Deep Learning Analysis of Polar Maps from SPECT Myocardial Perfusion Imaging for Prediction of Coronary Artery Disease

Abstract

Purpose: This study aimed to investigate the diagnostic accuracy of deep convolutional neural networks for classifying the polar map images in Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) by considering the physician’s diagnosis as reference.Methods: 3318 images of stress and rest polar maps related to patients (67% women and 33% men) who underwent 99mTc-sestamibi MPI were collected. The images were manually labeled with normal and abnormal labels according to the doctor’s diagnosis reports. The proposed deep learning model was trained using stress and rest polar maps and evaluated for prediction of obstructive disease in a stratified 5-fold cross-validation procedure.Results: The mean values of accuracy, sensitivity, accuracy, specificity, f1 score, and the area under the roc curve were 0.7562, 0.7856, 0.5748, 0.7434, 0.6646, and, 0.8450, respectively over 5 folds using both stress and rest scans. The inclusion of rest perfusion maps significantly improved AUC of the deep learning model (AUC: 0.845; 95% CI: 0.832-0.857), compared with using stress polar maps only (AUC: 0.827; 95% CI: 0.814-0.840); P < 0.05.Conclusion: The results of the present work reveal the possible applications of deep learning for polar map images classification in SPECT MPI.

AI-based classification algorithms in SPECT myocardial perfusion imaging for cardiovascular diagnosis: a review

“…Zahiri et al . [34]. investigated CNNs and exploited their capabilities in classifying polar maps in SPECT MPI format for diagnosing CAD.…”

Explainable Deep Fuzzy Cognitive Map Diagnosis of Coronary Artery Disease: Integrating Myocardial Perfusion Imaging, Clinical Data, and Natural Language Insights

“…Regarding ensuring our model's robustness, k-fold cross-validation was performed, where k represents the number of partitions into which the dataset is divided [47]. In our case, we divided the dataset into 10 partitions, of which 9 were utilized as training and 1 as testing.…”

Deep Learning-Based Automated Diagnosis for Coronary Artery Disease Using SPECT-MPI Images

“…The method is rather advantageous for most cases. This method can offer rest and stress representation of the patient's heart to identify areas that have myocardial perfusion abnormalities [3]. The most important factor is that SPECT offers three-dimensional information, as well as reduces scanning time, and decreases the procedure's cost [4,5].…”

“…This advantage has been extensively utilized by researchers in the field in adapting DL into a variety of medical diagnostics with minimal implementation and heterogeneous infrastructure harmonization efforts. Additionally, DL provides a pipeline for medical imaging applications such as segmentation, regression, image generation, and representation learning in medical diagnostics [3]. DL is an advancement of artificial neural networks (ANNs) that consists of more layers that allow for higher levels of abstraction and better data predictions.…”

“…This study concludes that DL for stress MPI has the potential in providing notable help in clinical cases. Zahiri et al in [3] suggested the implementation of a CNN to classify SPECT images for a successful CAD diagnosis. The dataset consists of polar maps demonstrated in stress and rest mode.…”