Cross-Domain Transfer Learning for PCG Diagnosis Algorithm

• Published in: Biosensors (Basel) Vol. 11; no. 4; p. 127
• Main Authors: Tseng, Kuo-Kun, Wang, Chao, Huang, Yu-Feng, Chen, Guan-Rong, Yung, Kai-Leung, Ip, Wai-Hung
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 20.04.2021; MDPI
• Subjects: Accuracy; Algorithms; biosignal diagnosis; Cardiovascular diseases; Classification; Deep learning; Design; Diagnostic systems; Disease; Heart; Machine learning; Medical instruments; Methods; Neural networks; Noise; phonocardiogram; Segmentation; Sound; Support vector machines; Transfer learning; Wavelet transforms; transfer learning; biosignal diagnosis; phonocardiogram
• ISSN: 2079-6374; 2079-6374
• DOI: 10.3390/bios11040127

Cardiechema is a way to reflect cardiovascular disease where the doctor uses a stethoscope to help determine the heart condition with a sound map. In this paper, phonocardiogram (PCG) is used as a diagnostic signal, and a deep learning diagnostic framework is proposed. By improving the architecture and modules, a new transfer learning and boosting architecture is mainly employed. In addition, a segmentation method is designed to improve on the existing signal segmentation methods, such as R wave to R wave interval segmentation and fixed segmentation. For the evaluation, the final diagnostic architecture achieved a sustainable performance with a public PCG database.