Neonatal Bowel Sound Detection Using Convolutional Neural Network and Laplace Hidden Semi-Markov Model

Abdominal auscultation is a convenient, safe and inexpensive method to assess bowel conditions, which is essential in neonatal care. It helps early detection of neonatal bowel dysfunctions and allows timely intervention. This paper presents a neonatal bowel sound detection method to assist the auscultation. Specifically, a Convolutional Neural Network (CNN) is proposed to classify peristalsis and non-peristalsis sounds. The classification is then optimized using a Laplace Hidden Semi-Markov Model (HSMM). The proposed method is validated on abdominal sounds from 49 newborn infants admitted to our tertiary Neonatal Intensive Care Unit (NICU). The results show that the method can effectively detect bowel sounds with accuracy and area under curve (AUC) score being 89.81% and 83.96% respectively, outperforming 13 baseline methods. Furthermore, the proposed Laplace HSMM refinement strategy is proven capable to enhance other bowel sound detection models. The outcomes of this work have the potential to facilitate future telehealth applications for neonatal care.

[1]  Guy A. Dumont,et al.  Neonatal Heart and Lung Sound Quality Assessment for Robust Heart and Breathing Rate Estimation for Telehealth Applications , 2020, IEEE Journal of Biomedical and Health Informatics.

[2]  Mario Hlawitschka,et al.  Comparison of Artificial Neural Network Types for Infant Vocalization Classification , 2021, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[3]  Mohammad Belayet Hossain,et al.  Attention-based VGG-16 model for COVID-19 chest X-ray image classification , 2020, Applied Intelligence.

[4]  P. Losty,et al.  Necrotising enterocolitis–A 15‐year outcome report from a UK specialist centre , 2020, Acta paediatrica.

[5]  Luca Foschini,et al.  Deep learning models for electrocardiograms are susceptible to adversarial attack , 2020, Nature Medicine.

[6]  N. Badawi,et al.  Continuous Positive Airway Pressure Belly Syndrome: Challenges of a Changing Paradigm , 2020 .

[7]  Yu Ma,et al.  Robust sleep stage classification with single-channel EEG signals using multimodal decomposition and HMM-based refinement , 2019, Expert Syst. Appl..

[8]  Faezeh Marzbanrad,et al.  Digital stethoscopes in paediatric medicine , 2019, Acta paediatrica.

[9]  S. Rogerson,et al.  Neonatologist performed point‐of‐care bowel ultrasound: Is the time right? , 2018, Australasian journal of ultrasound in medicine.

[10]  Adam Osseiran,et al.  Advances in Acoustic Signal Processing Techniques for Enhanced Bowel Sound Analysis , 2019, IEEE Reviews in Biomedical Engineering.

[11]  Zhihua Wang,et al.  Bowel Sound Detection Based on MFCC Feature and LSTM Neural Network , 2018, 2018 IEEE Biomedical Circuits and Systems Conference (BioCAS).

[12]  Michael Wainberg,et al.  Deep learning in biomedicine , 2018, Nature Biotechnology.

[13]  Zhihua Wang,et al.  Bowel sound recognition using SVM classification in a wearable health monitoring system , 2018, Science China Information Sciences.

[14]  Zhihua Wang,et al.  Bowel sound based digestion state recognition using artificial neural network , 2015, 2015 IEEE Biomedical Circuits and Systems Conference (BioCAS).

[15]  Bor-Shyh Lin,et al.  Higher-Order-Statistics-Based Fractal Dimension for Noisy Bowel Sound Detection , 2015, IEEE Signal Processing Letters.

[16]  Amir Lahav,et al.  Questionable sound exposure outside of the womb: frequency analysis of environmental noise in the neonatal intensive care unit , 2015, Acta paediatrica.

[17]  Umit D. Ulusar,et al.  Recovery of gastrointestinal tract motility detection using Naive Bayesian and minimum statistics , 2014, Comput. Biol. Medicine.

[18]  Umit Deniz Ulusar,et al.  Real-time monitoring for recovery of gastrointestinal tract motility detection after abdominal surgery , 2013, 2013 7th International Conference on Application of Information and Communication Technologies.

[19]  Jasmine Dumas,et al.  Feasibility of an electronic stethoscope system for monitoring neonatal bowel sounds. , 2013, Connecticut medicine.

[20]  Bor-Shyh Lin,et al.  Enhancing Bowel Sounds by Using a Higher Order Statistics-Based Radial Basis Function Network , 2013, IEEE Journal of Biomedical and Health Informatics.

[21]  Gerhard Thonhauser,et al.  Improving time series classification using Hidden Markov Models , 2012, 2012 12th International Conference on Hybrid Intelligent Systems (HIS).

[22]  Chul-Gyu Song,et al.  Awareness system for bowel motility estimation based on artificial neural network of bowel sounds , 2012, 4th International Conference on Awareness Science and Technology.

[23]  Thaweesak Yingthawornsuk,et al.  Speech Recognition using MFCC , 2012 .

[24]  Keo-Sik Kim,et al.  Non-invasive algorithm for bowel motility estimation using a back-propagation neural network model of bowel sounds , 2011, Biomedical engineering online.

[25]  Keo-Sik Kim,et al.  Estimation algorithm of the bowel motility based on regression analysis of the jitter and shimmer of bowel sounds , 2011, Comput. Methods Programs Biomed..

[26]  Shunzheng Yu,et al.  Hidden semi-Markov models , 2010, Artif. Intell..

[27]  George Kalliris,et al.  Bowel-sound pattern analysis using wavelets and neural networks with application to long-term, unsupervised, gastrointestinal motility monitoring , 2008, Expert Syst. Appl..

[28]  R. Adrezin,et al.  Stethoscope for Monitoring Neonatal Abdominal Sounds , 2008 .

[29]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[30]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[31]  G. David Forney,et al.  The Viterbi Algorithm: A Personal History , 2005, ArXiv.

[32]  V. Louis-Dorr,et al.  Wavelet-based bowel sounds denoising, segmentation and characterization , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[33]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[34]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[35]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.