1
|
Han X, Luo N, Xu L, Cao J, Guo N, He Y, Hong M, Jia X, Wang Z, Yang Z. Artificial intelligence stenosis diagnosis in coronary CTA: effect on the performance and consistency of readers with less cardiovascular experience. BMC Med Imaging 2022; 22:28. [PMID: 35177029 PMCID: PMC8851787 DOI: 10.1186/s12880-022-00756-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2021] [Accepted: 02/11/2022] [Indexed: 11/25/2022] Open
Abstract
Background To investigate the influence of artificial intelligence (AI) based on deep learning on the diagnostic performance and consistency of inexperienced cardiovascular radiologists. Methods We enrolled 196 patents who had undergone both coronary computed tomography angiography (CCTA) and invasive coronary angiography (ICA) within 6 months. Four readers with less cardiovascular experience (Reader 1–Reader 4) and two cardiovascular radiologists (level II, Reader 5 and Reader 6) evaluated all images for ≥ 50% coronary artery stenosis, with ICA as the gold standard. Reader 3 and Reader 4 interpreted with AI system assistance, and the other four readers interpreted without the AI system. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy (area under the receiver operating characteristic curve (AUC)) of the six readers were calculated at the patient and vessel levels. Additionally, we evaluated the interobserver consistency between Reader 1 and Reader 2, Reader 3 and Reader 4, and Reader 5 and Reader 6. Results The AI system had 94% and 78% sensitivity at the patient and vessel levels, respectively, which were higher than that of Reader 5 and Reader 6. AI-assisted Reader 3 and Reader 4 had higher sensitivity (range + 7.2–+ 16.6% and + 5.9–+ 16.1%, respectively) and NPVs (range + 3.7–+ 13.4% and + 2.7–+ 4.2%, respectively) than Reader 1 and Reader 2 without AI. Good interobserver consistency was found between Reader 3 and Reader 4 in interpreting ≥ 50% stenosis (Kappa value = 0.75 and 0.80 at the patient and vessel levels, respectively). Only Reader 1 and Reader 2 showed poor interobserver consistency (Kappa value = 0.25 and 0.37). Reader 5 and Reader 6 showed moderate agreement (Kappa value = 0.55 and 0.61). Conclusions Our study showed that using AI could effectively increase the sensitivity of inexperienced readers and significantly improve the consistency of coronary stenosis diagnosis via CCTA. Trial registration Clinical trial registration number: ChiCTR1900021867. Name of registry: Diagnostic performance of artificial intelligence-assisted coronary computed tomography angiography for the assessment of coronary atherosclerotic stenosis. Supplementary Information The online version contains supplementary material available at 10.1186/s12880-022-00756-y.
Collapse
Affiliation(s)
- Xianjun Han
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95 YongAn Road, Beijing, 100050, People's Republic of China
| | - Nan Luo
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95 YongAn Road, Beijing, 100050, People's Republic of China
| | - Lixue Xu
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95 YongAn Road, Beijing, 100050, People's Republic of China
| | - Jiaxin Cao
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95 YongAn Road, Beijing, 100050, People's Republic of China
| | - Ning Guo
- Shukun (Beijing) Technology Co., Ltd., Jinhui Bd, Qiyang Rd, Beijing, 100102, People's Republic of China
| | - Yi He
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95 YongAn Road, Beijing, 100050, People's Republic of China
| | - Min Hong
- Department of Computer Software Engineering, Soonchunhyang University, Asan, South Korea
| | - Xibin Jia
- Beijing University of Technology, Beijing, People's Republic of China
| | - Zhenchang Wang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95 YongAn Road, Beijing, 100050, People's Republic of China
| | - Zhenghan Yang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95 YongAn Road, Beijing, 100050, People's Republic of China.
