Arafat ŞENTÜRK, Zehra KARAPINAR ŞENTÜRK, Enver KÜÇÜKKÜLAHLI, Abdullah Talha KABAKUŞ, Devrim AKGÜN

A transfer learning-based deep learning approach for automated COVID-19 diagnosis with audio data

The COVID-19 pandemic has caused millions of deaths and changed daily life globally. Countries have declared a half or full lockdown to prevent the spread of COVID-19. According to medical doctors, as many people as possible should be tested to identify their status, and corresponding actions then should be taken for COVID-19 positive cases. Despite the clear necessity of these medical tests, many countries are still struggling to acquire them. This fact clearly indicates the necessity of a large-scale, cheap, fast, and accurate alternative prescreening tool that can be used for the diagnosis of COVID-19 while waiting for the medical tests. To this end, a novel end-to-end transfer learning-based deep learning approach that uses only a given cough sound for the diagnosis of COVID-19 was proposed in this study. The proposed models employed various pretrained deep neural networks, namely, VGG19, ResNet50V2, DenseNet121, and MobileNet, via the transfer learning technique. Then, these models were evaluated on a gold standard dataset, namely, Cambridge data. According to the experimental result, the proposed model, which employed the MobileNet via the transfer learning technique, provided the best accuracy, 86.42%, and outperformed the state-of-the-art. Thus, the proposed model has the potential to provide automated COVID-19 diagnosis in an easily applicable and fast yet accurate way.

