrospective study from 2009 to 2019. First, the lesion characteristics of cardiovascular CECT images were documented and compared by two radiologists. Then all patients were randomly allotted to either a primary group or a validation group according to a 7:3 ratio. Univariate analysis and the least absolute shrinkage and selection operator were used to select robust features. The best radiomics signature was constructed and validated using multivariate logistic regression. An independent clinical model was created for comparison. Results The best radiomics signature was developed using eight selected radiomics. The classification accuracies of the radiomics signature were 90.8% and 90.9%, and the area under the receiver operating characteristic curves were 0.969 and 0.926 in the training and testing cohorts, respectively. Cardiovascular CECT images showed that the two diseases had significant differences in location, surface, Hydrothorax, pericardial effusion and heart enlargement. The naked eye findings were used to create the clinical model. All metrics of the radiomics signature were higher than those of clinical model. Conclusions Compared with clinical model, the radiomics signature based on cardiovascular CECT performed better in differentiating CMs and thrombi, suggesting that it could help improving the diagnostic efficiency. Supplementary Information The online version contains supplementary material available at 10.1186/s12872-021-01961-3.
Collapse
Affiliation(s)
- Wen-Lei Qian
- Department of Radiology, West China Hospital, Sichuan University, 37# Guo Xue Xiang, Chengdu, 610041, Sichuan, China
| | - Yu Jiang
- Department of Radiology, West China Hospital, Sichuan University, 37# Guo Xue Xiang, Chengdu, 610041, Sichuan, China
| | - Xi Liu
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Department of Radiology, Peking University Cancer Hospital and Institute, No. 52 Fu Cheng Road Hai Dian District, Beijing, 100142, China
| | - Ying-Kun Guo
- Department of Radiology, Key Laboratory of Obstetric and Gynecologic and Pediatric Diseases and Birth Defects of Ministry of Education, West China Second University Hospital, Sichuan University, 20# South Renmin Road, Chengdu, 610041, Sichuan, China
| | - Yuan Li
- Department of Radiology, West China Hospital, Sichuan University, 37# Guo Xue Xiang, Chengdu, 610041, Sichuan, China
| | - Xin Tang
- Department of Radiology, West China Hospital, Sichuan University, 37# Guo Xue Xiang, Chengdu, 610041, Sichuan, China
| | - Zhi-Gang Yang
- Department of Radiology, West China Hospital, Sichuan University, 37# Guo Xue Xiang, Chengdu, 610041, Sichuan, China.
| |
Collapse
|
4
|
Uhlig J, Al-Bourini O, Salgado R, Francone M, Vliegenthart R, Bremerich J, Lotz J, Gutberlet M. Gadolinium-based Contrast Agents for Cardiac MRI: Use of Linear and Macrocyclic Agents with Associated Safety Profile from 154 779 European Patients. Radiol Cardiothorac Imaging 2020; 2:e200102. [PMID: 33778622 DOI: 10.1148/ryct.2020200102] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2020] [Revised: 07/20/2019] [Accepted: 07/23/2020] [Indexed: 12/14/2022]
Abstract
Purpose To assess current use and acute safety profiles of gadolinium-based contrast agents (GBCAs) in cardiac MRI given recent suspensions of GBCA approval. Materials and Methods Patients were retrospectively included from the multinational multicenter European Society of Cardiovascular Radiology (ESCR) MR/CT Registry collected between January 2013 and October 2019. GBCA-associated acute adverse events (AAEs) were classified as mild (self-limiting), moderate (pronounced AAE requiring medical management), and severe (life threatening). Multivariable generalized linear mixed-effect models were used to assess AAE likelihood. Results A total of 154 779 patients (average age, 53 years ± 19 [standard deviation]; 99 106 men) who underwent cardiac MRI were included, the majority of whom underwent administration of GBCAs (94.2% [n = 145 855]). While linear GBCAs were used in 15.2% of examinations through 2011, their use decreased to less than 1% in 2018 and 2019. Overall, 0.36% (n = 556) of AAEs were documented (mild, 0.12% [n = 178]; moderate, 0.21% [n = 331]; severe, 0.03% [n = 47]). For nonenhanced cardiac MRI, examination-related events were reported in 2.59% (231 of 8924) of cases, the majority of which were anxiety (0.98% [n = 87]) and dyspnea (0.93% [n = 83]). AAE rates varied significantly by pharmacologic stressor, GBCA molecular structure (macrocyclic vs linear GBCA: multivariable odds ratio, 0.634; 95% confidence interval: 0.452, 0.888; P = .008), GBCA subtype, and imaging indication. Conclusion Gadolinium-based contrast agent administration changed according to recent regulatory decisions, with use of macrocyclic agents almost exclusively in 2018 and 2019; these agents also demonstrated a favorable acute safety profile.Supplemental material is available for this article.© RSNA, 2020.