| |
Collapse
|
2
|
Are cardiology fellows receiving enough basic level I cardiovascular computed tomography education during their general fellowship training? Insights from a needs assessment survey at an academic medical center. J Cardiovasc Comput Tomogr 2021; 16:186-188. [PMID: 34600865 DOI: 10.1016/j.jcct.2021.09.005] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/13/2021] [Revised: 09/13/2021] [Accepted: 09/24/2021] [Indexed: 12/20/2022]
|
3
|
Henriksson L, Woisetschläger M, Alfredsson J, Janzon M, Ebbers T, Engvall J, Persson A. The transluminal attenuation gradient does not add diagnostic accuracy to coronary computed tomography. Acta Radiol 2021; 62:867-874. [PMID: 32722968 DOI: 10.1177/0284185120943042] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
BACKGROUND A method for improving the accuracy of coronary computed tomography angiography (CCTA) is highly sought after as it would help to avoid unnecessary invasive coronary angiographies. Measurement of the transluminal attenuation gradient (TAG) has been proposed as an alternative to other existing methods, i.e. CT perfusion and CT fractional flow reserve (FFR). PURPOSE To evaluate the incremental value of three types of TAG in high-pitch spiral CCTA with invasive FFR measurements as reference. MATERIAL AND METHODS TAG was measured using two semi-automatic methods and one manual method. A receiver operating characteristic (ROC) analysis was made to determine the usefulness of TAG alone as well as TAG combined with CCTA for detection of significant coronary artery stenoses defined by an invasive FFR value ≤0.80. RESULTS A total of 51 coronary vessels in 37 patients were included in this retrospective study. Hemodynamically significant stenoses were found in 13 vessels according to FFR. The ROC analysis TAG alone resulted in areas under the curve (AUCs) of 0.530 and 0.520 for the semi-automatic TAG and 0.557 for the manual TAG. TAG and CCTA combined resulted in AUCs of 0.567, 0.562 for semi-automatic TAG, and 0.569 for the manual TAG. CONCLUSION The results from our study showed no incremental value of TAG measured in single heartbeat CCTA in determining the severity of coronary artery stenosis degrees.
Collapse
Affiliation(s)
- Lilian Henriksson
- Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
- Department of Radiology, Department of Health, Medicine and Caring Sciences and, Linköping University, Linköping, Sweden
| | - Mischa Woisetschläger
- Department of Radiology, Department of Health, Medicine and Caring Sciences and, Linköping University, Linköping, Sweden
| | - Joakim Alfredsson
- Department of Cardiology and Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
| | - Magnus Janzon
- Department of Cardiology and Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
| | - Tino Ebbers
- Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
- Division of Cardiovascular Medicine, Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
| | - Jan Engvall
- Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
- Department of Clinical Physiology, Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
| | - Anders Persson
- Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
| |
Collapse
|
4
|
Chow BJW, Yam Y, Alenazy A, Crean AM, Clarkin O, Hossain A, Small GR. Are Training Programs Ready for the Rapid Adoption of CCTA?: CBME in CCTA. JACC Cardiovasc Imaging 2021; 14:1584-1593. [PMID: 33865790 DOI: 10.1016/j.jcmg.2021.01.040] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/11/2020] [Revised: 01/20/2021] [Accepted: 01/22/2021] [Indexed: 12/28/2022]
Abstract
OBJECTIVES This study sought to assess training volumes and its relationship to learning and identify potential new thresholds for determining expertise. BACKGROUND Competency-based medical education (CBME) is being rapidly adopted and therefore training programs will need to adapt and identify new and novel methods of defining, measuring, and assessing clinical skills. METHODS Consecutive cardiac computed tomography (CT) studies were interpreted independently by trainees and expert readers, and their interpretations (Agatston score, coronary artery disease severity, and Coronary Artery Disease Reporting and Data System) were collected. Kappa agreements were measured between trainees and experts for every 50 consecutive cases. Agreements between trainees and experts were tracked and compared with the agreement between expert readers. RESULTS A total of 36 trainees interpreted 14,432 cardiac CT studies. Agreement between trainees and experts increased with CT case volumes, but trainees learned at different rates. Using a threshold for expertise, skill of measuring coronary calcification was achieved within 50 cases, but expertise for coronary CT angiography appeared to require a mean case volume of 750, comprising 400 abnormal cases. CONCLUSIONS Current volume-based training guidelines may be insufficient and higher case volumes may be required. We demonstrate that tracking cardiac CT learners is feasible and that CBME could be incorporated into CT training programs.
Collapse
Affiliation(s)
- Benjamin J W Chow
- University of Ottawa Heart Institute, Ottawa, Canada; Department of Medicine (Cardiology), University of Ottawa, Ottawa, Canada; Department of Radiology, University of Ottawa, Ottawa, Canada.
