Automatic diagnosis of cardiovascular diseases using wavelet feature extraction and convolutional capsule network. (March 2023)

• Record Type: Journal Article
• Authors: El Boujnouni, Imane; Harouchi, Badr; Tali, Abdelhak; Rachafi, Said; Laaziz, Yassin
• Is Part Of: Biomedical signal processing and control. Volume 81(2023)
• Publication Date: 2023-03
• Subjects: Cardiovascular diseases -- Electrocardiogram -- Wavelet transform -- Capsule network -- Focal loss; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104497
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: An computer-aided diagnosis system based on the combination of wavelet transform features and capsule network is proposed for the automated classification of eight classes of cardiovascular diseases. The Focal loss is adopted to solve the class imbalance issue. The proposed method obtained great performance in terms of sensitivity using small training data. Abstract: Cardiovascular diseases (CVDs) are the primary cause of high mortality levels worldwide with coronary artery disease (CAD) being the largest contributor. Delay in diagnosis of CAD may progress and lead to myocardial infarction and congestive heart failure. Thus, timely diagnosis is a crucial key to prevent the development of serious complications and allow an optimum medication. This paper intends to design a diagnosis system to classify-eight different diseases using a capsule network with wavelet decomposed images of short ECG segments. It is noteworthy that in contrast to the previous studies that require large training data to efficiently predict unseen data, our designed models achieve high performance with less training data and training time. In the proposed system, firstly ECG signals are preprocessed and segmented into beats segments. Then, the continuous wavelet transform is used to transform the segments into 2D scalograms. These latter are decomposed using discrete wavelet transform to obtain wavelet coefficient images which are fed to the reformed capsule networks. The focal loss was applied to mitigate the class-imbalance issue. The proposed model was trained and tested using 5-fold cross-validation and train-test split techniques. The best performance parameters were achieved in the train-test split approach with an accuracy of 98.6%, sensitivity of 99.6%, specificity of 98.7%, precision of 99.1%, F1 score of 99.4% and area under the roc value of 0.99. Furthermore, experimental results demonstrated the superiority of our approach over state-of-the-art techniques using the same dataset.