Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

Advertisement

SpringerLink
Log in

A deep CNN-based acoustic model for the identification of lung diseases utilizing extracted MFCC features from respiratory sounds

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Machine learning algorithms have recently been increasingly used in medical data, particularly in healthcare areas where image processing techniques have played a crucial role. This study aims to utilize artificial intelligence (AI) techniques to forecast respiratory diseases by implementing a deep convolutional neural network (CNN) structure. The study employs an extensive dataset, specifically the Public Breathing Sound Database, which includes breathing sounds from 126 individuals with six different respiratory disorders. Furthermore, the main aim of this study is to tackle the difficulties related to the precise detection of lung disorders by creating a strong and effective model. The study examines the intricacies of pre-processing audio data, augmenting it, and extracting information from it. The primary focus is the utilization of Mel-frequency cepstral coefficients (MFCC) to identify significant characteristics of respiratory sounds. The suggested methodology utilizes a deep CNN structure to analyze retrieved characteristics and accurately identify diseases by detecting patterns and correlations. Moreover, the outcomes demonstrate a significant improvement in the precision of the model following the implementation of data balancing and augmentation strategies. The created model obtains a remarkable accuracy of 97.4% on the validation dataset, showcasing its effectiveness in training. Furthermore, it maintains a high accuracy of 95.1% on the independent test dataset. This research adds to the expanding collection of studies at the crossroads of AI and healthcare and shows great potential for promptly and precisely detecting respiratory disorders using acoustic signals. The results highlight the capacity of deep learning methods to transform diagnostic procedures in respiratory healthcare fundamentally.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

Data availability

The dataset used in this study can be found at “https://www.kaggle.com/vbookshelf/respiratory-sound-database”.

Abbreviations

AI:

Artificial Intelligence

ML:

Machine Learning

MFCC:

Mel-frequency cepstral coefficients

PD:

Parkinson's syndrome

SVM:

Support Vector Machine

Grad-CAM:

Gradient-weighted class activation mapping

BiGRU:

Bidirectional GRU

URTI:

Upper Respiratory Tract Infection

ReLU:

Rectified Linear Unit

FFT:

Fast Fourier transform

FP/ FN:

False Positive/ False Negative

ROC:

Receiver Operating Characteristic

CNN:

Convolutional Neural Network

DL:

Deep Learning

COPD:

Chronic Obstructive Pulmonary Disease

ABG:

Arterial Blood Gas test

RSD:

Respiratory Sound dataset

GRU:

Gated Recurrent Unit

TCN:

Gated temporal convolution layer

LRTI:

Lower Respiratory Tract Infection

FC:

Fully Connected

TP/ TN :

True Positive/ True Negative

CPU:

Central Processing Unit

References

  1. Ulukaya S, Sarıca AA, Erdem O, Karaali A (2023) MSCCov19Net: multi-branch deep learning model for COVID-19 detection from cough sounds. Med Biol Eng Comput 61(7):1619–1629. https://doi.org/10.1007/s11517-023-02803-4

    Article  Google Scholar 

  2. Mashika M, van der Haar D (2023) Mel frequency Cepstral coefficients and Support Vector machines for Cough Detection pp 250–259.https://doi.org/10.1007/978-3-031-35748-0_18

  3. Nayak SS, Darji AD, Shah PK (2023) Machine learning approach for detecting Covid-19 from speech signal using Mel frequency magnitude coefficient. Signal Image Video Process 17(6):3155–3162. https://doi.org/10.1007/s11760-023-02537-8

    Article  Google Scholar 

  4. Garcia-Mendez JP et al (2023) Machine learning for automated classification of abnormal lung sounds obtained from public databases: a systematic review. Bioengineering 10(10):1155. https://doi.org/10.3390/bioengineering10101155

    Article  Google Scholar 

  5. Issahaku FY, Liu X, Lu K, Fang X, Danwana SB, Asimeng E (2024) Multimodal deep learning model for Covid-19 detection. Biomed Signal Process Control 91:105906. https://doi.org/10.1016/j.bspc.2023.105906

    Article  Google Scholar 

  6. Prajapati SK, Choudhary TS, Mishra S (2023) Early detection of lung disease using multi-class classifiers. In: IEEE 4th Annual Flagship India Council International Subsections Conference (INDISCON), IEEE, pp 01–06.https://doi.org/10.1109/INDISCON58499.2023.10270105

  7. Lal KN (2023) A lung sound recognition model to diagnoses the respiratory diseases by using transfer learning. Multimed Tools Appl 82(23):36615–36631. https://doi.org/10.1007/s11042-023-14727-0

    Article  Google Scholar 

  8. Shivaanivarsha N, Sriram A, Saravaanan S, Rajesh V (2023) Respiratory sound analysis for lung disease diagnosis. In: International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE), IEEE, pp 1–4. https://doi.org/10.1109/AIKIIE60097.2023.10390099