PDF

___

[1] Srivastava A, Jain S, Miranda R, Patil S, Pandya S et al. Deep learning based respiratory sound analysis for detection of chronic obstructive pulmonary disease. PeerJ Computer Science 2021; 1-22. doi: 10.7717/peerj-cs.369
[2] Andrès E, Gass R, Charloux A, Brandt C, Hentzler A. Respiratory sound analysis in the era of evidence-based medicine and the world of medicine 2.0. Journal of Medicine and Life 2018; 11 (2): 89-106. doi: 10.5772/48402
[3] Huang M, Liu H, Pi X, Ao Y, Wang Z. Computer-aided diagnosis and new electronic stethoscope. Zhongguo Yi Liao Qi Xie Za Zhi 2017; 41 (3): 161-165.
[4] Laguarta J, Hueto F, Subirana B. COVID-19 artificial intelligence diagnosis using only cough recordings. IEEE Open Journal of Medical and Biological Engineering 2020; 1: 275-281. doi: 10.1109/ojemb.2020.3026928
[5] Chen X, Yao L, Zhou T, Dong J, Zhang Y. Momentum contrastive learning for few-shot COVID-19 diagnosis from chest CT images. Pattern Recognit. 2021; 113:107826. doi: 10.1016/j.patcog.2021.107826
[6] Jimping L, Zhao G, Tao Y, Zhai P, Chen H et al. Multi-task contrastive learning for automatic CT and X-ray diagnosis of COVID-19. Pattern Recognition 2021; 114: 107848. doi: 10.1016/j.patcog.2021.107848
[7] Wu X, Chen C, Zhong M, Wang J, Shi J. COVID-AL: the diagnosis of COVID-19 with deep active learning. Medical Image Analysis 2021; 68: 101913. doi: 10.1016/j.media.2020.101913
[8] Javor D, Kaplan H, Kaplan A, Puchner SB, Krestan C et al. Deep learning analysis provides accurate COVID-19 diagnosis on chest computed tomography. Europen Journal of Radiology 2020; 133: 109402. doi: 10.1016/j.ejrad.2020.109402
[9] Wu Z, Li L, Jin R, Liang L, Hu Z et al. Texture feature-based machine learning classifier could assist in the diagnosis of COVID-19. Europen Journal of Radiology 2021; 137: 109602. doi: 10.1016/j.ejrad.2021.109602
[10] Shorfuzzaman M, Hossain MS. MetaCOVID: A Siamese neural network framework with contrastive loss for n-shot diagnosis of COVID-19 patients. Pattern Recognition 2020; 113: 107700. doi: 10.1016/j.patcog.2020.107700
[11] Vaid S, Kalantar R, Bhandari M. Deep learning COVID-19 detection bias: accuracy through artificial intelligence. International Orthopaedics 2020; 44 (8): 1539-1542. doi: 10.1007/s00264-020-04609-7
[12] Jin W, Dong S, Dong C, Ye X. A hybrid ensemble model for differential diagnosis between COVID-19 and common viral pneumonia by chest X-ray radiograph. Computers in Biology and Medicine 2021; 131: 104252. doi: 10.1016/j.compbiomed.2021.104252
[13] Colombi D, Petrini M, Maffi G, Villani GD, Bodini FC et al. Comparison of admission chest computed tomography and lung ultrasound performance for diagnosis of COVID-19 pneumonia in populations with different disease prevalence. Europen Journal of Radiology 2020; 133: 109344. doi: 10.1016/j.ejrad.2020.109344
[14] Canayaz M. MH-COVIDNet: Diagnosis of COVID-19 using deep neural networks and meta-heuristicbased feature selection on X-ray images. Biomedical Signal Processing and Control 2021; 64: 102257. doi: 10.1016/j.bspc.2020.102257
[15] Yang D, Xu Z, Li W, Myronenko A, Roth HR et al. Federated semi-supervised learning for COVID region segmentation in chest CT using multi-national data from China, Italy, Japan. Medical Image Analysis 2021; 70: 101992. doi: 10.1016/j.media.2021.101992
[16] Gao K, Su J, Jiang Z, Zeng L, Feng Z et al. Dual-branch combination network (DCN): towards accurate diagnosis and lesion segmentation of COVID-19 using CT images. Medical Image Analysis 2021; 67: 101836. doi: 10.1016/j.media.2020.101836
[17] Vidal PL, Moura J, Novo J, Ortega M. Multi-stage transfer learning for lung segmentation using portable X-ray devices for patients with COVID-19. Expert Systems Applications 2021; 173: 114677. doi: 10.1016/j.eswa.2021.114677
[18] Abdel-Basset M, Chang V, Hawash H, Chakrabortty RK, Ryan M. FSS-2019-nCov: a deep learning architecture for semi-supervised few-shot segmentation of COVID-19 infection. Knowledge-Based Systems 2021; 212: 106647. doi: 10.1016/j.knosys.2020.106647
[19] Shuja J, Alanazi E, Alasmary W, Alashaikh A. COVID-19 open source data sets: a comprehensive survey. Applied Intelligence 2021; 51: 1296-1325. doi: 10.1007/s10489-020-01862-6
[20] Imran A, Posokhava I, Qureshi HN, Masood U, Riaz MS et al. AI4COVID-19: AI enabled preliminary diagnosis for COVID-19 from cough samples via an app. Informatics in Medicine Unlocked 2020; 20: 100378. doi: 10.1016/j.imu.2020.100378
[21] Brown C, Chauhan J, Grammenos A, Han J, Hasthanasombat A et al. Exploring automatic diagnosis of COVID19 from crowdsourced respiratory sound data. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2020; 11: 3474-3484. doi: 10.1145/3394486.3412865
[22] Sharma N, Krishnan P, Kumar R, Ramoji S, Chetupalli S et al. Coswara – a database of breathing, cough, and voice sounds for COVID-19 diagnosis. Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH, vol. 2020- October. pp. 4811–4815. May 2020; Accessed: Mar. 04, 2021. [Online]. Available: http://arxiv.org/abs/2005.10548.
[23] Han J, Qian K, Song M, Yang Z, Ren Z et al. An early study on intelligent analysis of speech under COVID-19: severity, sleep quality, fatigue, and anxiety. Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH. vol. 2020- October. pp. 4946–4950. Apr. 2020; Accessed: Mar. 04, 2021. [Online]. Available: http://arxiv.org/abs/2005.00096.
