Classification of Heart Sounds Using Chaogram Transform and Deep Convolutional Neural Network Transfer Learning
Heart sounds convey important information regarding potential heart diseases. Currently, heart sound classification attracts many researchers from the fields of telemedicine, digital signal processing, and machine learning—among others—mainly to identify cardiac pathology as quickly as possible. Thi...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/24/9569 |
| _version_ | 1797455391674597376 |
|---|---|
| author | Ali Harimi Yahya Majd Abdorreza Alavi Gharahbagh Vahid Hajihashemi Zeynab Esmaileyan José J. M. Machado João Manuel R. S. Tavares |
| author_facet | Ali Harimi Yahya Majd Abdorreza Alavi Gharahbagh Vahid Hajihashemi Zeynab Esmaileyan José J. M. Machado João Manuel R. S. Tavares |
| author_sort | Ali Harimi |
| collection | DOAJ |
| description | Heart sounds convey important information regarding potential heart diseases. Currently, heart sound classification attracts many researchers from the fields of telemedicine, digital signal processing, and machine learning—among others—mainly to identify cardiac pathology as quickly as possible. This article proposes chaogram as a new transform to convert heart sound signals to colour images. In the proposed approach, the output image is, therefore, the projection of the reconstructed phase space representation of the phonocardiogram (PCG) signal on three coordinate planes. This has two major benefits: (1) it makes possible to apply deep convolutional neural networks to heart sounds and (2) it is also possible to employ a transfer learning scheme by converting a heart sound signal to an image. The performance of the proposed approach was verified on the PhysioNet dataset. Due to the imbalanced data on this dataset, it is common to assess the results quality using the average of sensitivity and specificity, which is known as score, instead of accuracy. In this study, the best results were achieved using the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>I</mi><mi>n</mi><mi>c</mi><mi>e</mi><mi>p</mi><mi>t</mi><mi>i</mi><mi>o</mi><mi>n</mi><mi>V</mi><mn>3</mn></mrow></semantics></math></inline-formula> model, which achieved a score of 88.06%. |
| first_indexed | 2024-03-09T15:53:44Z |
| format | Article |
| id | doaj.art-9b7c9019ccb84746aa589386baf0e45e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T15:53:44Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9b7c9019ccb84746aa589386baf0e45e2023-11-24T17:51:42ZengMDPI AGSensors1424-82202022-12-012224956910.3390/s22249569Classification of Heart Sounds Using Chaogram Transform and Deep Convolutional Neural Network Transfer LearningAli Harimi0Yahya Majd1Abdorreza Alavi Gharahbagh2Vahid Hajihashemi3Zeynab Esmaileyan4José J. M. Machado5João Manuel R. S. Tavares6Department of Electrical Engineering, Shahrood Branch, Islamic Azad University, Shahrood 43189-36199, IranSchool of Surveying and Built Environment, Toowoomba Campus, University of Southern Queensland (USQ), Darling Heights, QLD 4350, AustraliaFaculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, s/n, 4200-465 Porto, PortugalFaculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, s/n, 4200-465 Porto, PortugalDepartment of Electrical Engineering, Shahrood Branch, Islamic Azad University, Shahrood 43189-36199, IranDepartamento de Engenharia Mecânica, Faculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, s/n, 4200-465 Porto, PortugalDepartamento de Engenharia Mecânica, Faculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, s/n, 4200-465 Porto, PortugalHeart sounds convey important information regarding potential heart diseases. Currently, heart sound classification attracts many researchers from the fields of telemedicine, digital signal processing, and machine learning—among others—mainly to identify cardiac pathology as quickly as possible. This article proposes chaogram as a new transform to convert heart sound signals to colour images. In the proposed approach, the output image is, therefore, the projection of the reconstructed phase space representation of the phonocardiogram (PCG) signal on three coordinate planes. This has two major benefits: (1) it makes possible to apply deep convolutional neural networks to heart sounds and (2) it is also possible to employ a transfer learning scheme by converting a heart sound signal to an image. The performance of the proposed approach was verified on the PhysioNet dataset. Due to the imbalanced data on this dataset, it is common to assess the results quality using the average of sensitivity and specificity, which is known as score, instead of accuracy. In this study, the best results were achieved using the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>I</mi><mi>n</mi><mi>c</mi><mi>e</mi><mi>p</mi><mi>t</mi><mi>i</mi><mi>o</mi><mi>n</mi><mi>V</mi><mn>3</mn></mrow></semantics></math></inline-formula> model, which achieved a score of 88.06%.https://www.mdpi.com/1424-8220/22/24/9569biomedical signalphonocardiogramdeep learningsignal to image transform |
| spellingShingle | Ali Harimi Yahya Majd Abdorreza Alavi Gharahbagh Vahid Hajihashemi Zeynab Esmaileyan José J. M. Machado João Manuel R. S. Tavares Classification of Heart Sounds Using Chaogram Transform and Deep Convolutional Neural Network Transfer Learning Sensors biomedical signal phonocardiogram deep learning signal to image transform |
| title | Classification of Heart Sounds Using Chaogram Transform and Deep Convolutional Neural Network Transfer Learning |
| title_full | Classification of Heart Sounds Using Chaogram Transform and Deep Convolutional Neural Network Transfer Learning |
| title_fullStr | Classification of Heart Sounds Using Chaogram Transform and Deep Convolutional Neural Network Transfer Learning |
| title_full_unstemmed | Classification of Heart Sounds Using Chaogram Transform and Deep Convolutional Neural Network Transfer Learning |
| title_short | Classification of Heart Sounds Using Chaogram Transform and Deep Convolutional Neural Network Transfer Learning |
| title_sort | classification of heart sounds using chaogram transform and deep convolutional neural network transfer learning |
| topic | biomedical signal phonocardiogram deep learning signal to image transform |
| url | https://www.mdpi.com/1424-8220/22/24/9569 |
| work_keys_str_mv | AT aliharimi classificationofheartsoundsusingchaogramtransformanddeepconvolutionalneuralnetworktransferlearning AT yahyamajd classificationofheartsoundsusingchaogramtransformanddeepconvolutionalneuralnetworktransferlearning AT abdorrezaalavigharahbagh classificationofheartsoundsusingchaogramtransformanddeepconvolutionalneuralnetworktransferlearning AT vahidhajihashemi classificationofheartsoundsusingchaogramtransformanddeepconvolutionalneuralnetworktransferlearning AT zeynabesmaileyan classificationofheartsoundsusingchaogramtransformanddeepconvolutionalneuralnetworktransferlearning AT josejmmachado classificationofheartsoundsusingchaogramtransformanddeepconvolutionalneuralnetworktransferlearning AT joaomanuelrstavares classificationofheartsoundsusingchaogramtransformanddeepconvolutionalneuralnetworktransferlearning |