Skip to content
2000
Volume 21, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format text download EPUB
file format pdf download PDF
side by side viewer icon HTML

Abstract

Introduction

Driven by environmental pollution and the rise in infectious diseases, the increasing prevalence of lung conditions demands advancements in diagnostic techniques.

Materials and Methods

This study explores the use of various features, such as spectrograms, chromograms, and Mel Frequency Cepstral Coefficients (MFCC), to extract crucial information from auscultation recordings. It addresses challenges through filter-based audio enhancement methods. The primary goal is to improve disease detection accuracy by leveraging convolutional neural networks (CNNs) for feature extraction and dense neural networks for classification.

Results

While deep learning models like CNNs and Recurrent Neural Network (RNN) outperform traditional machine learning models such as Sequence Vector Machine, K-Nearest Neighbours (KNN) and random forest with accuracies ranging from 70% to 85%. The combination of CNN, RNN, and long short-term memory achieved an accuracy of 88%. By integrating MFCC, Chroma Short-Term Fourier Transform (STFT), and spectrogram features with a CNN-based classifier, the proposed multi-feature deep learning model achieved the highest accuracy of 92%, surpassing all other methods.

Discussion

The study effectively addresses key issues, including the overrepresentation of Chronic Obstructive Pulmonary Disease (COPD) samples over Lower Respiratory Tract Infections (LRTI) and Upper Respiratory Tract Infections (URTI) which hampers generalization across test audio samples.

Conclusion

The proposed methodology caters common challenges like background noise in recordings, and the limited and imbalanced nature of datasets. These findings pave the way for enhanced clinical applications, showcasing the transformative potential of multi-feature deep learning methods in the classification of pulmonary diseases.

© 2025 The Author(s). Published by Bentham Science Publishers.
This is an open access article published under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/legalcode
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056388107250710120917
2025-07-18
2025-09-20

  • From This Site

    /content/journals/cmir/10.2174/0115734056388107250710120917
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/cmir/21/1/CMIR-21-E15734056388107.html?itemId=/content/journals/cmir/10.2174/0115734056388107250710120917&mimeType=html&fmt=ahah

