Automated Lung Sound Classification Using a Hybrid CNN-LSTM Network and Focal Loss Function
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Respiratory diseases constitute one of the leading causes of death worldwide and directly affect the patient’s quality of life. Early diagnosis and patient monitoring, which conventionally include lung auscultation, are essential for the efficient management of respiratory diseases. Manual lung sound interpretation is a subjective and time-consuming process that requires high medical expertise. The capabilities that deep learning offers could be exploited in order that robust lung sound classification models can be designed. In this paper, we propose a novel hybrid neural model that implements the focal loss (FL) function to deal with training data imbalance. Features initially extracted from short-time Fourier transform (STFT) spectrograms via a convolutional neural network (CNN) are given as input to a long short-term memory (LSTM) network that memorizes the temporal dependencies between data and classifies four types of lung sounds, including normal, crackles, wheezes, and both crackles and wheezes. The model was trained and tested on the ICBHI 2017 Respiratory Sound Database and achieved state-of-the-art results using three different data splitting strategies—namely, sensitivity 47.37%, specificity 82.46%, score 64.92% and accuracy 73.69% for the official 60/40 split, sensitivity 52.78%, specificity 84.26%, score 68.52% and accuracy 76.39% using interpatient 10-fold cross validation, and sensitivity 60.29% and accuracy 74.57% using leave-one-out cross validation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Original approach for the localisation of objects in images
Vaillant, R. (1994) · IEE Proceedings - Vision, Image, and Signal Processing · doi:10.1049/ip-vis:19941301 · Cited by 280
Research works printed but not linked: 34
- Forum of International Respiratory Societies (2017). The Global Impact of Respiratory Disease—Second Edition, European Respiratory Society.
- Rocha, B.M., Pessoa, D., Marques, A., Carvalho, P., and Paiva, R.P. (2020). Automatic Classification of Adventitious Respiratory Sounds: A (Un)Solved Problem?. Sensors, 21. · DOI
- Ibarra, 2018, Lung and Heart Sounds Analysis: State-of-the-Art and Future Trends, Crit. Rev. Biomed. Eng., 46, 33, 10.1615/CritRevBiomedEng.2018025112 · DOI
- Watt, J., Borhani, R., and Katsaggelos, A.K. (2020). Machine Learning Refined: Foundations, Algorithms, and Applications, Cambridge University Press. [2nd ed.]. · DOI
- Pramono, R.X.A., Bowyer, S., and Rodriguez-Villegas, E. (2017). Automatic adventitious respiratory sound analysis: A systematic review. PLoS ONE, 12. · DOI · Paper page
- Rocha, 2019, An open access database for the evaluation of respiratory sound classification algorithms, Physiol. Meas., 40, 035001, 10.1088/1361-6579/ab03ea · doi:10.1088/1361-6579/ab03ea
- 2015, Two-level coarse-to-fine classification algorithm for asthma wheezing recognition in children’s respiratory sounds, Biomed. Signal Process. Control, 21, 105, 10.1016/j.bspc.2015.05.002 · doi:10.1016/j.bspc.2015.05.002
- Matsutake, S., Yamashita, M., and Matsunaga, S. (September, January 31). Abnormal-respiration detection by considering correlation of observation of adventitious sounds. Proceedings of the 23rd European Signal Processing Conference (EUSIPCO), Nice, France.
- Sen, 2015, A Comparison of SVM and GMM-Based Classifier Configurations for Diagnostic Classification of Pulmonary Sounds, IEEE Trans. Biomed. Eng., 62, 1768, 10.1109/TBME.2015.2403616 · doi:10.1109/tbme.2015.2403616
- Mendes, L., Vogiatzis, I.M., Perantoni, E., Kaimakamis, E., Chouvarda, I., Maglaveras, N., Tsara, V., Teixeira, C., Carvalho, P., and Henriques, J. (2015, January 25–29). Detection of wheezes using their signature in the spectrogram space and musical features. Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy. · DOI
- Bokov, 2016, Wheezing recognition algorithm using recordings of respiratory sounds at the mouth in a pediatric population, Comput. Biol. Med., 70, 40, 10.1016/j.compbiomed.2016.01.002 · DOI
- Chamberlain, D., Kodgule, R., Ganelin, D., Miglani, V., and Fletcher, R.R. (2016, January 16–20). Application of semi-supervised deep learning to lung sound analysis. Proceedings of the 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA. · DOI
- Sengupta, 2016, Lung sound classification using cepstral-based statistical features, Comput. Biol. Med., 75, 118, 10.1016/j.compbiomed.2016.05.013 · DOI · Paper page
- Serbes, G., Ulukaya, S., and Kahya, Y.P. (2017). An Automated Lung Sound Preprocessing and Classification System Based OnSpectral Analysis Methods. International Conference on Biomedical and Health Informatics, Springer. · doi:10.1007/978-981-10-7419-6_8
- Jakovljević, N., and Lončar-Turukalo, T. (2017). Hidden Markov Model Based Respiratory Sound Classification. Precision Medicine Powered by PHealth and Connected Health, Springer. · doi:10.1007/978-981-10-7419-6_7
- Bardou, 2018, Lung sounds classification using convolutional neural networks, Artif. Intell. Med., 88, 58, 10.1016/j.artmed.2018.04.008 · DOI · Paper page