  9. Dubey R, Bodade RM, Dubey D (2023) Efficient classification of the adventitious sounds of the lung through a combination of SVM-LSTM-Bayesian optimization algorithm with features based on wavelet bi-phase and bi-spectrum. Res Biomed Eng 39(2):349–363. https://doi.org/10.1007/s42600-023-00270-2

    Article  Google Scholar 

  10. Ge B, Yang H, Ma P, Guo T, Pan J, Wang W (2023) Detection of pulmonary hypertension associated with congenital heart disease based on time-frequency domain and deep learning features. Biomed Signal Process Control 81:104316. https://doi.org/10.1016/j.bspc.2022.104316

    Article  Google Scholar 

  11. Cinyol F, Baysal U, Köksal D, Babaoğlu E, Ulaşlı SS (2023) Incorporating support vector machine to the classification of respiratory sounds by convolutional neural network. Biomed Signal Process Control 79:104093. https://doi.org/10.1016/j.bspc.2022.104093

    Article  Google Scholar 

  12. Zakaria N, Sundaraj K (2023) VGG16-based deep learning architectures for classification of lung sounds into normal, crackles, and wheezes using gammatonegrams. In: 2023 International Conference on Information Technology (ICIT), IEEE, pp 83–88. https://doi.org/10.1109/ICIT58056.2023.10225790

  13. Mridha K, Sarkar S, Kumar D (2021) Respiratory disease classification by CNN using MFCC. In: 2021 IEEE 6th International Conference on Computing, Communication and Automation (ICCCA), IEEE, pp 517–523. https://doi.org/10.1109/ICCCA52192.2021.9666346

  14. Shuvo SB, Ali SN, Swapnil SI, Hasan T, Bhuiyan MIH (2021) A lightweight CNN model for detecting respiratory diseases from lung auscultation sounds using EMD-CWT-Based hybrid scalogram. IEEE J Biomed Health Inform 25(7):2595–2603. https://doi.org/10.1109/JBHI.2020.3048006

    Article  Google Scholar 

  15. Deeven VR, Kumar VN, Padma Sai Y, Akshitha N, Kaivalya M (2023) Pulmonary sound analysis with deep learning for efficient respiratory disease categorization. In Second International Conference on Emerging Trends in Engineering (ICETE 2023). Atlantis Press,  pp 68–78

  16. Tariq Z, Shah SK, Lee Y (2022) Feature-based Fusion using CNN for Lung and Heart Sound classification. Sensors 22(4):1521. https://doi.org/10.3390/s22041521

    Article  Google Scholar 

  17. Zulfiqar R, Majeed F, Irfan R, Rauf HT, Benkhelifa E, Belkacem AN (2021) Abnormal respiratory sounds classification using deep CNN through artificial noise addition. Front Med (Lausanne) 8. https://doi.org/10.3389/fmed.2021.714811

  18. Balasubramanian S, Rajadurai P (2023) Machine learning-based classification of pulmonary diseases through real-time lung sounds. Int J Eng Technol Innov 14(1):85–102. https://doi.org/10.46604/ijeti.2023.12294

    Article  Google Scholar 

  19. Sadi TM, Hassan R (2020) Development of classification methods for wheeze and crackle using mel frequency cepstral coefficient (MFCC): a deep learning approach. Int J Percept Cognit Comput 6(2):107–114. https://doi.org/10.31436/ijpcc.v6i2.166

  20. Roy A, Satija U (2023) RDLINet: a novel lightweight inception network for respiratory disease classification using lung sounds. IEEE Trans Instrum Meas 72:1–13. https://doi.org/10.1109/TIM.2023.3292953

    Article  Google Scholar 

  21. Alqudah AM, Qazan S, Obeidat YM (2022) Deep learning models for detecting respiratory pathologies from raw lung auscultation sounds. Soft Comput 26(24):13405–13429. https://doi.org/10.1007/s00500-022-07499-6

    Article  Google Scholar 

  22. Fraiwan M, Fraiwan L, Alkhodari M, Hassanin O (2022) Recognition of pulmonary diseases from lung sounds using convolutional neural networks and long short-term memory. J Ambient Intell Humaniz Comput 13(10):4759–4771. https://doi.org/10.1007/s12652-021-03184-y

    Article  Google Scholar 

  23. Baghel N, Nangia V, Dutta MK (2021) ALSD-Net: Automatic lung sounds diagnosis network from pulmonary signals. Neural Comput Appl 33(24):17103–17118. https://doi.org/10.1007/s00521-021-06302-1

    Article  Google Scholar 

  24. Kim Y, Camacho D, Choi C (2024) Real-time multi-class classification of respiratory diseases through dimensional data combinations. Cognit Comput 16(2):776–787. https://doi.org/10.1007/s12559-023-10228-2

    Article  Google Scholar 

  25. Xia T, Han J, Mascolo C (2022) Exploring machine learning for audio-based respiratory condition screening: A concise review of databases, methods, and open issues. Exp Biol Med 247(22):2053–2061. https://doi.org/10.1177/15353702221115428