References

  1. HarperL.J. KidambiP. KirincichJ.M. ThorntonJ.D. KhatriS.B. CulverD.A. Health disparities.Chest2023164117918910.1016/j.chest.2023.02.033
     [Google Scholar]
  2. ReychlerG. PirauxE. BeaumontM. CatyG. LiistroG. Telerehabilitation as a form of pulmonary rehabilitation in chronic lung disease: A systematic review.Healthcare2022109179510.3390/healthcare10091795
     [Google Scholar]
  3. DouilletD. ChouihedT. BertolettiL. RoyP-M. Pulmonary embolism and respiratory deterioration in chronic cardiopulmonary disease: A narrative review.Diagnostics202313114110.3390/diagnostics13010141
     [Google Scholar]
  4. PoppW. ReeseL. ScottiE. Heated tobacco products and chronic obstructive pulmonary disease: A narrative review of peer-reviewed publications.Eur. Med. J.2023596810.33590/emj/10309781
     [Google Scholar]
  5. XinyueX. Physical activity and chronic obstructive pulmonary disease: A scoping review.BMC Pulm. Med.202210.1186/s12890‑022‑02099‑4S
     [Google Scholar]
  6. ZaidiS.Z.Y. AkramM.U. JameelA. AlghamdiN.S. Lung segmentation-based pulmonary disease classification using deep neural networks.IEEE Access2021912520212521410.1109/ACCESS.2021.3110904
     [Google Scholar]
  7. StafinskiT. NagaseF.I. AvdagovskaM. SticklandM.K. MenonD. Effectiveness of home-based pulmonary rehabilitation programs for patients with chronic obstructive pulmonary disease (COPD): Systematic review.BMC Health Serv. Res.202222155710.1186/s12913‑022‑07779‑9
     [Google Scholar]
  8. DawadikarA. Survey of techniques for pulmonary disease classification using deep learning.2022 IEEE 7th International conference for Convergence in Technology (I2CT)Mumbai, India, 07-09 April 2022, pp. 1-5.10.1109/I2CT54291.2022.9824879
     [Google Scholar]
  9. HaiderN.S. SinghB.K. PeriyasamyR. BeheraA.K. Respiratory sound based classification of chronic obstructive pulmonary disease: A risk stratification approach in machine learning paradigm.J. Med. Syst.201943825510.1007/s10916‑019‑1388‑031254141
     [Google Scholar]
  10. ShuvoS.B. AliS.N. SwapnilS.I. HasanT. BhuiyanM.I.H. A lightweight CNN model for detecting respiratory diseases from lung auscultation sounds using EMD-CWT-based hybrid scalogram.IEEE J. Biomed. Health Inform.20212572595260310.1109/JBHI.2020.304800633373309
     [Google Scholar]
  11. KidoS. HiranoY. HashimotoN. Detection and classification of lung abnormalities by use of convolutional neural network (CNN) and regions with CNN features (R-CNN.2018 International Workshop on Advanced Image Technology (IWAIT)Chiang Mai, Thailand, 07-09 January 2018, pp. 1-4.10.1109/IWAIT.2018.8369798
     [Google Scholar]
  12. PernaD. Convolutional neural networks learning from respiratory data.2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)Madrid, Spain, 03-06 December 2018, pp. 2109-2113.10.1109/BIBM.2018.8621273
     [Google Scholar]
  13. PernaD. TagarelliA. Deep auscultation: Predicting respiratory anomalies and diseases via recurrent neural networks.2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)Cordoba, Spain, 05-07 June 2019, pp. 50-55.10.1109/CBMS.2019.00020
     [Google Scholar]
  14. CaiL. LongT. DaiY. HuangY. Full dimensional dynamic 3D convolution and point cloud in pulmonary nodule detection.J. Adv. Res.202410.1109/ACCESS.2020.2976432
     [Google Scholar]
  15. ChiZ. LiY. ChenC. Deep convolutional neural network combined with concatenated spectrogram for environmental sound classification.2019 IEEE 7th International Conference on Computer Science and Network Technology (ICCSNT)Dalian, China, 19-20 October 2019, pp. 251-254.10.1109/ICCSNT47585.2019.8962462
     [Google Scholar]
  16. DecorsièreR. SøndergaardP. MacDonaldE. DauT. Inversion of auditory spectrograms, traditional spectrograms, and other envelope representations.IEEE/ACM Trans. Audio Speech Lang. Process.2014231110.1109/TASLP.2014.2367821
     [Google Scholar]
