dc.contributor.author | Uçar, Murat | |
dc.date.accessioned | 2022-11-22T08:25:07Z | |
dc.date.available | 2022-11-22T08:25:07Z | |
dc.date.issued | 2022 | en_US |
dc.identifier.citation | Uçar, M. (2022). Automatic segmentation of COVID-19 from computed tomography images using modified U-Net
model-based majority voting approach. Neural Computing and Applications, 34 (24), pp. 21927-21938.
https://doi.org/10.1007/s00521-022-07653-z | en_US |
dc.identifier.uri | https://doi.org/10.1007/s00521-022-07653-z | |
dc.identifier.uri | https://hdl.handle.net/20.500.12508/2305 | |
dc.description.abstract | The coronavirus disease (COVID-19) is an important public health problem that has spread rapidly around the world and has caused the death of millions of people. Therefore, studies to determine the factors affecting the disease, to perform preventive actions and to find an effective treatment are at the forefront. In this study, a deep learning and segmentation-based approach is proposed for the detection of COVID-19 disease from computed tomography images. The proposed model was created by modifying the encoder part of the U-Net segmentation model. In the encoder part, VGG16, ResNet101, DenseNet121, InceptionV3 and EfficientNetB5 deep learning models were used, respectively. Then, the results obtained with each modified U-Net model were combined with the majority vote principle and a final result was reached. As a result of the experimental tests, the proposed model obtained 85.03% Dice score, 89.13% sensitivity and 99.38% specificity on the COVID-19 segmentation test dataset. The results obtained in the study show that the proposed model will especially benefit clinicians in terms of time and cost. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Springer | en_US |
dc.relation.isversionof | 10.1007/s00521-022-07653-z | en_US |
dc.rights | info:eu-repo/semantics/openAccess | en_US |
dc.subject | COVID-19 | en_US |
dc.subject | Deep learning | en_US |
dc.subject | Majority voting | en_US |
dc.subject | Segmentation | en_US |
dc.subject.classification | Radiological Findings | |
dc.subject.classification | Clinical Features | |
dc.subject.classification | COVID-19 | |
dc.subject.classification | Computer Science | |
dc.subject.classification | Electrical Engineering, Electronics & Computer Science
- Computer Vision & Graphics - Retinal Images | |
dc.subject.other | Computerized tomography | |
dc.subject.other | Deep learning | |
dc.subject.other | Image segmentation | |
dc.subject.other | Learning systems | |
dc.subject.other | Signal encoding | |
dc.subject.other | Statistical tests | |
dc.subject.other | Automatic segmentations | |
dc.subject.other | Computed tomography images | |
dc.subject.other | Coronaviruses | |
dc.subject.other | Deep learning | |
dc.subject.other | Majority voting | |
dc.subject.other | Model-based OPC | |
dc.subject.other | Net model | |
dc.subject.other | Preventive action | |
dc.subject.other | Segmentation | |
dc.subject.other | Voting approach | |
dc.subject.other | COVID-19 | |
dc.title | Automatic segmentation of COVID-19 from computed tomography images using modified U-Net model-based majority voting approach | en_US |
dc.type | article | en_US |
dc.relation.journal | Neural Computing and Applications | en_US |
dc.contributor.department | İşletme ve Yönetim Bilimleri Fakültesi -- Yönetim Bilişim Sistemleri Bölümü | en_US |
dc.identifier.volume | 34 | en_US |
dc.identifier.issue | 24 | en_US |
dc.identifier.startpage | 21927 | en_US |
dc.identifier.endpage | 21938 | en_US |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
dc.contributor.isteauthor | Uçar, Murat | |
dc.relation.index | Web of Science - Scopus - PubMed | en_US |
dc.relation.index | Web of Science Core Collection - Science Citation Index Expanded | |