Deep Learning-Based Covid-19 Detection Using Lung Parenchyma Ct Scans

dc.authorid kaya, zeynep/0000-0001-9831-6246
dc.authorid KOCA, Nizameddin/0000-0003-1457-4366
dc.authorid KURT, ZUHAL/0000-0003-1740-6982
dc.authorscopusid 56247256600
dc.authorscopusid 55806648900
dc.authorscopusid 56247318100
dc.authorscopusid 55257455900
dc.authorscopusid 57822380500
dc.authorwosid kaya, zeynep/N-5338-2015
dc.authorwosid KOCA, Nizameddin/V-9228-2017
dc.contributor.author Kaya, Zeynep
dc.contributor.author Kurt, Zuhal
dc.contributor.author Koca, Nizameddin
dc.contributor.author Cicek, Sumeyye
dc.contributor.author Isik, Sahin
dc.contributor.other Computer Engineering
dc.date.accessioned 2024-07-05T15:16:50Z
dc.date.available 2024-07-05T15:16:50Z
dc.date.issued 2022
dc.department Atılım University en_US
dc.department-temp [Kaya, Zeynep] Eskisehir Osmangazi Univ, Dept Elect & Elect Engn, Eskisehir, Turkey; [Kurt, Zuhal] Atilim Univ, Dept Comp Engn, Ankara, Turkey; [Isik, Sahin] Eskisehir Osmangazi Univ, Dept Comp Engn, Eskisehir, Turkey; [Koca, Nizameddin; Cicek, Sumeyye] Univ Hlth Sci, Dept Internal Med, Bursa, Turkey en_US
dc.description kaya, zeynep/0000-0001-9831-6246; KOCA, Nizameddin/0000-0003-1457-4366; KURT, ZUHAL/0000-0003-1740-6982 en_US
dc.description.abstract During the outbreak of the COVID-19 pandemic, it is important to improve early diagnosis using effective ways in order to lower the risks and further spread of the viruses as early as possible. This is also important when it comes to appropriate treatments and the reduction of mortality rates. In this respect, computer tomography (CT) scanning is a useful technique in detecting COVID-19. The present paper, as such, is an attempt to contribute to this process by generating an open-source, CT-based image dataset. This dataset contains the CT scans of lung parenchyma regions of 180 COVID-19 positives and 86 COVID-19 negative patients, all from Bursa Yuksek Ihtisas Training and Research Hospital. The experimental studies demonstrate that this dataset is effectively utilized deep learning-based models for diagnostic purposes. Firstly, a smart segmentation mechanism based on the k-means algorithm is applied to this dataset as a pre-processing stage. Then, the performance of the proposed method is evaluated using InceptionV3 and Xception convolutional neural networks, yielding a 96.20% and 96.55% accuracy rate and 95.00% and 95.50% F1-score, respectively. These state-of-the-art models are observed to detect COVID-19 cases faster and more accurately. In addition, the fine-tuning stage of the convolutional neural network (CNN) features sufficiently improves this accuracy rate. For these features, the support vector machine (SVM) classifier is used, resulting in remarkable 96.76% accuracy rate and 95.81% F1-score. The implications of the proposed method are immense both for present-day applications as well as future developments. en_US
dc.identifier.citationcount 1
dc.identifier.doi 10.1007/978-981-19-0604-6_23
dc.identifier.endpage 275 en_US
dc.identifier.isbn 9789811906046
dc.identifier.isbn 9789811906039
dc.identifier.issn 2367-3370
dc.identifier.issn 2367-3389
dc.identifier.scopus 2-s2.0-85135085932
dc.identifier.scopusquality Q4
dc.identifier.startpage 261 en_US
dc.identifier.uri https://doi.org/10.1007/978-981-19-0604-6_23
dc.identifier.uri https://hdl.handle.net/20.500.14411/1677
dc.identifier.volume 394 en_US
dc.identifier.wos WOS:000874485500022
dc.institutionauthor Kurt, Zühal
dc.language.iso en en_US
dc.publisher Springer international Publishing Ag en_US
dc.relation.ispartof International Conference on Computing and Communication Networks (ICCCN) -- NOV 19-20, 2021 -- Manchester Metropolitan Univ, Manchester, ENGLAND en_US
dc.relation.ispartofseries Lecture Notes in Networks and Systems
dc.relation.publicationcategory Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/closedAccess en_US
dc.scopus.citedbyCount 1
dc.subject Lung parenchyma en_US
dc.subject Deep learning en_US
dc.subject COVID-19 detection en_US
dc.subject CT image dataset en_US
dc.subject Fine-tuning en_US
dc.subject K-means en_US
dc.subject Support vector machine en_US
dc.title Deep Learning-Based Covid-19 Detection Using Lung Parenchyma Ct Scans en_US
dc.type Conference Object en_US
dc.wos.citedbyCount 1
dspace.entity.type Publication
relation.isAuthorOfPublication c1644357-fb5e-46b5-be18-1dd9b8e84e2e
relation.isAuthorOfPublication.latestForDiscovery c1644357-fb5e-46b5-be18-1dd9b8e84e2e
relation.isOrgUnitOfPublication e0809e2c-77a7-4f04-9cb0-4bccec9395fa
relation.isOrgUnitOfPublication.latestForDiscovery e0809e2c-77a7-4f04-9cb0-4bccec9395fa

Files

Collections