  17. TowhidM.S. RahmanM.M. Spectrogram segmentation for bird species classification based on temporal continuity.2017 20th International Conference of Computer and Information Technology (ICCIT)Dhaka, Bangladesh, 22-24 December 2017, pp. 1-4.201710.1109/ICCITECHN.2017.8281775
     [Google Scholar]
  18. LeuJ-G. GeengL-t. PuC.E. ShiauJ-B. Speaker verification based on comparing normalized spectrograms.2011 Carnahan Conference on Security TechnologyBarcelona, Spain, 2011, pp. 1-5.10.1109/CCST.2011.6095878
     [Google Scholar]
  19. TariqZ. ShahS.K. LeeY. Lung disease classification using deep convolutional neural network.2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)San Diego, CA, USA, 18-21 November 2019, pp. 732-735.10.1109/BIBM47256.2019.8983071
     [Google Scholar]
  20. ZakM KrzyżakA. Classification of lung diseases using deep learning models.Comput. Sci. – ICCS 202020201213962163410.1007/978‑3‑030‑50420‑5_47
     [Google Scholar]
  21. BharatiS. PodderP. Hybrid deep learning for detecting lung diseases from X-ray images.Inform. Med. Unlocked20202010039110.1016/j.imu.2020.100391
     [Google Scholar]
  22. KieuS.T.H. BadeA. HijaziM.H.A. KolivandH. A survey of deep learning for lung disease detection on medical images: State-of-the-art, taxonomy, issues and future directions.J. Imaging202061213110.3390/jimaging612013134460528
     [Google Scholar]
  23. MaYi XuXinzi YuQing ZhangYuhang LiYongfu ZhaoJian WangGuoxing A smart digital stethoscope for detecting respiratory disease using bi-resnet deep learning algorithm.2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)Nara, Japan, 17-19 October 2019, pp. 1-4.10.1109/BIOCAS.2019.8919021
     [Google Scholar]
  24. KaplanA. FrankC. MolnarF. Chronic obstructive pulmonary disease and asthma management in older patients.Can. Fam. Physician2021671075175210.46747/cfp.671075134649899
     [Google Scholar]
  25. DemirF. SengurA. BajajV. Convolutional neural networks based efficient approach for classification of lung diseases.Health Inf. Sci. Syst.202081410.1007/s13755‑019‑0091‑331915523
     [Google Scholar]
  26. SpathisD. VlamosP. Diagnosing asthma and chronic obstructive pulmonary disease with machine learning.Health Informatics J.201925381182710.1177/146045821772316928820010
     [Google Scholar]
  27. RahmanT. KhandakarA. KadirM.A. IslamK.R. IslamK.F. MazharR. HamidT. IslamM.T. KashemS. MahbubZ.B. AyariM.A. ChowdhuryM.E.H. Reliable tuberculosis detection using chest X-ray with deep learning, segmentation and visualization.IEEE Access2020819158619160110.1109/ACCESS.2020.3031384
     [Google Scholar]
  28. Al-antariM.A. HuaC.H. BangJ. LeeS. “Fast deep learning computer-aided diagnosis of COVID-19 based on digital chest x-ray images”.Appl. Intell.20215152890290710.1007/s10489‑020‑02076‑634764573
     [Google Scholar]
  29. MaJ. SongY. TianX. HuaY. ZhangR. WuJ. Survey on deep learning for pulmonary medical imaging.Front. Med.202014445046910.1007/s11684‑019‑0726‑431840200
     [Google Scholar]
  30. Diaz-EscobarJ. Ordóñez-GuillénN.E. Villarreal-ReyesS. Galaviz-MosquedaA. KoberV. Rivera-RodriguezR. Lozano RizkJ.E. Deep-learning based detection of COVID-19 using lung ultrasound imagery.PLoS One2021168e025588610.1371/journal.pone.025588634388187
     [Google Scholar]
  31. PernaD. TagarelliA. Deep auscultation: Predicting respiratory anomalies and diseases via recurrent neural networks.2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)Córdoba, June 2019, pp. 50-55.
     [Google Scholar]
  32. RoyS. MenapaceW. OeiS. LuijtenB. FiniE. SaltoriC. HuijbenI. ChennakeshavaN. MentoF. SentelliA. PeschieraE. TrevisanR. MaschiettoG. TorriE. InchingoloR. SmargiassiA. SoldatiG. RotaP. PasseriniA. van SlounR.J.G. RicciE. DemiL. Deep learning for classification and localization of COVID-19 markers in point-of-care lung ultrasound.IEEE Trans. Med. Imaging20203982676268710.1109/TMI.2020.299445932406829
