Zhen-Yu Shu1, Si-Jia Cui2, Yue-Qiao Zhang3, Yu-Yun Xu1, Shng-Che Hung4,5, Li-Ping Fu6, Pei-Pei Pang7, Xiang-Yang Gong8,9, Qin-Yang Jin10. 1. Department of Radiology, Zhejiang Provincial People's Hospital, Affiliated People's Hospital of Hangzhou Medical College, No. 158 Shangtang Road, Hangzhou, Zhejiang, China. 2. Second Clinical College, Zhejiang Chinese Medical University, Hangzhou, China. 3. Department of Radiology, Shao-Yifu Hospital Affiliated to Zhejiang University, Hangzhou, China. 4. Division of Neuroradiology, Department of Radiology, University of North Carolina School of Medicine, Chapel Hill, NC, USA. 5. Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA. 6. Department of Nuclear Medicine, Zhejiang Provincial People's Hospital, Affiliated People's Hospital of Hangzhou Medical College, Hangzhou, China. 7. GE Healthcare China, Shanghai, China. 8. Department of Radiology, Zhejiang Provincial People's Hospital, Affiliated People's Hospital of Hangzhou Medical College, No. 158 Shangtang Road, Hangzhou, Zhejiang, China. cjr.gxy@hotmail.com. 9. Institute of Artificial Intelligence and Remote Imaging, Hangzhou Medical College, Hangzhou, China. cjr.gxy@hotmail.com. 10. Department of Radiology, Zhejiang Provincial People's Hospital, Affiliated People's Hospital of Hangzhou Medical College, No. 158 Shangtang Road, Hangzhou, Zhejiang, China. Jqy119@163.com.
Abstract
BACKGROUND: Coronary computed tomography angiography (CCTA) is a well-established non-invasive diagnostic test for the assessment of coronary artery diseases (CAD). CCTA not only provides information on luminal stenosis but also permits non-invasive assessment and quantitative measurement of stenosis based on radiomics. PURPOSE: This study is aimed to develop and validate a CT-based radiomics machine learning for predicting chronic myocardial ischemia (MIS). METHODS: CCTA and SPECT-myocardial perfusion imaging (MPI) of 154 patients with CAD were retrospectively analyzed and 94 patients were diagnosed with MIS. The patients were randomly divided into two sets: training (n = 107) and test (n = 47). Features were extracted for each CCTA cross-sectional image to identify myocardial segments. Multivariate logistic regression was used to establish a radiomics signature after feature dimension reduction. Finally, the radiomics nomogram was built based on a predictive model of MIS which in turn was constructed by machine learning combined with the clinically related factors. We then validated the model using data from 49 CAD patients and included 18 MIS patients from another medical center. The receiver operating characteristic curve evaluated the diagnostic accuracy of the nomogram based on the training set and was validated by the test and validation set. Decision curve analysis (DCA) was used to validate the clinical practicability of the nomogram. RESULTS: The accuracy of the nomogram for the prediction of MIS in the training, test and validation sets was 0.839, 0.832, and 0.816, respectively. The diagnosis accuracy of the nomogram, signature, and vascular stenosis were 0.824, 0.736 and 0.708, respectively. A significant difference in the number of patients with MIS between the high and low-risk groups was identified based on the nomogram (P < .05). The DCA curve demonstrated that the nomogram was clinically feasible. CONCLUSION: The radiomics nomogram constructed based on the image of CCTA act as a non-invasive tool for predicting MIS that helps to identify high-risk patients with coronary artery disease.
BACKGROUND: Coronary computed tomography angiography (CCTA) is a well-established non-invasive diagnostic test for the assessment of coronary artery diseases (CAD). CCTA not only provides information on luminal stenosis but also permits non-invasive assessment and quantitative measurement of stenosis based on radiomics. PURPOSE: This study is aimed to develop and validate a CT-based radiomics machine learning for predicting chronic myocardial ischemia (MIS). METHODS: CCTA and SPECT-myocardial perfusion imaging (MPI) of 154 patients with CAD were retrospectively analyzed and 94 patients were diagnosed with MIS. The patients were randomly divided into two sets: training (n = 107) and test (n = 47). Features were extracted for each CCTA cross-sectional image to identify myocardial segments. Multivariate logistic regression was used to establish a radiomics signature after feature dimension reduction. Finally, the radiomics nomogram was built based on a predictive model of MIS which in turn was constructed by machine learning combined with the clinically related factors. We then validated the model using data from 49 CAD patients and included 18 MIS patients from another medical center. The receiver operating characteristic curve evaluated the diagnostic accuracy of the nomogram based on the training set and was validated by the test and validation set. Decision curve analysis (DCA) was used to validate the clinical practicability of the nomogram. RESULTS: The accuracy of the nomogram for the prediction of MIS in the training, test and validation sets was 0.839, 0.832, and 0.816, respectively. The diagnosis accuracy of the nomogram, signature, and vascular stenosis were 0.824, 0.736 and 0.708, respectively. A significant difference in the number of patients with MIS between the high and low-risk groups was identified based on the nomogram (P < .05). The DCA curve demonstrated that the nomogram was clinically feasible. CONCLUSION: The radiomics nomogram constructed based on the image of CCTA act as a non-invasive tool for predicting MIS that helps to identify high-risk patients with coronary artery disease.
Authors: Andrés Larroza; Andrzej Materka; María P López-Lereu; José V Monmeneu; Vicente Bodí; David Moratal Journal: Eur J Radiol Date: 2017-05-01 Impact factor: 3.528
Authors: Christina M Shay; Hongyan Ning; Stephen R Daniels; Cherie R Rooks; Samuel S Gidding; Donald M Lloyd-Jones Journal: Circulation Date: 2013-04-01 Impact factor: 29.690
Authors: Marcus Hacker; Tobias Jakobs; Nicolas Hack; Konstantin Nikolaou; Christoph Becker; Franz von Ziegler; Andreas Knez; Andreas König; Volker Klauss; Maximilian Reiser; Klaus Hahn; Reinhold Tiling Journal: Eur J Nucl Med Mol Imaging Date: 2006-09-02 Impact factor: 9.236
Authors: W Bob Meijboom; Carlos A G Van Mieghem; Niels van Pelt; Annick Weustink; Francesca Pugliese; Nico R Mollet; Eric Boersma; Eveline Regar; Robert J van Geuns; Peter J de Jaegere; Patrick W Serruys; Gabriel P Krestin; Pim J de Feyter Journal: J Am Coll Cardiol Date: 2008-08-19 Impact factor: 24.094
Authors: Edward Hulten; Christopher Pickett; Marcio Sommer Bittencourt; Todd C Villines; Sara Petrillo; Marcelo F Di Carli; Ron Blankstein Journal: J Am Coll Cardiol Date: 2013-02-06 Impact factor: 24.094
Authors: Stefanie Mangold; Sergios Gatidis; Oliver Luz; Benjamin König; Christoph Schabel; Malte N Bongers; Thomas G Flohr; Claus D Claussen; Christoph Thomas Journal: Invest Radiol Date: 2014-12 Impact factor: 6.016