Collapse
Affiliation(s)
- Johannes Uhlig
- Department of Diagnostic and Interventional Radiology, University Medical Center Goettingen, Robert-Koch-Strasse 40, 37075 Goettingen, Germany (J.U., O.A.B., J.L.); Section of Interventional Radiology, Yale School of Medicine, New Haven, Conn (J.U.); Department of Radiology, Antwerp University Hospital, Antwerp, Belgium (R.S.); Department of Radiology, Holy Heart Hospital, Lier, Belgium (R.S.); Department of Radiological, Oncological and Pathological Sciences, Sapienza University of Rome, Rome, Italy (M.F.); Department of Radiology, Center for Medical Imaging, University Medical Center Groningen, Groningen, the Netherlands (R.V.); Radiology Department, University Hospital Basel, Basel, Switzerland (J.B.); German Cardiovascular Research Center (DZHK), Partner site Goettingen, Germany (J.L.); and Department of Diagnostic and Interventional Radiology, University of Leipzig-Heart Centre, Leipzig, Germany (M.G.)
| | - Omar Al-Bourini
- Department of Diagnostic and Interventional Radiology, University Medical Center Goettingen, Robert-Koch-Strasse 40, 37075 Goettingen, Germany (J.U., O.A.B., J.L.); Section of Interventional Radiology, Yale School of Medicine, New Haven, Conn (J.U.); Department of Radiology, Antwerp University Hospital, Antwerp, Belgium (R.S.); Department of Radiology, Holy Heart Hospital, Lier, Belgium (R.S.); Department of Radiological, Oncological and Pathological Sciences, Sapienza University of Rome, Rome, Italy (M.F.); Department of Radiology, Center for Medical Imaging, University Medical Center Groningen, Groningen, the Netherlands (R.V.); Radiology Department, University Hospital Basel, Basel, Switzerland (J.B.); German Cardiovascular Research Center (DZHK), Partner site Goettingen, Germany (J.L.); and Department of Diagnostic and Interventional Radiology, University of Leipzig-Heart Centre, Leipzig, Germany (M.G.)
| | - Rodrigo Salgado
- Department of Diagnostic and Interventional Radiology, University Medical Center Goettingen, Robert-Koch-Strasse 40, 37075 Goettingen, Germany (J.U., O.A.B., J.L.); Section of Interventional Radiology, Yale School of Medicine, New Haven, Conn (J.U.); Department of Radiology, Antwerp University Hospital, Antwerp, Belgium (R.S.); Department of Radiology, Holy Heart Hospital, Lier, Belgium (R.S.); Department of Radiological, Oncological and Pathological Sciences, Sapienza University of Rome, Rome, Italy (M.F.); Department of Radiology, Center for Medical Imaging, University Medical Center Groningen, Groningen, the Netherlands (R.V.); Radiology Department, University Hospital Basel, Basel, Switzerland (J.B.); German Cardiovascular Research Center (DZHK), Partner site Goettingen, Germany (J.L.); and Department of Diagnostic and Interventional Radiology, University of Leipzig-Heart Centre, Leipzig, Germany (M.G.)
| | - Marco Francone
- Department of Diagnostic and Interventional Radiology, University Medical Center Goettingen, Robert-Koch-Strasse 40, 37075 Goettingen, Germany (J.U., O.A.B., J.L.); Section of Interventional Radiology, Yale School of Medicine, New Haven, Conn (J.U.); Department of Radiology, Antwerp University Hospital, Antwerp, Belgium (R.S.); Department of Radiology, Holy Heart Hospital, Lier, Belgium (R.S.); Department of Radiological, Oncological and Pathological Sciences, Sapienza University of Rome, Rome, Italy (M.F.); Department of Radiology, Center for Medical Imaging, University Medical Center Groningen, Groningen, the Netherlands (R.V.); Radiology Department, University Hospital Basel, Basel, Switzerland (J.B.); German Cardiovascular Research Center (DZHK), Partner site Goettingen, Germany (J.L.); and Department of Diagnostic and Interventional Radiology, University of Leipzig-Heart Centre, Leipzig, Germany (M.G.)
