Post-revascularization Ejection Fraction Prediction for Patients Undergoing Percutaneous Coronary Intervention Based on Myocardial Perfusion SPECT Imaging Radiomics: a Preliminary Machine Learning Study |
| |
Authors: | Mohebi Mobin Amini Mehdi Alemzadeh-Ansari Mohammad Javad Alizadehasl Azin Rajabi Ahmad Bitarafan Shiri Isaac Zaidi Habib Orooji Mahdi |
| |
Affiliation: | 1.Department of Biomedical Engineering, Tarbiat Modares University, Tehran, Iran ;2.Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva 4, Switzerland ;3.Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran ;4.Echocardiography Research Center, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran ;5.Cardio-Oncology Research Center, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran ;6.Geneva University Neuro Center, Geneva University, Geneva, Switzerland ;7.Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, Netherlands ;8.Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark ;9.Department of Electrical and Computer Engineering, University of California–Davis, Davis, CA, USA ; |
| |
Abstract: | In this study, the ability of radiomics features extracted from myocardial perfusion imaging with SPECT (MPI-SPECT) was investigated for the prediction of ejection fraction (EF) post-percutaneous coronary intervention (PCI) treatment. A total of 52 patients who had undergone pre-PCI MPI-SPECT were enrolled in this study. After normalization of the images, features were extracted from the left ventricle, initially automatically segmented by k-means and active contour methods, and finally edited and approved by an expert radiologist. More than 1700 2D and 3D radiomics features were extracted from each patient’s scan. A cross-combination of three feature selections and seven classifier methods was implemented. Three classes of no or dis-improvement (class 1), improved EF from 0 to 5% (class 2), and improved EF over 5% (class 3) were predicted by using tenfold cross-validation. Lastly, the models were evaluated based on accuracy, AUC, sensitivity, specificity, precision, and F-score. Neighborhood component analysis (NCA) selected the most predictive feature signatures, including Gabor, first-order, and NGTDM features. Among the classifiers, the best performance was achieved by the fine KNN classifier, which yielded mean accuracy, AUC, sensitivity, specificity, precision, and F-score of 0.84, 0.83, 0.75, 0.87, 0.78, and 0.76, respectively, in 100 iterations of classification, within the 52 patients with 10-fold cross-validation. The MPI-SPECT-based radiomic features are well suited for predicting post-revascularization EF and therefore provide a helpful approach for deciding on the most appropriate treatment. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|