Improved Accuracy of Myocardial Perfusion SPECT for the Detection of Coronary Artery Disease Using a Support Vector Machine Algorithm

Abstract

We aimed to improve the diagnostic accuracy of automatic myocardial perfusion SPECT (MPS) interpretation analysis for the prediction of coronary artery disease (CAD) by integrating several quantitative perfusion and functional variables for noncorrected (NC) data by Support Vector Machine (SVM) algorithm, a computer method for machine learning. Methods: Rest-stress gated 99m Tc MPS NC studies (n 5 957) from 623 consecutive patients with correlating invasive coronary angiography and 334 with a low likelihood of CAD (,5%) were assessed. Stenosis $50% in left main or $70% in all other vessels was considered abnormal. Total perfusion deficit (TPD) was computed automatically. In addition, ischemic changes (ISCHs) and ejection fraction changes (EFCs) between stress and rest were derived by quantitative software. The SVM was trained using a group of 125 patients (25 with low-likelihood, 25 with 0-vessel, 25 with 1-vessel, 25 with 2-vessel, and 25 with 3-vessel CAD) with the above quantitative variables and second-order polynomial fitting. The remaining patients (n 5 832) were categorized using probability estimates, with CAD defined as a probability estimate $ 0.50. The diagnostic accuracy of SVM was also compared with visual segmental scoring by 2 experienced readers. Results: The sensitivity of SVM (84%) was significantly better than ISCH (75%, P , 0.05) and EFC (31%, P , 0.05). The specificity of SVM (88%) was significantly better than TPD (78%, P , 0.05) and EFC (77%, P , 0.05). The diagnostic accuracy of SVM (86%) was significantly better than TPD (81%), ISCH (81%), or EFC (46%) (P , 0.05 for all). The receiver-operating-characteristic (ROC) area under the curve for SVM (0.92) was significantly better than TPD (0.90), ISCH (0.87), and EFC (0.64) (P , 0.001 for all). The diagnostic accuracy of SVM was comparable to the overall accuracy of both visual readers (86% vs. 84%, P 5 NS). The ROC area under the curve for SVM (0.92) was significantly better than that of both visual readers (0.87 and 0.88, P , 0.03). Conclusion: Computational integration of quantitative perfusion and functional variables using the SVM approach significantly improves the diagnostic accuracy of MPS and can significantly outperform visual assessment based on ROC analysis.

Relationship Between Quantitative Adverse Plaque Features From Coronary Computed Tomography Angiography and Downstream Impaired Myocardial Flow Reserve by 13 N-Ammonia Positron Emission Tomography

“…In ensemble boosting, a high performance of classification is obtained by combining individual classifiers, resulting in a strong ensemble classification scheme by iteratively adjusting appropriate weights for each of the base-level classifiers. For the current analysis, we utilized the LogitBoost method 22 , which has been shown to be superior to the other methods such as AdaBoost 23, 2425 , and has been successfully applied previously to a variety of classification schemes, including improvement of the diagnostic accuracy of myocardial perfusion Single Photon Emission Computed Tomography (SPECT) 26 . Patient age, gender, quantitative plaque features (maximum stenosis, non-calcified, low-density and calcified plaque burden, total lesion length and contrast density difference) as well as estimated myocardial mass were combined by machine learning into a composite risk score to predict regional impaired arterial MFR (MFR ≤ 2.0 by PET) within the Waikato Environment for Knowledge Analysis (WEKA) environment 27 .…”

Cardiac imaging: working towards fully-automated machine analysis & interpretation

“…For example, functional cardiac parameters and perfusion parameters both carry some diagnostic information and physicians try to combine this information in their minds when arriving at the final diagnosis. Studies have been reported, in which the overall diagnostic accuracy of conventional MPI was demonstrated to be improved by combining perfusion and functional parameters, utilizing a support vector machines (SVM) machine learning algorithm [109]. Perfusion deficits, ischemic changes, and ejection fraction changes between stress and rest were derived by the quantitative software.…”

Automated Quantitative Nuclear Cardiology Methods

“…integrated various parameters from automated analysis (TPD, ischemic changes, and ejection fraction changes between stress and rest) with a support vector machines algorithm to generate a diagnostic score for significant CAD which was significantly superior to any single parameter in isolation. 62 Moreover, further studies showed it is also possible to combine quantitative parameters with clinical parameters, akin to the integrative clinical scan analysis performed by physicians for both diagnostic and prognostic risk assessments. 4,63 A LogitBoost ensemble machine learning method trained in a 10-fold cross-validation experiment was compared to TPD and visual scores in a large study (n=1181) with correlating invasive angiography.…”