| | - Rozemarijn Vliegenthart
- Department of Diagnostic and Interventional Radiology, University Medical Center Goettingen, Robert-Koch-Strasse 40, 37075 Goettingen, Germany (J.U., O.A.B., J.L.); Section of Interventional Radiology, Yale School of Medicine, New Haven, Conn (J.U.); Department of Radiology, Antwerp University Hospital, Antwerp, Belgium (R.S.); Department of Radiology, Holy Heart Hospital, Lier, Belgium (R.S.); Department of Radiological, Oncological and Pathological Sciences, Sapienza University of Rome, Rome, Italy (M.F.); Department of Radiology, Center for Medical Imaging, University Medical Center Groningen, Groningen, the Netherlands (R.V.); Radiology Department, University Hospital Basel, Basel, Switzerland (J.B.); German Cardiovascular Research Center (DZHK), Partner site Goettingen, Germany (J.L.); and Department of Diagnostic and Interventional Radiology, University of Leipzig-Heart Centre, Leipzig, Germany (M.G.)
| | - Jens Bremerich
- Department of Diagnostic and Interventional Radiology, University Medical Center Goettingen, Robert-Koch-Strasse 40, 37075 Goettingen, Germany (J.U., O.A.B., J.L.); Section of Interventional Radiology, Yale School of Medicine, New Haven, Conn (J.U.); Department of Radiology, Antwerp University Hospital, Antwerp, Belgium (R.S.); Department of Radiology, Holy Heart Hospital, Lier, Belgium (R.S.); Department of Radiological, Oncological and Pathological Sciences, Sapienza University of Rome, Rome, Italy (M.F.); Department of Radiology, Center for Medical Imaging, University Medical Center Groningen, Groningen, the Netherlands (R.V.); Radiology Department, University Hospital Basel, Basel, Switzerland (J.B.); German Cardiovascular Research Center (DZHK), Partner site Goettingen, Germany (J.L.); and Department of Diagnostic and Interventional Radiology, University of Leipzig-Heart Centre, Leipzig, Germany (M.G.)
| | - Joachim Lotz
- Department of Diagnostic and Interventional Radiology, University Medical Center Goettingen, Robert-Koch-Strasse 40, 37075 Goettingen, Germany (J.U., O.A.B., J.L.); Section of Interventional Radiology, Yale School of Medicine, New Haven, Conn (J.U.); Department of Radiology, Antwerp University Hospital, Antwerp, Belgium (R.S.); Department of Radiology, Holy Heart Hospital, Lier, Belgium (R.S.); Department of Radiological, Oncological and Pathological Sciences, Sapienza University of Rome, Rome, Italy (M.F.); Department of Radiology, Center for Medical Imaging, University Medical Center Groningen, Groningen, the Netherlands (R.V.); Radiology Department, University Hospital Basel, Basel, Switzerland (J.B.); German Cardiovascular Research Center (DZHK), Partner site Goettingen, Germany (J.L.); and Department of Diagnostic and Interventional Radiology, University of Leipzig-Heart Centre, Leipzig, Germany (M.G.)
| | - Matthias Gutberlet
- Department of Diagnostic and Interventional Radiology, University Medical Center Goettingen, Robert-Koch-Strasse 40, 37075 Goettingen, Germany (J.U., O.A.B., J.L.); Section of Interventional Radiology, Yale School of Medicine, New Haven, Conn (J.U.); Department of Radiology, Antwerp University Hospital, Antwerp, Belgium (R.S.); Department of Radiology, Holy Heart Hospital, Lier, Belgium (R.S.); Department of Radiological, Oncological and Pathological Sciences, Sapienza University of Rome, Rome, Italy (M.F.); Department of Radiology, Center for Medical Imaging, University Medical Center Groningen, Groningen, the Netherlands (R.V.); Radiology Department, University Hospital Basel, Basel, Switzerland (J.B.); German Cardiovascular Research Center (DZHK), Partner site Goettingen, Germany (J.L.); and Department of Diagnostic and Interventional Radiology, University of Leipzig-Heart Centre, Leipzig, Germany (M.G.)
| |
Collapse
|