Heart sounds classification: Application of a new CyTex inspired method and deep convolutional neural network with transfer learning

Abstract

Analysis of heart sounds is an effective means for the early diagnosis of cardiac pathologies. Heart sound classification is a challenging multi-disciplinary field that attracts many machine learning researchers. This paper proposes a new CyTex-inspired transform to convert heart sound signals to textured images. In our proposed method, the neighboring pixels have meaningful relationships that result in semi-periodic patterns in the output image. This method has two significant benefits. Firstly, this makes it possible to apply deep convolutional neural networks (DCNN) to heart sound classification. Consequently, correlative moving masks of the convolutional layers can extract short-term and long-term information from these images in vertical and horizontal directions. Secondly, by converting the heart sound signal to images as a compatible input for DCNNs, we can employ a transfer learning scheme to reduce the risk of overfitting. The performance of four popular pre-trained DCNNs – AlexNet, VGG16, InceptionV3, and ResNet50 – has been tested. Furthermore, data augmentation, hyper-parameter optimization, and drop-out techniques are employed. The performance of the proposed system is verified on the heart sounds dataset PhysioNet. Results were obtained using cross-validation techniques. Our experiments demonstrate the potential of our proposed method for achieving excellent performance compared to previous methods on the same dataset with a score of over 0.9200 at a sensitivity of 0.8775 and specificity of 0.9637 using the ResNet with data augmentation, hyperparameter optimization, and dropout techniques.