Machine Learning Algorithms to Distinguish Myocardial Perfusion SPECT Polar Maps

Myocardial perfusion imaging (MPI) plays an important role in patients with suspected and documented coronary artery disease (CAD). Machine Learning (ML) algorithms have been developed for many medical applications with excellent performance. The aim of the study was to use ML algorithms to discern normal and abnormal gated Single Photon Emission Computed Tomography (SPECT) images. One thousand and seven polar maps from a database of patients referred to a university hospital for clinically indicated MPI were analyzed between January 2016 and December 2018. These studies were reported and evaluated by two different expert readers. The image features were extracted from an image slicing process. The dataset was then divided into training and testing data, and cross-validation was performed with data augmentation in the training set. Four ML models were tested. All models had accuracy greater than 90% and area under the receiver operating characteristics curve (AUC) greater than 0.80 except for Adaptive Boosting (AUC = 0.77), while all precision and recall obtained were greater than 96% and 92%, respectively. Random Forest had the best performance (AUC: 0.853; accuracy: 0,938; precision: 0.968; recall: 0.963). ML algorithms performed very well in the image classification. These models were capable of distinguishing polar maps remarkably into normal and abnormal.