Multi support vector machine and image processing for diagnosis of coronary artery disease

The optimal non-invasive test, Coronary computed tomography angiography (CCTA), is to control coronary artery disease (CAD). This paper proposes a developed algorithm called Multi Support Vector Machine (MSVM) applied in classification and diagnosing common heart disease, CAD, utilizing the features extracted from patients’ CCTA images through two image-processing-based approaches. These approaches including quantification of cardiovascular vessels autoencoder (AE) network are utilized for extraction images. Then, novel MSVM diseases. A dataset Tehran Heart Center addition collection datasets literature evaluate performance proposed algorithms based on accuracy, precision, recall measures. compared with number existing methods where results show that outperforms all competing terms In addition, it concluded performs much better than classical SVM method under scenarios.