     [Google Scholar]
  33. WangC.D. ChenN. HuangL. WangJ.R. ChenZ.Y. JiangY.M. HeY.Z. JiY.L. Impact of CYP1A1 polymorphisms on susceptibility to chronic obstructive pulmonary disease: A meta-analysis.BioMed Res. Int.2015201594295826425562
     [Google Scholar]
  34. KararM.E. HemdanE.E.D. ShoumanM.A. Cascaded deep learning classifiers for computer-aided diagnosis of COVID-19 and pneumonia diseases in X-ray scans.Complex Intell. Syst.20217123524710.1007/s40747‑020‑00199‑434777953
     [Google Scholar]
  35. AcharyaJ. BasuA. Deep neural network for respiratory sound classification in wearable devices enabled by patient specific model tuning.IEEE Trans. Biomed. Circuits Syst.2020143110.1109/TBCAS.2020.298117232191898
     [Google Scholar]
  36. RochaB.M. FilosD. MendesL. SerbesG. UlukayaS. KahyaY.P. JakovljevicN. TurukaloT.L. VogiatzisI.M. PerantoniE. KaimakamisE. NatsiavasP. OliveiraA. JácomeC. MarquesA. MaglaverasN. Pedro PaivaR. ChouvardaI. de CarvalhoP. An open access database for the evaluation of respiratory sound classification algorithms.Physiol. Meas.201940303500110.1088/1361‑6579/ab03ea30708353
     [Google Scholar]
  37. CaiL. LongT. DaiY. HuangY. Mask R-CNN-based detection and segmentation for pulmonary nodule 3D visualization diagnosis.IEEE Access20208444004440910.1109/ACCESS.2020.2976432
     [Google Scholar]
  38. KohJ.H. ChongL.C.Y. KohG.C.H. TyagiS. Telemedical interventions for chronic obstructive pulmonary disease management: Umbrella review.J. Med. Internet Res.202325e3318510.2196/33185
     [Google Scholar]
  39. BorateM.V. AdsulA. PurohitM.P. Analysis of lung disease prediction using machine learning algorithms.J. Adv. Res. Comput.2024124560
     [Google Scholar]
  40. AbdelhamidA. AkinniyiO. SalehG.A. An ensemble neural architecture for lung diseases prediction using chest X-rays.J. Comput. Syst.2024159811410.12785/ijcds/160174
     [Google Scholar]
  41. SharmaS. GuleriaK. Multiclass lung disease classification with ensembled CNN and LSTM modeling.AIP Conf. Proc.202432091060021-1060021-1010.1063/5.0229036
     [Google Scholar]
  42. KumarS. ShvetsovA.V. FuzzyGuard: A novel multimodal neuro-fuzzy framework for COPD early diagnosis.IEEE Internet Things J.202418
     [Google Scholar]
  43. ShahS.T.H. ShahS.A.H. KhanI.I. Data-driven classification and explainable-AI in the field of lung imaging.Front. Big Data20247113
     [Google Scholar]
  44. PandeyK.M. BaloniD. Ensemble explainable artificial intelligence model for COVID-19 detection using chest X-ray images.2024 1st International Conference on Advanced Computing and Emerging Technologies (ACET)Ghaziabad, India, 23-24 August 2024, pp. 1-6.10.1109/ACET61898.2024.10730093
     [Google Scholar]
  45. KhanM.A. ShaukatA. MustansarZ. Segmented 3D lung cube dataset and dual-model framework for COVID-19 severity prediction.IEEE Access202412112
     [Google Scholar]
  46. MuellerA.N. MillerH.A. TaylorM.J. Identification of idiopathic pulmonary fibrosis and prediction of disease severity via machine learning analysis of comprehensive metabolic panel and complete blood count.Lung2024202431910.1007/s00408‑024‑00673‑7
     [Google Scholar]
  47. MaashiM. AlahmariS. ArasiM.A. Towards laryngeal cancer diagnosis using dandelion optimizer algorithm with ensemble learning on biomedical throat region images.Sci. Rep.2024142115
     [Google Scholar]
  48. ParamasivanP. RajestS.S. ChinnusamyK. Advancements in clinical medicine using deep learning and feature extraction for COVID-19 detection.Advancements in Clinical MedicineIGI Global202498114
     [Google Scholar]
  49. FraiwanM. FraiwanL. KhassawnehB. IbnianA. A dataset of lung sounds recorded from the chest wall using an electronic stethoscope.Mendeley Data202110.17632/jwyy9np4gv.3
     [Google Scholar]
  50. TodaR. TeramotoA. KondoM. ImaizumiK. SaitoK. FujitaH. Lung cancer CT image generation from a free-form sketch using style-based pix2pix for data augmentation.Sci. Rep.20221211286710.1038/s41598‑022‑16861‑535896575