| | - Yeung Yam
- University of Ottawa Heart Institute, Ottawa, Canada; Department of Medicine (Cardiology), University of Ottawa, Ottawa, Canada
| | - Ali Alenazy
- University of Ottawa Heart Institute, Ottawa, Canada; Department of Medicine (Cardiology), University of Ottawa, Ottawa, Canada
| | - Andrew M Crean
- University of Ottawa Heart Institute, Ottawa, Canada; Department of Medicine (Cardiology), University of Ottawa, Ottawa, Canada
| | - Owen Clarkin
- University of Ottawa Heart Institute, Ottawa, Canada; Department of Medicine (Cardiology), University of Ottawa, Ottawa, Canada
| | - Alomgir Hossain
- Cardiovascular Research Methods Centre, University of Ottawa Heart Institute, Ottawa, Canada; School of Epidemiology and Public Health, University of Ottawa, Ottawa, Ontario, Canada
| | - Gary R Small
- University of Ottawa Heart Institute, Ottawa, Canada
| |
Collapse
|
5
|
Choi AD, Thomas DM, Lee J, Abbara S, Cury RC, Leipsic JA, Maroules C, Nagpal P, Steigner ML, Wang DD, Williams MC, Zeb I, Villines TC, Blankstein R. 2020 SCCT Guideline for Training Cardiology and Radiology Trainees as Independent Practitioners (Level II) and Advanced Practitioners (Level III) in Cardiovascular Computed Tomography: A Statement from the Society of Cardiovascular Computed Tomography. Radiol Cardiothorac Imaging 2021; 3:e200480. [PMID: 33778658 PMCID: PMC7978013 DOI: 10.1148/ryct.2020200480] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/14/2023]
Abstract
Cardiovascular computed tomography (CCT) is a well-validated noninvasive imaging tool with an ever-expanding array of applications beyond the assessment of coronary artery disease. These include the evaluation of structural heart diseases, congenital heart diseases, peri-procedural electrophysiology applications, and the functional evaluation of ischemia. This breadth requires a robust and diverse training curriculum to ensure graduates of CCT training programs meet minimum competency standards for independent CCT interpretation. This statement from the Society of Cardiovascular Computed Tomography aims to supplement existing societal training guidelines by providing a curriculum and competency framework to inform the development of a comprehensive, integrated training experience for cardiology and radiology trainees in CCT. This article is being published synchronously in Radiology: Cardiothoracic Imaging, Journal of Cardiovascular Computed Tomography, and JACC: Cardiovascular Imaging. © 2020 Society of Cardiovascular Computed Tomography. Published by RSNA with permission.
Collapse
|
6
|
Choi AD, Thomas DM, Lee J, Abbara S, Cury RC, Leipsic JA, Maroules C, Nagpal P, Steigner ML, Wang DD, Williams MC, Zeb I, Villines TC, Blankstein R. 2020 SCCT Guideline for Training Cardiology and Radiology Trainees as Independent Practitioners (Level II) and Advanced Practitioners (Level III) in Cardiovascular Computed Tomography: A Statement from the Society of Cardiovascular Computed Tomography. J Cardiovasc Comput Tomogr 2021; 15:2-15. [PMID: 33032977 PMCID: PMC7427549 DOI: 10.1016/j.jcct.2020.08.003] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
Cardiovascular computed tomography (CCT) is a well-validated non-invasive imaging tool with an ever-expanding array of applications beyond the assessment of coronary artery disease. These include the evaluation of structural heart diseases, congenital heart diseases, peri-procedural electrophysiology applications, and the functional evaluation of ischemia. This breadth requires a robust and diverse training curriculum to ensure graduates of CCT training programs meet minimum competency standards for independent CCT interpretation. This statement from the Society of Cardiovascular Computed Tomography aims to supplement existing societal training guidelines by providing a curriculum and competency framework to inform the development of a comprehensive, integrated training experience for cardiology and radiology trainees in CCT.
Collapse
Affiliation(s)
- Andrew D Choi
- Division of Cardiology & Department of Radiology, The George Washington University School of Medicine, Washington, DC, USA.
