An open access database for the evaluation of respiratory sound classification algorithms

OBJECTIVE Over the last few decades, there has been significant interest in the automatic analysis of respiratory sounds. However, currently there are no publicly available large databases with which new algorithms can be evaluated and compared. Further developments in the field are dependent on the creation of such databases. APPROACH This paper describes a public respiratory sound database, which was compiled for an international competition, the first scientific challenge of the IFMBE's International Conference on Biomedical and Health Informatics. The database includes 920 recordings acquired from 126 participants and two sets of annotations. One set contains 6898 annotated respiratory cycles, some including crackles, wheezes, or a combination of both, and some with no adventitious respiratory sounds. In the other set, precise locations of 10 775 events of crackles and wheezes were annotated. MAIN RESULTS The best system that participated in the challenge achieved an average score of 52.5% with the respiratory cycle annotations and an average score of 91.2% with the event annotations. SIGNIFICANCE The creation and public release of this database will be useful to the research community and could bring attention to the respiratory sound classification problem.

[1]  Ivan W. Selesnick,et al.  Sparse signal representations using the tunable Q-factor wavelet transform , 2011, Optical Engineering + Applications.

[2]  E. Andrès,et al.  Analysis of Respiratory Sounds: State of the Art , 2008, Clinical medicine. Circulatory, respiratory and pulmonary medicine.

[3]  D. Scuse,et al.  A comparison of neural network models for wheeze detection , 1995, IEEE WESCANEX 95. Communications, Power, and Computing. Conference Proceedings.

[4]  J J Marini,et al.  The significance of wheezing in chronic airflow obstruction. , 1979, The American review of respiratory disease.

[5]  N. Jakovljević,et al.  Hidden Markov Model Based Respiratory Sound Classification , 2017, BHI 2017.

[6]  F. K. Lam,et al.  Crackle detection and classification based on matched wavelet analysis , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[7]  Cristina Jácome,et al.  Automatic Crackle Detection Algorithm Based on Fractal Dimension and Box Filtering , 2015, CENTERIS/ProjMAN/HCist.

[8]  Nabil Alshurafa,et al.  When generalized eating detection machine learning models fail in the field , 2017, UbiComp/ISWC Adjunct.

[9]  Mark J. F. Gales,et al.  The Application of Hidden Markov Models in Speech Recognition , 2007, Found. Trends Signal Process..

[10]  R. Murphy,et al.  Validation of an automatic crackle (rale) counter. , 1989, The American review of respiratory disease.

[11]  Xi Liu,et al.  Detection of adventitious lung sounds using entropy features and a 2-D threshold setting , 2015, 2015 10th International Conference on Information, Communications and Signal Processing (ICICS).

[12]  Ioanna Chouvarda,et al.  Α Respiratory Sound Database for the Development of Automated Classification , 2017, BHI 2017.

[13]  Leontios J. Hadjileontiadis,et al.  Wheeze detection based on time-frequency analysis of breath sounds , 2007, Comput. Biol. Medicine.

[14]  Mary Boudreau Conover,et al.  Understanding heart sounds and murmurs : with an introduction to lung sounds , 1984 .

[15]  J. Tielsch,et al.  Computerized lung sound analysis as diagnostic aid for the detection of abnormal lung sounds: a systematic review and meta-analysis. , 2011, Respiratory medicine.

[16]  F. Dalmasso,et al.  Definition of terms for applications of respiratory sounds , 2000 .

[17]  Cristina Jácome,et al.  Usability of Computerized Lung Auscultation–Sound Software (CLASS) for learning pulmonary auscultation , 2017, Medical & Biological Engineering & Computing.

[18]  Vivek Miglani,et al.  Application of semi-supervised deep learning to lung sound analysis , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[19]  Naoki Nakamura,et al.  Detection of patients considering observation frequency of continuous and discontinuous adventitious sounds in lung sounds , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[20]  Patrice Flaud,et al.  Wheezing recognition algorithm using recordings of respiratory sounds at the mouth in a pediatric population , 2016, Comput. Biol. Medicine.

[21]  Mohammed Bahoura,et al.  Pattern recognition methods applied to respiratory sounds classification into normal and wheeze classes , 2009, Comput. Biol. Medicine.

