Heartbeat murmurs detection in phonocardiogram recordings via transfer learning
Heart murmurs are abnormal heartbeat patterns that could be indicative of a serious heart condition, which can only be detected by trained specialists with the use of a stethoscope. However, it is occasionally the case that those specialists are not available, resulting in the need for a machine-aut...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016822002940 |
| _version_ | 1797978754575761408 |
|---|---|
| author | Omair Rashed Abdulwareth Almanifi Ahmad Fakhri Ab Nasir Mohd Azraai Mohd Razman Rabiu Muazu Musa Anwar P.P. Abdul Majeed |
| author_facet | Omair Rashed Abdulwareth Almanifi Ahmad Fakhri Ab Nasir Mohd Azraai Mohd Razman Rabiu Muazu Musa Anwar P.P. Abdul Majeed |
| author_sort | Omair Rashed Abdulwareth Almanifi |
| collection | DOAJ |
| description | Heart murmurs are abnormal heartbeat patterns that could be indicative of a serious heart condition, which can only be detected by trained specialists with the use of a stethoscope. However, it is occasionally the case that those specialists are not available, resulting in the need for a machine-automated system for murmur detection. Many methods might be used to produce such a system, one of which is the utilization of transfer learning. A recent machine learning method that saw popularity due to the little time it needs for training and the boosted accuracy it produces. This paper aims at testing the performance of transfer learning when detecting murmurs of the heart, by evaluating three transfer learning models, namely, VGG16, VGG19, and ResNet50, trained on a database of phonocardiogram (PCG) heartbeat recordings, i.e., PASCAL CHSC database. The data is cleansed, processed, and converted into images using two signal representation methods; Spectrograms and Mel Frequency Cepstral Coefficients (MFCCs). The paper compares the results of each model, using metrics of accuracy and loss, where the use of Spectrograms proved to yield the best results with 83.95%, 83.95%, and 87.65%, classification accuracy for VGG16, VGG19, and ResNet50, respectively. Based on the findings of the paper, it is evident that the Spectrogram-ResNet50 transfer learning pipeline could further facilitate the detection of heart murmurs with less time spent on training. |
| first_indexed | 2024-04-11T05:29:05Z |
| format | Article |
| id | doaj.art-3f6fa468fa3b4dbf8605946e53ae06fb |
| institution | Directory Open Access Journal |
| issn | 1110-0168 |
| language | English |
| last_indexed | 2024-04-11T05:29:05Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj.art-3f6fa468fa3b4dbf8605946e53ae06fb2022-12-23T04:38:47ZengElsevierAlexandria Engineering Journal1110-01682022-12-0161121099511002Heartbeat murmurs detection in phonocardiogram recordings via transfer learningOmair Rashed Abdulwareth Almanifi0Ahmad Fakhri Ab Nasir1Mohd Azraai Mohd Razman2Rabiu Muazu Musa3Anwar P.P. Abdul Majeed4Innovative Manufacturing, Mechatronics and Sports Laboratory, Faculty of Manufacturing and Mechatronics Engineering Technology, Universiti Malaysia Pahang (UMP), 26600 Pekan, Pahang Darul Makmur, MalaysiaInnovative Manufacturing, Mechatronics and Sports Laboratory, Faculty of Manufacturing and Mechatronics Engineering Technology, Universiti Malaysia Pahang (UMP), 26600 Pekan, Pahang Darul Makmur, MalaysiaInnovative Manufacturing, Mechatronics and Sports Laboratory, Faculty of Manufacturing and Mechatronics Engineering Technology, Universiti Malaysia Pahang (UMP), 26600 Pekan, Pahang Darul Makmur, MalaysiaCentre for Fundamental and Liberal Education, Universiti Malaysia Terengganu (UMT), 21030 Kuala Nerus, Terengganu Darul Iman, MalaysiaInnovative Manufacturing, Mechatronics and Sports Laboratory, Faculty of Manufacturing and Mechatronics Engineering Technology, Universiti Malaysia Pahang (UMP), 26600 Pekan, Pahang Darul Makmur, Malaysia; School of Robotics, XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong-Liverpool University, Suzhou, 215123, P. R. China; EUREKA Robotics Centre, Cardiff School of Technologies, Cardiff Metropolitan University, CF5 2YB, Cardiff, UK; Corresponding author at: School of Robotics, XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong-Liverpool University. Suzhou. 215123. P. R. China.Heart murmurs are abnormal heartbeat patterns that could be indicative of a serious heart condition, which can only be detected by trained specialists with the use of a stethoscope. However, it is occasionally the case that those specialists are not available, resulting in the need for a machine-automated system for murmur detection. Many methods might be used to produce such a system, one of which is the utilization of transfer learning. A recent machine learning method that saw popularity due to the little time it needs for training and the boosted accuracy it produces. This paper aims at testing the performance of transfer learning when detecting murmurs of the heart, by evaluating three transfer learning models, namely, VGG16, VGG19, and ResNet50, trained on a database of phonocardiogram (PCG) heartbeat recordings, i.e., PASCAL CHSC database. The data is cleansed, processed, and converted into images using two signal representation methods; Spectrograms and Mel Frequency Cepstral Coefficients (MFCCs). The paper compares the results of each model, using metrics of accuracy and loss, where the use of Spectrograms proved to yield the best results with 83.95%, 83.95%, and 87.65%, classification accuracy for VGG16, VGG19, and ResNet50, respectively. Based on the findings of the paper, it is evident that the Spectrogram-ResNet50 transfer learning pipeline could further facilitate the detection of heart murmurs with less time spent on training.http://www.sciencedirect.com/science/article/pii/S1110016822002940Transfer learningConvolution neural networksPhonocardiogramSpectrogramsMel frequency cepstral coefficients |
| spellingShingle | Omair Rashed Abdulwareth Almanifi Ahmad Fakhri Ab Nasir Mohd Azraai Mohd Razman Rabiu Muazu Musa Anwar P.P. Abdul Majeed Heartbeat murmurs detection in phonocardiogram recordings via transfer learning Alexandria Engineering Journal Transfer learning Convolution neural networks Phonocardiogram Spectrograms Mel frequency cepstral coefficients |
| title | Heartbeat murmurs detection in phonocardiogram recordings via transfer learning |
| title_full | Heartbeat murmurs detection in phonocardiogram recordings via transfer learning |
| title_fullStr | Heartbeat murmurs detection in phonocardiogram recordings via transfer learning |
| title_full_unstemmed | Heartbeat murmurs detection in phonocardiogram recordings via transfer learning |
| title_short | Heartbeat murmurs detection in phonocardiogram recordings via transfer learning |
| title_sort | heartbeat murmurs detection in phonocardiogram recordings via transfer learning |
| topic | Transfer learning Convolution neural networks Phonocardiogram Spectrograms Mel frequency cepstral coefficients |
| url | http://www.sciencedirect.com/science/article/pii/S1110016822002940 |
| work_keys_str_mv | AT omairrashedabdulwarethalmanifi heartbeatmurmursdetectioninphonocardiogramrecordingsviatransferlearning AT ahmadfakhriabnasir heartbeatmurmursdetectioninphonocardiogramrecordingsviatransferlearning AT mohdazraaimohdrazman heartbeatmurmursdetectioninphonocardiogramrecordingsviatransferlearning AT rabiumuazumusa heartbeatmurmursdetectioninphonocardiogramrecordingsviatransferlearning AT anwarppabdulmajeed heartbeatmurmursdetectioninphonocardiogramrecordingsviatransferlearning |