| | | | - James Lee
- Department of Medicine, Division of Cardiology, Henry Ford Health System, Center for Structural Heart Disease, Detroit, MI, USA
| | - Suhny Abbara
- Division of Cardiothoracic Imaging, Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Ricardo C Cury
- Miami Cardiac and Vascular Institute, Baptist Health of South Florida, Miami, FL and Department of Radiology, Herbert Wertheim College of Medicine, Florida International University, Miami, FL, USA; Department of Radiology, Herbert Wertheim College of Medicine, Florida International University, Miami, FL, USA
| | - Jonathon A Leipsic
- Department of Radiology, St. Paul's Hospital, Vancouver, British Columbia, Canada
| | | | - Prashant Nagpal
- Department of Radiology, University of Iowa Hospitals and Clinics, Iowa City, IA, USA
| | - Michael L Steigner
- Cardiovascular Imaging Program, Department of Radiology, Brigham and Women's Hospital, Boston, MA, USA
| | - Dee Dee Wang
- Department of Medicine, Division of Cardiology, Henry Ford Health System, Center for Structural Heart Disease, Detroit, MI, USA
| | - Michelle C Williams
- University of Edinburgh/British Heart Foundation Centre for Cardiovascular Science, Edinburgh, UK
| | - Irfan Zeb
- Division of Cardiology, West Virginia University School of Medicine, Morgantown, WV, USA
| | - Todd C Villines
- Division of Cardiology, University of Virginia Health System, Charlottesville, VA, USA
| | - Ron Blankstein
- Cardiovascular Imaging Program, Departments of Medicine (Cardiovascular Division) and Radiology, Brigham and Women's Hospital, Boston, MA, USA
| |
Collapse
|
7
|
Choi AD, Thomas DM, Lee J, Abbara S, Cury RC, Leipsic JA, Maroules C, Nagpal P, Steigner ML, Wang DD, Williams MC, Zeb I, Villines TC, Blankstein R. 2020 SCCT Guideline for Training Cardiology and Radiology Trainees as Independent Practitioners (Level II) and Advanced Practitioners (Level III) in Cardiovascular Computed Tomography: A Statement from the Society of Cardiovascular Computed Tomography. JACC Cardiovasc Imaging 2021; 14:272-287. [PMID: 33168479 DOI: 10.1016/j.jcmg.2020.09.004] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/08/2023]
Abstract
Cardiovascular computed tomography (CCT) is a well-validated non-invasive imaging tool with an ever-expanding array of applications beyond the assessment of coronary artery disease. These include the evaluation of structural heart diseases, congenital heart diseases, peri-procedural electrophysiology applications, and the functional evaluation of ischemia. This breadth requires a robust and diverse training curriculum to ensure graduates of CCT training programs meet minimum competency standards for independent CCT interpretation. This statement from the Society of Cardiovascular Computed Tomography aims to supplement existing societal training guidelines by providing a curriculum and competency framework to inform the development of a comprehensive, integrated training experience for cardiology and radiology trainees in CCT.
Collapse
Affiliation(s)
- Andrew D Choi
- Division of Cardiology & Department of Radiology, The George Washington University School of Medicine, Washington, DC.
| | | | - James Lee
- Department of Medicine, Division of Cardiology, Henry Ford Health System, Center for Structural Heart Disease, Detroit, Michigan
| | - Suhny Abbara
- Division of Cardiothoracic Imaging, Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Ricardo C Cury
- Miami Cardiac and Vascular Institute, Baptist Health of South Florida, Miami, Florida and Department of Radiology, Herbert Wertheim College of Medicine, Florida International University, Miami, Florida; Department of Radiology, Herbert Wertheim College of Medicine, Florida International University, Miami, Florida
| | - Jonathon A Leipsic
- Department of Radiology, St. Paul's Hospital, Vancouver, British Columbia, Canada
| | | | - Prashant Nagpal
- Department of Radiology, University of Iowa Hospitals and Clinics, Iowa City, Iowa
| | - Michael L Steigner
- Cardiovascular Imaging Program, Department of Radiology, Brigham and Women's Hospital, Boston, Massachusetts
| | - Dee Dee Wang
- Department of Medicine, Division of Cardiology, Henry Ford Health System, Center for Structural Heart Disease, Detroit, Michigan
| | - Michelle C Williams
- University of Edinburgh/British Heart Foundation Centre for Cardiovascular Science, Edinburgh, United Kingdom
| | - Irfan Zeb
- Division of Cardiology, West Virginia University School of Medicine, Morgantown, West Virginia
| | - Todd C Villines
- Division of Cardiology, University of Virginia Health System, Charlottesville, Virginia
| | - Ron Blankstein
- Cardiovascular Imaging Program, Departments of Medicine (Cardiovascular Division) and Radiology, Brigham and Women's Hospital, Boston, Massachusetts
| |
Collapse
|
8
|
Artzner C, Daubert M, Ehieli W, Kong D, Mammarappallil J, Nikolaou K, Boll DT, Koweek L. Impact of computed tomography (CT)-derived fractional flow reserve on reader confidence for interpretation of coronary CT angiography. Eur J Radiol 2018; 108:242-248. [DOI: 10.1016/j.ejrad.2018.09.035] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2018] [Revised: 09/18/2018] [Accepted: 09/30/2018] [Indexed: 12/27/2022]
|
9
|
Maliel KT, Furgerson JL, Thomas DM. Training in Cardiac CT: a Continuously Evolving Modality. CURRENT CARDIOVASCULAR IMAGING REPORTS 2016. [DOI: 10.1007/s12410-016-9382-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|