Automatic detection of the respiratory cycle from recorded, single-channel soundsfrom lungs

Listening to the sounds made by the lungs is a long-standing method that is still used to diagnose lungdiseases. Many studies have been conducted on the automatic recognition of recorded sounds from the lungs. However,in these studies, respiratory cycles, i.e. inhalations followed by exhalations, were either monitored manually or by usingmultichannel signals of the sounds made by the lungs. In order to recognize sounds made by the lungs automatically, onemust rst use these sounds to determine the respiratory cycles. Our previous study was the rst study presented in theliterature in which the boundaries of respiratory cycles were determined based on single-channel sounds from the lungs.However, this method was not successful when ambient noise occurred and interfered with the sounds from the lungs.In the present study, a new method has been developed in which important changes were made to reduce or negatethe effects of ambient noises. Our proposed new method includes a processing method that we developed to obtainrespiratory cycles as smooth, repetitive patterns. Then the dynamic time-warping algorithm was used to determine theboundaries of the respiratory cycles, based on the similarity of the patterns. This new method was used to detect theseven sounds that are commonly made by the lung. As a result, the limits of the respiratory cycles were obtained witha mean absolute error of 56.51 ms. In addition, the method we developed has the potential to determine the boundariesof the patterns in signals that contain repetitive data, such as the sounds made by the lungs in this study.

PDF

___

[1]Lakhe A, Sodhi I, Warrier J, Sinha V. Development of digital stethoscope for telemedicine. J Med Eng Technol2016; 40: 20-24.
[2]Aras S,Ozturk M, Gangal A. Endpoint detection of lung sounds for electronic auscultation. In: IEEE 2016International Conference on Telecommunications and Signal Processing; 27{29 June 2016; Vienna, Austria. NewYork, NY, USA: IEEE. pp. 405-408.
[3]Gurung A, Scrafford CG, Tielsch JM, Levine OS, Checkley W. Computerized lung sound analysis as diagnostic aidfor the detection of abnormal lung sounds: a systematic review and meta-analysis. Resp Med 2011; 105: 1396-1403.
[4]Mondal A, Bhattacharya P, Saha G. Detection of lungs' status using morphological complexities of respiratorysounds. Sci World J 2014; Article ID 182938.
[5]Huq S, Moussavi Z. Acoustic breath-phase detection using tracheal breath sounds. Med Biol Eng Comput 2012; 50:297-308.
[6]Tabata H, Hirayama M, Enseki M, Nukaga M, Hirai K, Furuya H, Mochizuki H. A novel method for detectingairway narrowing using breath sound spectrum analysis in children. Respir Investig 2016; 54: 20-28.
[7]Yahya O, Faezipour M. Automatic detection and classi cation of acoustic breathing cycles. In: IEEE 2014 Confer-ence of the American Society for Engineering Education; 3{5 April 2014; Bridgeport, CT, USA. New York, NY,USA: IEEE. pp. 1-5.
[8]Dabiri S, Shirazi MAM. Estimation of respiratory rate from photoplethysmogram signal of sleep apnea patients:A comparative study of different methods. In: IEEE 2015 International Conference on Telecommunications andSignal Processing; 9{11 July 2015; Prague, Czech Republic. New York, NY, USA: IEEE. p. 440-443.
[9]Anusha AR, Soodi AL, Kumar SP. Design of low-cost hardware for lung sound acquisition and determination ofinspiratory-expiratory phase using respiratory waveform. In: IEEE 2012 International Conference on ComputingCommunication and Networking Technologies; 26{28 July 2012; Coimbatore, India. New York, NY, USA: IEEE. p.1-5.21
[10]Moussavi ZK, Leopando MT, Pasterkamp H, Rempel G. Computerised acoustical respiratory phase detectionwithout air ow measurement. Med Biol Eng Comput 2000; 38: 198-203.
[11]Nam Y, Reyes BA, Chon KH. Estimation of respiratory rates using the built-in microphone of a smartphone orheadset. IEEE J Biomed Health 2015; 20: 1493-1501.
[12]Reyes BA, Reljin N, Kong Y, Nam Y, Ha S, Chon KH. Towards the development of a mobile phonopneumogram:automatic breath-phase classi cation using smartphones. Ann Biomed Eng 2016; 44: 2746-2759.
[13]Palaniappan R, Sundaraj K, Sundaraj S, Huliraj N, Revadi SS. A novel approach to detect respiratory phases frompulmonary acoustic signals using normalised power spectral density and fuzzy inference system. Clin Resp J 2016;10: 486-494.
[14]Alsmadi S, Kahya YP. Design of a DSP-based instrument for real-time classi cation of pulmonary sounds. ComputBiol Med 2008; 38: 53-61.
[15]Lozano M, Fiz JA, Jane R. Performance evaluation of the Hilbert{Huang transform for respiratory sound analysisand its application to continuous adventitious sound characterization. Signal Proc 2016; 120: 99-116.
[16]Cam SL, Collet C, Salzenstein F. Acoustical respiratory signal analysis and phase detection. IEEE 2008 InternationalConference on Acoustics, Speech and Signal Processing; 31 March{4 April 2008; Las Vegas, NV, USA. New York,NY, USA: IEEE. pp. 3629-3632.
[17]Garcia D. Robust smoothing of gridded data in one and higher dimensions with missing values. Comput Stat DataAn 2010; 54: 1167-1178.
[18]Rabiner L, Juang BH. Fundamentals of Speech Recognition. Upper Saddle River, NJ, USA: Prentice-Hall, 1993.
[19]Jin F, Sattar F, Goh D, Louis IM. A robust respiratory phase identi cation scheme based on a new mixing index.In: IEEE 2009 European Signal Processing Conference; 24{28 August 2009; Glasgow, UK. New York, NY, USA:IEEE, pp. 637-641.
[20]Yadollahi A, Moussavi ZM. A robust method for estimating respiratory ow using tracheal sounds entropy. IEEET Biomed Eng 2006; 53: 662-668.22