    Article  Google Scholar 

  26. Alice RS, Wendling L, Santosh K (2023) 2D respiratory sound analysis to detect lung abnormalities. 46–58. https://doi.org/10.1007/978-3-031-23599-3_5

  27. Huang D-M, Huang J, Qiao K, Zhong N-S, Lu H-Z, Wang W-J (2023) Deep learning-based lung sound analysis for intelligent stethoscope. Mil Med Res 10(1):44. https://doi.org/10.1186/s40779-023-00479-3

    Article  Google Scholar 

  28. Kranthi Kumar L, Alphonse PJA (2022) COVID-19: respiratory disease diagnosis with regularized deep convolutional neural network using human respiratory sounds. Eur Phys J Spec Top 231(18–20):3673–3696. https://doi.org/10.1140/epjs/s11734-022-00649-9

    Article  Google Scholar 

  29. Sonali CS, Kiran J, Chinmayi BS, Suma KV, Easa M (2023) Transformer-based network for Accurate classification of lung auscultation sounds. Crit Rev Biomed Eng 51(6):1–16. https://doi.org/10.1615/CritRevBiomedEng.2023048981

    Article  Google Scholar 

  30. Zhang P, Swaminathan A, Uddin AA (2023) Pulmonary disease detection and classification in patient respiratory audio files using long short-term memory neural networks. Front Med (Lausanne) 10. https://doi.org/10.3389/fmed.2023.1269784

  31. Alqudaihi KS et al (2021) Cough sound detection and diagnosis using artificial intelligence techniques: challenges and opportunities. IEEE Access 9:102327–102344. https://doi.org/10.1109/ACCESS.2021.3097559

    Article  Google Scholar 

  32. Dar JA, Srivastava KK, Mishra A (2023) Lung anomaly detection from respiratory sound database (sound signals). Comput Biol Med 164:107311. https://doi.org/10.1016/j.compbiomed.2023.107311

    Article  Google Scholar 

  33. Choi Y, Lee H (2023) Interpretation of lung disease classification with light attention connected module. Biomed Signal Process Control 84:104695. https://doi.org/10.1016/j.bspc.2023.104695

    Article  Google Scholar 

  34. Basu V, Rana S (2020) Respiratory diseases recognition through respiratory sound with the help of deep neural network. In: 2020 4th International Conference on Computational Intelligence and Networks (CINE), IEEE, pp 1–6. https://doi.org/10.1109/CINE48825.2020.234388

  35. Lo Giudice M, Mammone N, Ieracitano C, Aguglia U, Mandic D, Morabito FC (2022) Explainable Deep Learning Classification of Respiratory Sound for Telemedicine Applications. In International Conference on Applied Intelligence and Informatics. Cham: Springer Nature Switzerland, pp 391–403

  36. Nassif AB, Shahin I, Bader M, Hassan A, Werghi N (2022) COVID-19 detection systems using deep-learning algorithms based on speech and image data. Mathematics 10(4):564. https://doi.org/10.3390/math10040564

    Article  Google Scholar 

  37. Saeed T, Ijaz A, Sadiq I, Qureshi HN, Rizwan A, Imran A (2024) An AI-Enabled bias-free respiratory disease diagnosis model using cough audio. Bioengineering 11(1):55. https://doi.org/10.3390/bioengineering11010055

    Article  Google Scholar 

  38. Dey RK, Das AK (2023) Modified term frequency-inverse document frequency based deep hybrid framework for sentiment analysis. Multimed Tools Appl 82(21):32967–32990. https://doi.org/10.1007/s11042-023-14653-1

    Article  Google Scholar 

  39. Dey RK, Das AK (2022) A simple strategy for handling ‘NOT’ can improve the performance of sentiment analysis pp 255–267. https://doi.org/10.1007/978-981-19-3089-8_25

Download references

Funding

This research was funded by the Deanship of Scientific Research at Princess Nourah bint Abdulrahman University, through the Research Funding Program, Grant No. (FRP-1444-1)

Author information

Authors and Affiliations

  1. Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O.Box 84428, Riyadh, 11671, Saudi Arabia

    Norah Saleh Alghamdi & Hanen Karamti

  2. Department of Computer Science, College of Computer and Information Sciences, King Saud University, P.O. Box 57168, Riyadh, 21574, Saudi Arabia

    Mohammed Zakariah

Authors
  1. Norah Saleh Alghamdi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohammed Zakariah
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hanen Karamti
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Norah Saleh Alghamdi.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interest regarding the publication of this paper.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Alghamdi, N.S., Zakariah, M. & Karamti, H. A deep CNN-based acoustic model for the identification of lung diseases utilizing extracted MFCC features from respiratory sounds. Multimed Tools Appl 83, 82871–82903 (2024). https://doi.org/10.1007/s11042-024-18703-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-024-18703-0

Keywords

Search

Navigation