[24] Wen L, Gao L, Li X. A new deep transfer learning based on sparse auto-encoder for fault diagnosis. IEEE Transactions on Systems, Man, and Cybernetics: Systems 2019; 49 (1): 136-144. doi: 10.1109/TSMC.2017.2754287
[25] Hu F, Xia GS, Hu J, Zhang L. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery. Remote Sensing 2015; 7 (11): 14680-14707. doi: 10.3390/rs71114680
[26] Khanna H, Gaunt SLL, McCallum DA. Digital spectrographic cross-correlation: tests of sensitivity. Bioacoustics 1997; 7: 209-234. doi: 10.1080/09524622.1997.9753332
[27] Verstraete D, Ferrada A, Droguett EL, Meruane V, Modarres M. Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings. Shock and Vibration 2017; 2017: 1-17. doi: 10.1155/2017/5067651
[28] McFee B, Raffel C, Liang D, Ellis DP, McVicar M et al. librosa: audio and music signal analysis in Python. In: Proceedings of the 14th Python in Science Conference (SciPy 2015); City, Country; 2015. pp. 18-25. doi: 10.25080/majora-7b98e3ed-003
[29] Dörfler M, Bammer R, Grill T. Inside the Spectrogram: Convolutional Neural Networks in Audio Processing. In: Proceedings of the 2017 12th International Conference on Sampling Theory and Applications (SampTA 2017); City, Country; 2017. pp. 152-155. doi: 10.1109/SAMPTA.2017.8024472
[30] Chollet F. Deep Learning with Python. New York, NY, USA: Simon and Schuster, 2017.
[31] Abadi M, Barham P, Chen J, Chen Z, Davis A et al. TensorFlow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2016); City, Country; 2016. pp. 265-283.
[32] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015); City, Country; 2015. pp. 1–14.
[33] He K, Zhang X, Ren S, Sun J. Identity mappings in deep residual networks. In: Leibe B, Matas J, Sebe N, Welling M (editors). Computer Vision – ECCV 2016. ECCV 2016. Lecture Notes in Computer Science, Vol. 9908. Cham, Switzerland: Springer, 2016.
[34] Huang G, Liu Z, Van der Maaten L, Weinberger KQ. Densely Connected Convolutional Networks. In: Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017); City, Country; 2017. doi: 10.1109/CVPR.2017.243
[35] Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W et al. MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv 2017; 1704.04861: 1-9.
[36] Rahimzadeh M, Attar A. A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2. Informatics in Medicine Unlocked 2020; 19: 1-9. doi: 10.1016/j.imu.2020.100360
[37] Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 2014; 15 (1): 1929-1958.
[38] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; 521: 436-444. doi: 10.1038/nmeth.3707
[39] Ramachandran P, Zoph B, Le QV. Searching for activation functions. arXiv preprint 2017; 1710.05941: 1-13.
[40] Hu Z, Li Y, Yang Z. Improving convolutional neural network using pseudo derivative ReLU. In: Proceedings of the 2018 5th International Conference on Systems and Informatics (ICSAI 2018); City, Country; 2018. pp. 283-287. doi: 10.1109/ICSAI.2018.8599372
[41] Ng HW, Nguyen VD, Vonikakis V, Winkler S. Deep learning for emotion recognition on small datasets using transfer learning. In: Proceedings of the 2015 ACM International Conference on Multimodal Interaction (ICMI 2015); City, Country; 2015. pp. 443–449. doi: 10.1145/2818346.2830593
[42] Hinton G, Srivastava N, Swersky K. Neural Networks for Machine Learning. 2012.
[43] Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B et al. Scikit-learn: machine learning in Python. Journal of Machine Learning Research 2011; 12: 2825-2830.
[44] Zhang Y, Wu L. Bankruptcy prediction by genetic ant colony algorithm. Advanced Materials Research 2011; 186: 459-463. doi: 10.4028/www.scientific.net/AMR.186.459.
[45] Zeng Y, Jiang K, Chen J. Automatic seismic salt interpretation with deep convolutional neural networks. In: Proceedings of the 2019 3rd International Conference on Information System and Data Mining (ICISDM 2019); City, Country; 2019. pp. 16-20. doi: 10.1145/3325917.3325926
[46] Ying X. An overview of overfitting and its solutions. In: Proceedings of the International Conference on Computer Information Science and Application Technology (CISAT 2018); City, Country; 2018. pp. 1–6. doi: 10.1088/1742- 6596/1168/2/022022
[47] Gopalakrishnan K, Khaitan SK, Choudhary A, Agrawal A. Deep convolutional neural Networks with transfer learning for computer vision-based data-driven pavement distress detection. Construction and Building Materials 2017; 157: 322-330. doi: 10.1016/j.conbuildmat.2017.09.110
[48] Kong W, Dong ZY, Luo F, Meng K, Zhang W et al. Effect of automatic hyperparameter tuning for residential load forecasting via deep learning. In: Australasian Universities Power Engineering Conference (AUPEC 2017); City, Country; 2017. pp. 1-6. doi: 10.1109/AUPEC.2017.8282478
[49] Chaudhary PK, Pachori RB. FBSED based automatic diagnosis of COVID-19 using X-ray and CT images. Computers in Biology and Medicine 2021; 134: 104454. doi: 10.1016/j.compbiomed.2021.104454
[50] Saygılı A. A new approach for computer-aided detection of coronavirus (COVID-19) from CT and X-ray images using machine learning methods. Applied Soft Computing 2021; 105: 107323. doi: 10.1016/j.asoc.2021.107323
[51] Li X, Zhai M, Sun J. DDCNNC: dilated and depthwise separable convolutional neural Network for diagnosis COVID-19 via chest X-ray images. International Journal of Cognitive Computing in Engineering 2021; 2: 71-82. doi: 10.1016/j.ijcce.2021.04.001
[52] Jia G, Lam HK, Xu Y. Classification of COVID-19 chest X-Ray and CT images using a type of dynamic CNN modification method. Computers in Biology and Medicine 2021; 134: 104425. doi: 10.1016/j.compbiomed.2021.104425