- Kochetov, K., Putin, E., Balashov, M., Filchenkov, A., and Shalyto, A. (2018, January 4–7). Noise Masking Recurrent Neural Network for Respiratory Sound Classification. Proceedings of the International Conference on Artificial Neural Networks 2018, Rhodes, Greece. · DOI
- Chambres, G., Hanna, P., and Desainte-Catherine, M. (2018, January 4–6). Automatic Detection of Patient with Respiratory Diseases Using Lung Sound Analysis. Proceedings of the International Conference on Content-Based Multimedia Indexing (CBMI), La Rochelle, France. · doi:10.1109/cbmi.2018.8516489
- Liu, R., Cai, S., Zhang, K., and Hu, N. (2019, January 21–24). Detection of Adventitious Respiratory Sounds based on Convolutional Neural Network. Proceedings of the International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS), Shanghai, China. · DOI
- Minami, K., Lu, H., Kim, H., Mabu, S., Hirano, Y., and Kido, S. (2019, January 15–18). Automatic Classification of Large-Scale Respiratory Sound Dataset Based on Convolutional Neural Network. Proceedings of the 2019 19th International Conference on Control, Automation and Systems (ICCAS), Jeju, Korea. · DOI
- Ma, Y., Xu, X., Yu, Q., Zhang, Y., Li, Y., Zhao, J., and Wang, G. (2019, January 17–19). LungBRN: A Smart Digital Stethoscope for Detecting Respiratory Disease Using bi-ResNet Deep Learning Algorithm. Proceedings of the IEEE Biomedical Circuits and Systems Conference (BioCAS), Nara, Japan. · DOI
- Demir, 2019, Convolutional neural networks based efficient approach for classification of lung diseases, Health Inf. Sci. Syst., 8, 1
- Acharya, 2020, Deep Neural Network for Respiratory Sound Classification in Wearable Devices Enabled by Patient Specific Model Tuning, IEEE Trans. Biomed. Circuits Syst., 14, 535
- Demir, 2020, Classification of Lung Sounds with CNN Model Using Parallel Pooling Structure, IEEE Access, 8, 105376, 10.1109/ACCESS.2020.3000111 · doi:10.1109/access.2020.3000111
- Saraiva, A., Santos, D., Francisco, A., Sousa, J., Ferreira, N., Soares, S., and Valente, A. (2020, January 24–26). Classification of Respiratory Sounds with Convolutional Neural Network. Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies, Valletta, Malta. · doi:10.5220/0008965101380144
- Gairola, S., Tom, F., Kwatra, N., and Jain, M. (2021, January 1–5). Respirenet: A deep neural network for accurately detecting abnormal lung sounds in limited data setting. Proceedings of the 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Mexico City, Mexico. · DOI
- Ma, Y., Xu, X., and Li, Y. (2020, January 25–29). LungRN+NL: An Improved Adventitious Lung Sound Classification Using Non-Local Block ResNet Neural Network with Mixup Data Augmentation. Proceedings of the Interspeech 2020, Shanghai, China. · doi:10.21437/interspeech.2020-2487
- Yang, Z., Liu, S., Song, M., Parada-Cabaleiro, E., and Schuller, B.W. (2020, January 25–29). Adventitious Respiratory Classification Using Attentive Residual Neural Networks. Proceedings of the Interspeech 2020, Shanghai, China. · DOI
- Pham, 2021, CNN-MoE Based Framework for Classification of Respiratory Anomalies and Lung Disease Detection, IEEE J. Biomed. Health Inform., 25, 2938, 10.1109/JBHI.2021.3064237 · DOI · Paper page
- Nguyen, T., and Pernkopf, F. (2021). Lung Sound Classification Using Co-tuning and Stochastic Normalization. arXiv. · DOI · Paper page
- Nguyen, T., and Pernkopf, F. (2020, January 20–24). Lung Sound Classification Using Snapshot Ensemble of Convolutional Neural Networks. Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada. · doi:10.1109/embc44109.2020.9176076
- Jiang, 2009, Time–frequency feature representation using energy concentration: An overview of recent advances, Digit. Signal Process., 19, 153, 10.1016/j.dsp.2007.12.004 · DOI · Paper page
- Lin, 2020, Focal Loss for Dense Object Detection, IEEE Trans. Pattern Anal. Mach. Intell., 42, 318, 10.1109/TPAMI.2018.2858826 · DOI · Paper page
- Petmezas, 2020, Automated Atrial Fibrillation Detection using a Hybrid CNN-LSTM Network on Imbalanced ECG Datasets, Biomed. Signal Process. Control, 63, 102194, 10.1016/j.bspc.2020.102194 · DOI · Paper page
Cited by
Cross-dataset video deepfake detection using Transformer and CNN architectures
Petmezas, G. (2026) · Machine Vision and Applications · doi:10.1007/s00138-026-01809-w · Cited by 6
Metadata
- Authors
- Petmezas, G., Cheimariotis, G.-A., Stefanopoulos, L., Rocha, B., Paiva, R. P., Katsaggelos, A. K., & Maglaveras, N.
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2022-02-06
- Volume
- 22
- Issue
- 3
- Pages
- 1232
- ISSN
- 1424-8220 (ISSN-L)
- OpenAlex
- W4210428539
- Cited by
- 200
- References
- 3
- FWCI
- 22.41
- Type
- journal article
- Language
- en
- Open access
- gold
- Funders
- European Commission (210510516)
- Fundação para a Ciência e Tecnologia (FCT) (SFRH/BD/135686/2018 and 2020.04927.BD)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Automated Lung Sound Classification Using a Hybrid CNN-LSTM Network and Focal Loss Function. https://app.cochat.ai/papers/10.3390/s22031232
- The paper
- Petmezas, G., Cheimariotis, G.-A., Stefanopoulos, L., Rocha, B., Paiva, R. P., Katsaggelos, A. K., & Maglaveras, N. (2022). Automated Lung Sound Classification Using a Hybrid CNN-LSTM Network and Focal Loss Function. Sensors. https://doi.org/10.3390/s22031232
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.