Fetal Heart Rate Estimation in Phonocardiograms Using Deep Learning and Digital Signal Processing

• Hugo Carvalho de Moraes UFAM
• Rafael C. Carvalho UFAM
• Juan G. Colonna Victoria University of Wellington / UFAM
• Eduardo Freire Nakamura UFAM

DOI: https://doi.org/10.5753/webmedia.2025.15316

Resumo

Fetal heart rate monitoring through phonocardiograms enables non-invasive assessment of fetal health, supporting the early detection of potential complications during pregnancy. However, accurate frequency estimation is hindered by various noise sources, such as maternal heart sounds and ambient interference. This study proposes a lightweight 1D-CNN regression model for fetal heart rate estimation, leveraging MFCC and Delta-MFCC coefficients extracted from audio segments. A simple but effective data augmentation technique was also employed to mitigate the scarcity of labeled data. Experiments conducted on the SUFHSDB dataset yielded a mean absolute error of 3.94±0.41 bpm. The results suggest that deep learning-based approaches, especially when combined with data augmentation, are promising alternatives for fetal heart rate estimation, potentially reducing reliance on traditional signal-processing pipelines.

Palavras-chave: Deep Learning Fetal Hearth Rate Digital Signal Processing

Referências

Zrar Kh. Abdul and Abdulbasit K. Al-Talabani. 2022. Mel Frequency Cepstral Coefficient and its Applications: A Review. IEEE Access 10 (2022), 122136–122158. DOI: 10.1109/ACCESS.2022.3223444

Mohanad Alkhodari, Murad Almadani, Samit Kumar Ghosh, and Ahsan H. Khandoker. 2023. Fhsu-Net: Deep Learning-Based Model for the Extraction of Fetal Heart Sounds in Abdominal Phonocardiography. In 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP). 1–6. DOI: 10.1109/MLSP55844.2023.10285907

Murad Almadani, Mohanad Alkhodari, Samit Ghosh, and Ahsan Khandoker. 2023. FHSU-NETR: Transformer-based Deep Learning Model for the Detection of Fetal Heart Sounds in Phonocardiography. DOI: 10.22489/CinC.2023.026

Vijay S. Chourasia, Anil Kumar Tiwari, and Ranjan Gangopadhyay. 2014. A novel approach for phonocardiographic signals processing to make possible fetal heart rate evaluations. Digital Signal Processing 30 (2014), 165–183. DOI: 10.1016/j.dsp.2014.03.009

Md Rashidul Hasan, Mustafa Jamil, MGRMS Rahman, et al. 2004. Speaker identification using mel frequency cepstral coefficients. variations 1, 4 (2004), 565–568.

S.G. Mallat. 1989. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence 11, 7 (1989), 674–693. DOI: 10.1109/34.192463

Radek Martinek, Jan Nedoma, Marcel Fajkus, Radana Kahankova, Jaromir Konecny, Petr Janku, Stanislav Kepak, Petr Bilik, and Homer Nazeran. 2017. A Phonocardiographic-Based Fiber-Optic Sensor and Adaptive Filtering System for Noninvasive Continuous Fetal Heart Rate Monitoring. Sensors (Basel) 17, 4 (Apr 2017), 890. DOI: 10.3390/s17040890 arXiv: [link] The authors declare no conflict of interest..

Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. LNCS 9351, 234–241. DOI: 10.1007/978-3-319-24574-4_28

Maryam Samieinasab and Reza Sameni. 2015. Fetal phonocardiogram extraction using single channel blind source separation. 2015 23rd Iranian Conference on Electrical Engineering (2015), 78–83. [link]

Annachiara Strazza, Agnese Sbrollini, Valeria Battista, Rita Ricci, Letizia Trillini, Ilaria Marcantoni, Micaela Morettini, Sandro Fioretti, and Laura Burattini. 2019. PCG-Delineator: an Efficient Algorithm for Automatic Heart Sounds Detection in Fetal Phonocardiography. DOI: 10.22489/CinC.2018.045

Annachiara Strazza, Agnese Sbrollini, Marica Olivastrelli, Agnese Piersanti, Selene Tomassini, Ilaria Marcantoni, Micaela Morettini, Sandro Fioretti, and Laura Burattini. 2019. PCG-Decompositor: A New Method for Fetal Phonocardiogram Filtering Based on Wavelet Transform Multi-level Decomposition. 47–53. DOI: 10.1007/978-3-030-31635-8_6

Selene Tomassini, Agnese Sbrollini, Annachiara Strazza, Reza Sameni, Ilaria Marcantoni, Micaela Morettini, and Laura Burattini. 2020. AdvFPCG-Delineator: Advanced delineator for fetal phonocardiography. Biomedical Signal Processing and Control 61 (2020), 102021. DOI: 10.1016/j.bspc.2020.102021

Radana Vilimkova Kahankova, Martina Mikolasova, Rene Jaros, Kateřina Barnová, Martina Ládrová, and Radek Martinek. 2022. A Review of Recent Advances and Future Developments in Fetal Phonocardiography. IEEE Reviews in Biomedical Engineering PP (06 2022), 1–1. DOI: 10.1109/RBME.2022.3179633

Frank Wilcoxon. 1945. Individual comparisons by ranking methods. Biometrics bulletin 1, 6 (1945), 80–83.

Pengjie Zhang, Shiwei Ye, Zhipei Huang, Dina Jiaerken, Shuxia Zhao, Lingyan Zhang, and Jiankang Wu. 2019. A Noninvasive Continuous Fetal Heart Rate Monitoring System for Mobile Healthcare Based on Fetal Phonocardiography. In Advances in Body Area Networks I, Giancarlo Fortino and Zhelong Wang (Eds.). Springer International Publishing, Cham, 191–204.

Bin Zhen, XihongWu, Zhimin Liu, and Huisheng Chi. 2001. On the Importance of Components of the MFCC in Speech and Speaker Recognition. Acta Scientiarum Naturalium-Universitatis Pekinensis 37, 3 (2001), 371–378.