Thorough Analysis of Deep Learning Methods for Diagnosis of COVID-19 CT Images:

Gnaneswari Gnanaguru CMR Institute of Technology, India S.Silvia Priscila Bharath Institute of Higher Education and Research, India M. Sakthivanitha Vels Institute of Science, Technology, and Advanced Studies, India Sangeetha Radhakrishnan Vels Institute of Science, Technology, and Advanced Studies, India S. Suman Rajest Dhaanish Ahmed College of Engineering, India https://orcid.org/0000-0001-8315-3747 Sonia Singh Toss Global Management, UAE Thorough Analysis of Deep Learning Methods for Diagnosis of COVID-19 CT Images

Since March 2020, WHO has classified COVID-19 a pandemic. This respiratory-system-focused viral infection causes atypical pneumonia. Experts stress the necessity of early COVID-19 detection. Isolating affected people is essential to stopping the virus. Early identification and efficient tracking are crucial for treatment and transmission reduction due to urgency. CT scans are fast and accurate COVID-19 screening tools. Using these scans to classify COVID-19 requires a radiologist, which can prolong the process. This chapter examines common deep learning (DL) techniques for COVID-19 detection. Their use in image processing is explored to improve diagnostics. Deep learning, a subset of machine learning (ML), can automate screening with medical practitioners to improve diagnostic accuracy and efficiency. The review discusses DL methods' pros and cons and their importance in radiologists' and doctors' collaboration.
chapter 4 2024 4 26 46 65 10.4018/979-8-3693-5946-4.ch004 20240501110912 https://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/979-8-3693-5946-4.ch004 https://www.igi-global.com/viewtitle.aspx?TitleId=346190 10.1109/ICBME51989.2020.9319326 Abdar, A. K., Sadjadi, S. M., Soltanian-Zadeh, H., Bashirgonbadi, A., & Naghibi, M. (2020). Automatic detection of coronavirus (COVID-19) from chest CT images using VGG16-based deep-learning. In 2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME), (pp. 212-216). IEEE. Revolutionizing Patient Care with Connected Healthcare Solutions. R. C.Aditya Komperla 2023 144 3 FMDB Transactions on Sustainable Health Science Letters Aditya KomperlaR. C. (2023). Revolutionizing Patient Care with Connected Healthcare Solutions.FMDB Transactions on Sustainable Health Science Letters, 1(3), 144–154. 1 10.1016/j.compbiomed.2021.105014 10.3844/jcssp.2020.620.625 10.1155/2022/1043299 Alzahrani, A., Bhuiyan, M. & Akhter, F. (2022). Detecting COVID-19 Pneumonia over Fuzzy Image Enhancement on Computed Tomography Images. Computational and Mathematical Methods in Medicine, 1-12. 10.1016/j.compbiomed.2020.104037 10.4018/979-8-3693-1301-5.ch006 10.1038/s41591-019-0447-x Analysing Healthcare Disparities in Breast Cancer: Strategies for Equitable Prevention, Diagnosis, and Treatment among Minority Women. Z.Bala Kuta 2023 130 3 FMDB Transactions on Sustainable Health Science Letters Bala KutaZ.Bin SulaimanR. (2023). Analysing Healthcare Disparities in Breast Cancer: Strategies for Equitable Prevention, Diagnosis, and Treatment among Minority Women.FMDB Transactions on Sustainable Health Science Letters, 1(3), 130–143. 1 Coronavirus (COVID-19) classification using CT images by machine learning methods. In arXiv M.Barstugan 2020 BarstuganM.OzkayaU.OzturkS. (2020). Coronavirus (COVID-19) classification using CT images by machine learning methods. In arXiv[cs.CV]. http://arxiv.org/abs/2003.09424 10.3390/app11157004 10.1038/s41598-020-76282-0 10.1016/S0140-6736(20)30211-7 Chen, X., Yao, L., & Zhang, Y. (2020). Residual attention u-net for automated multi-class segmentation of COVID-19 chest CT images. arXiv preprint arXiv:2004.05645, pp.1-7. 10.1007/s12559-020-09751-3 10.1007/978-3-319-66179-7_64 10.3233/JIFS-201985 10.1109/TMI.2020.2996645 10.1148/radiol.2020200280 Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan. China: A descriptive study Geng 2020 424 4 Lancet Geng, Y. (2020). Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan. China: A descriptive study. Lancet, 92(4), 424–432. 92 10.1007/s11760-021-02130-x 10.3389/fmed.2020.608525 An Improved Model for Diabetic Retinopathy Detection by Using Transfer Learning and Ensemble Learning. M. S.Hasan Talukder 2023 92 2 FMDB Transactions on Sustainable Health Science Letters Hasan TalukderM. S.SarkarA.AkterS.Nuhi-AlaminM.Bin SulaimanR. (2023). An Improved Model for Diabetic Retinopathy Detection by Using Transfer Learning and Ensemble Learning.FMDB Transactions on Sustainable Health Science Letters, 1(2), 92–106. 1 A.-E.Hassanien 2020 Big data analytics and artificial intelligence against COVID-19: Innovation vision and approach HassanienA.-E.DeyN.ElghamrawyS. (Eds.). (2020). Big data analytics and artificial intelligence against COVID-19: Innovation vision and approach. Springer International Publishing. 