     [Google Scholar]
  51. AbdulahiA.T. OgundokunR.O. AdenikeA.R. ShahM.A. AhmedY.K. PulmoNet: A novel deep learning based pulmonary diseases detection model.BMC Med. Imaging20242415110.1186/s12880‑024‑01227‑238418987
     [Google Scholar]
  52. SikderJ. DattaN. TripuraD. A deep learning approach for recognizing covid-19 from chest X-ray using modified CNN-BiLSTM with M-SVM.2022 International Conference on Electrical, Computer and Energy Technologies (ICECET)Prague, Czech Republic, 2022, pp. 1-6.10.1109/ICECET55527.2022.9872776
     [Google Scholar]
  53. WedisingheH. FernandoT.G.I. Explainable AI for early lung cancer detection: A path to confidence.2024 4th International Conference on Advanced Research in Computing (ICARC)Belihuloya, Sri Lanka, 2024, pp. 13-18.10.1109/ICARC61713.2024.10499787
     [Google Scholar]
  54. KhanA.A. MahendranR.K. PerumalK. FaheemM. Dual-3DM 3 AD: Mixed transformer based semantic segmentation and triplet pre-processing for early multi-class Alzheimer’s diagnosis.IEEE Trans. Neural Syst. Rehabil. Eng.20243269670710.1109/TNSRE.2024.335772338261494
     [Google Scholar]
  55. KujurA. RazaZ. KhanA.A. WechtaisongC. Data complexity based evaluation of the model dependence of brain MRI images for classification of brain tumor and Alzheimer’s disease.IEEE Access20221011211711213310.1109/ACCESS.2022.3216393
     [Google Scholar]
  56. AlhussenA. Anul HaqM. Ahmad KhanA. MahendranR.K. KadryS. XAI-RACapsNet: Relevance aware capsule network-based breast cancer detection using mammography images via explainability O-net ROI segmentation.Expert Syst. Appl.202526112546110.1016/j.eswa.2024.125461
     [Google Scholar]
  57. KhanA.A. MadendranR.K. ThirunavukkarasuU. FaheemM. D 2 PAM : Epileptic seizures prediction using adversarial deep dual patch attention mechanism.CAAI Trans. Intell. Technol.20238375576910.1049/cit2.12261
     [Google Scholar]
  58. PerumalK. MahendranR.K. Ahmad KhanA. KadryS. Tri‐M2MT: Multi‐modalities based effective acute bilirubin encephalopathy diagnosis through multi‐transformer using neonatal Magnetic Resonance Imaging.CAAI Trans. Intell. Technol.2025cit2.1240910.1049/cit2.12409
     [Google Scholar]
  59. SinghA.P. NigamA. KumarV. An analysis of deep learning algorithms for detection of pulmonary illness.2025 2nd International Conference on Computational Intelligence, Communication Technology and Networking (CICTN)Ghaziabad, India, 2025, pp. 349-354.10.1109/CICTN64563.2025.10932572
     [Google Scholar]
  60. Pal SinghA. KumarV. KumarN. Pneumonia detection based on image analysis using machine learning.2025 2nd International Conference on Computational Intelligence, Communication Technology and Networking (CICTN)Ghaziabad, India, 2025, pp. 288-292.10.1109/CICTN64563.2025.10932571
     [Google Scholar]
  61. YadavV. ShrivastavaS. SinghA.P. Enhanced pneumonia detection using deep learning techniques on chest X-rays.2024 2nd International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT)Faridabad, India, 2024, pp. 923-929.10.1109/ICAICCIT64383.2024.10912391
     [Google Scholar]
  62. DawadikarA. SrivastavaA. ShelarN. GaikwadG. PawarA. Three feature based ensemble deep learning model for pulmonary disease classification.IRJET2023102696702
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056388107250710120917
Loading
Evaluation of Deep Learning Methods for Pulmonary Disease Classification
Curr. Med. Imaging 21, E15734056388107 (2025); https://doi.org/10.2174/0115734056388107250710120917
/content/journals/cmir/10.2174/0115734056388107250710120917
/content/journals/cmir/10.2174/0115734056388107250710120917
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Chromagram; CNN; Deep Learning; MFCC; Pulmonary Diseases; Spectrogram

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test