[22]  Richard M. Schwartz,et al.  Enhancement of speech corrupted by acoustic noise , 1979, ICASSP.

[23]  Ioanna Chouvarda,et al.  Detection of crackle events using a multi-feature approach , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[24]  Aintree Chest,et al.  Current methods used for computerized respiratory sound analysis , 2000 .

[25]  R. Loddenkemper,et al.  Respiratory health and disease in Europe: the new European Lung White Book , 2013, European Respiratory Journal.

[26]  Gorkem Serbes,et al.  An Automated Lung Sound Preprocessing and Classification System Based OnSpectral Analysis Methods , 2018 .

[27]  Y P Kahya,et al.  Comparison of AR-based algorithms for respiratory sounds classification. , 1994, Computers in biology and medicine.

[28]  Ivan W. Selesnick,et al.  Wavelet Transform With Tunable Q-Factor , 2011, IEEE Transactions on Signal Processing.

[29]  Steve S Kraman,et al.  The physiologic basis of spirometry. , 2009, Respiratory care.

[30]  Bor-Shing Lin,et al.  Automatic Wheezing Detection Using Speech Recognition Technique , 2016 .

[31]  P. Piirilä,et al.  Crackles: recording, analysis and clinical significance. , 1995, The European respiratory journal.

[32]  Hans Pasterkamp,et al.  Wheezes, crackles and rhonchi: simplifying description of lung sounds increases the agreement on their classification: a study of 12 physicians' classification of lung sounds from video recordings , 2016, BMJ Open Respiratory Research.

[33]  Robert L. Wilkins,et al.  Fundamentals of lung and heart sounds , 2015 .

[34]  Bruno Henrique Groenner Barbosa,et al.  Classification of lung sounds using higher-order statistics: A divide-and-conquer approach , 2016, Comput. Methods Programs Biomed..

[35]  Guilherme Campos,et al.  Respiratory Sound Annotation Software , 2018, HEALTHINF.

[36]  P. Alapat,et al.  Validation of Automatic Wheeze Detection in Patients with Obstructed Airways and in Healthy Subjects , 2008, The Journal of asthma : official journal of the Association for the Care of Asthma.

[37]  Cristina Jácome,et al.  Computerized Adventitious Respiratory Sounds as Outcome Measures for Respiratory Therapy: A Systematic Review , 2014, Respiratory Care.

[38]  Eric C. Larson,et al.  Pulmonary Monitoring Using Smartphones , 2017, Mobile Health - Sensors, Analytic Methods, and Applications.

[39]  A. R. Nath,et al.  Inspiratory crackles—early and late , 1974 .

[40]  José Antonio Fiz,et al.  Automatic Differentiation of Normal and Continuous Adventitious Respiratory Sounds Using Ensemble Empirical Mode Decomposition and Instantaneous Frequency , 2016, IEEE Journal of Biomedical and Health Informatics.

[41]  Ana Oliveira,et al.  Respiratory sounds in healthy people: a systematic review. , 2014, Respiratory medicine.

[42]  Stuart A. Bowyer,et al.  Automatic adventitious respiratory sound analysis: A systematic review , 2017, PloS one.

[43]  C. Carrington,et al.  Crackles (rales) in the interstitial pulmonary diseases. , 1978, Chest.

[44]  M. Sarkar,et al.  Auscultation of the respiratory system , 2015, Annals of thoracic medicine.

[45]  R. Baughman,et al.  Quantitation of wheezing in acute asthma. , 1984, Chest.

[46]  Nicos Maglaveras,et al.  Combining pervasive technologies and Cloud Computing for COPD and comorbidities management , 2014, 2014 4th International Conference on Wireless Mobile Communication and Healthcare - Transforming Healthcare Through Innovations in Mobile and Wireless Technologies (MOBIHEALTH).

[47]  R. Urquhart,et al.  The diagnostic value of pulmonary sounds: a preliminary study by computer-aided analysis. , 1981, Computers in biology and medicine.

[48]  Petri Toiviainen,et al.  MIR in Matlab (II): A Toolbox for Musical Feature Extraction from Audio , 2007, ISMIR.

[49]  Gorkem Serbes,et al.  Overcomplete discrete wavelet transform based respiratory sound discrimination with feature and decision level fusion , 2017, Biomed. Signal Process. Control..