10.1016/j.patcog.2021.107828 10.3389/frcmn.2021.645040 10.1109/TMI.2020.2992546 10.1148/radiol.2020200241 10.1016/j.bbe.2021.05.013 10.3389/fpubh.2020.599550 10.1155/2022/7672196 10.1016/j.csbj.2018.01.001 Diagnosing COVID-19 from CT Image of Lung Segmentation & Classification with Deep Learning Based on Convolutional Neural Networks. K. S.Kumari 2021 1 Wireless Personal Communications KumariK. S.SamalS.MishraR.MadirajuG.MahabobM. N.ShivappaA. B. (2021). Diagnosing COVID-19 from CT Image of Lung Segmentation & Classification with Deep Learning Based on Convolutional Neural Networks.Wireless Personal Communications, 1–17.34602752 A Systematic Review on Workforce Development in Healthcare Sector: Implications in the Post-COVID Scenario. P. S.Kuragayala 2023 36 1 FMDB Transactions on Sustainable Technoprise Letters KuragayalaP. S. (2023). A Systematic Review on Workforce Development in Healthcare Sector: Implications in the Post-COVID Scenario.FMDB Transactions on Sustainable Technoprise Letters, 1(1), 36–46. 1 10.1016/j.csbj.2020.09.029 10.1038/s41591-020-0931-3 10.1038/s41591-020-0916-2 A comparative study of medical image enhancement algorithms and quality assessment metrics on COVID-19 CT images. M. W.Mirza 2022 1 Signal, Image and Video Processing MirzaM. W.SiddiqA.KhanI. R. (2022). A comparative study of medical image enhancement algorithms and quality assessment metrics on COVID-19 CT images.Signal, Image and Video Processing, 1–10.35493403 COVID-19 Pneumonia Classification Based on NeuroWavelet Capsule Network. H. N.Monday 2022 1 3 Health Care MondayH. N.LiJ.NnejiG. U.NaharS.HossinM. A.JacksonJ. (2022). COVID-19 Pneumonia Classification Based on NeuroWavelet Capsule Network.Health Care, 10(3), 1–19.35326900 10 10.1016/j.imu.2021.100681 10.1056/NEJMp2000929 10.1007/s00330-020-07044-9 10.4018/979-8-3693-0502-7 Importance of Business Financial Risk Analysis in SMEs According to COVID-19. M. P.Ocoró 2023 12 1 FMDB Transactions on Sustainable Management Letters OcoróM. P.PoloO. C. C.KhandareS. (2023). Importance of Business Financial Risk Analysis in SMEs According to COVID-19.FMDB Transactions on Sustainable Management Letters, 1(1), 12–21. 1 10.1007/s00330-020-06713-z 10.1016/j.compbiomed.2021.104319 10.4018/979-8-3693-1301-5 10.4018/978-1-6684-9189-8 10.4018/978-1-6684-9189-8.ch018 Regin, R., Khanna, A. A., Krishnan, V., Gupta, M., & Bose, R. S., & Rajest, S. S. (2023a). Information design and unifying approach for secured data sharing using attribute-based access control mechanisms. In Recent Developments in Machine and Human Intelligence (pp. 256–276). IGI Global, USA. 10.4018/979-8-3693-0502-7.ch019 10.1504/IJBRA.2023.10057044 MuscleDrive: A Proof of Concept Describing the Electromyographic Navigation of a Vehicle. R. R.Saxena 2023 107 2 FMDB Transactions on Sustainable Health Science Letters SaxenaR. R.SujithS.NelavalaR. (2023). MuscleDrive: A Proof of Concept Describing the Electromyographic Navigation of a Vehicle.FMDB Transactions on Sustainable Health Science Letters, 1(2), 107–117. 1 10.1504/IJBRA.2023.135363 10.1016/j.imu.2020.100427 10.1007/s10096-020-03901-z 10.1109/TCBB.2021.3065361 Exploring the Frontiers of Pervasive Computing in Healthcare: Innovations and Challenges. A.Tak 2023 164 3 FMDB Transactions on Sustainable Health Science Letters TakA.ShuvoS. A.MaddouriA. (2023). Exploring the Frontiers of Pervasive Computing in Healthcare: Innovations and Challenges.FMDB Transactions on Sustainable Health Science Letters, 1(3), 164–174. 1 Pervasive Technologies and Social Inclusion in Modern Healthcare: Bridging the Digital Divide. A.Tak 2023 118 3 FMDB Transactions on Sustainable Health Science Letters TakA.SundararajanV. (2023). Pervasive Technologies and Social Inclusion in Modern Healthcare: Bridging the Digital Divide.FMDB Transactions on Sustainable Health Science Letters, 1(3), 118–129. 1 Tripathi, S., & Al -Zubaidi, A. (2023). A Study within Salalah’s Higher Education Institutions on Online Learning Motivation and Engagement Challenges during Covid-19. FMDB Transactions on Sustainable Techno Learning, 1(1), 1–10. 10.3390/diagnostics11091735 10.1016/j.asoc.2020.106897 10.1016/S0140-6736(20)30185-9 10.1038/s41598-020-76550-z 10.1007/s00330-021-07715-1 10.1007/s00330-021-07715-1 10.1038/s41591-020-0822-7 10.1109/TIP.2021.3058783 10.3389/fbioe.2020.00898 A Comprehensive Review of Smartphone Applications in Real-time Patient Monitoring. S.Yalavarthi 2023 155 3 FMDB Transactions on Sustainable Health Science Letters YalavarthiS.Boussi RahmouniH. (2023). A Comprehensive Review of Smartphone Applications in Real-time Patient Monitoring.FMDB Transactions on Sustainable Health Science Letters, 1(3), 155–163. 1 10.1016/j.cell.2020.04.045 10.1016/j.compbiomed.2021.104526 10.1101/2020.03.12.20027185 10.1002/ima.22527 10.1109/WACV.2018.00079 10.1016/j.jinf.2020.03.033