Comparative study for automated coronavirus detection in CT images with transfer learning
Purpose: To design a computer-aided diagnosis system with transfer learning methods to serve as decision support system for automated coronavirus detection in CT images. Methods: Four pre-trained deep convolutional neural networks (ResNet-18, SqueezeNet, ShuffleNet, MobileNet-v2) have been investi...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | Arabic |
| Published: |
damascus university
2023-01-01
|
| Series: | مجلة جامعة دمشق للعلوم الهندسية |
| Subjects: | |
| Online Access: | http://journal.damascusuniversity.edu.sy/index.php/engj/article/view/2248 |
| _version_ | 1797957160186937344 |
|---|---|
| author | Nisreen Sulayman |
| author_facet | Nisreen Sulayman |
| author_sort | Nisreen Sulayman |
| collection | DOAJ |
| description |
Purpose: To design a computer-aided diagnosis system with transfer learning methods to serve as decision support system for automated coronavirus detection in CT images.
Methods: Four pre-trained deep convolutional neural networks (ResNet-18, SqueezeNet, ShuffleNet, MobileNet-v2) have been investigated to diagnose coronavirus with CT scans. To evaluate the pre-trained deep convolutional neural network, we used the COVID-CT dataset, which contains 349 CT images of COVID-19 from 216 patients, and 397 CT images obtained from non-COVID-19 subjects.
Results: Considering binary classification performance results, it has been seen that the pre-trained ResNet-18 model provides the highest classification performance (97.0470 ± 5.5466 accuracy, 98.7342 ± 2.1925 sensitivity, 95.1429 ± 9.3460 specificity, and 0.9737± 0.0489 F1-score) among other three used models.
Conclusion: ResNet-18 model can be employed as a supportive decision-making system to assist radiologists at clinics and hospitals to screen patients swiftly.
|
| first_indexed | 2024-04-11T00:01:07Z |
| format | Article |
| id | doaj.art-6b26838ecfda485992e897c44a401ec7 |
| institution | Directory Open Access Journal |
| issn | 1999-7302 2789-6854 |
| language | Arabic |
| last_indexed | 2024-04-11T00:01:07Z |
| publishDate | 2023-01-01 |
| publisher | damascus university |
| record_format | Article |
| series | مجلة جامعة دمشق للعلوم الهندسية |
| spelling | doaj.art-6b26838ecfda485992e897c44a401ec72023-01-10T04:21:25Zaradamascus universityمجلة جامعة دمشق للعلوم الهندسية1999-73022789-68542023-01-01384Comparative study for automated coronavirus detection in CT images with transfer learningNisreen Sulayman0Damascus University Purpose: To design a computer-aided diagnosis system with transfer learning methods to serve as decision support system for automated coronavirus detection in CT images. Methods: Four pre-trained deep convolutional neural networks (ResNet-18, SqueezeNet, ShuffleNet, MobileNet-v2) have been investigated to diagnose coronavirus with CT scans. To evaluate the pre-trained deep convolutional neural network, we used the COVID-CT dataset, which contains 349 CT images of COVID-19 from 216 patients, and 397 CT images obtained from non-COVID-19 subjects. Results: Considering binary classification performance results, it has been seen that the pre-trained ResNet-18 model provides the highest classification performance (97.0470 ± 5.5466 accuracy, 98.7342 ± 2.1925 sensitivity, 95.1429 ± 9.3460 specificity, and 0.9737± 0.0489 F1-score) among other three used models. Conclusion: ResNet-18 model can be employed as a supportive decision-making system to assist radiologists at clinics and hospitals to screen patients swiftly. http://journal.damascusuniversity.edu.sy/index.php/engj/article/view/2248Transfer learningResNet-18CoronavirusCOVID-CT dataset |
| spellingShingle | Nisreen Sulayman Comparative study for automated coronavirus detection in CT images with transfer learning مجلة جامعة دمشق للعلوم الهندسية Transfer learning ResNet-18 Coronavirus COVID-CT dataset |
| title | Comparative study for automated coronavirus detection in CT images with transfer learning |
| title_full | Comparative study for automated coronavirus detection in CT images with transfer learning |
| title_fullStr | Comparative study for automated coronavirus detection in CT images with transfer learning |
| title_full_unstemmed | Comparative study for automated coronavirus detection in CT images with transfer learning |
| title_short | Comparative study for automated coronavirus detection in CT images with transfer learning |
| title_sort | comparative study for automated coronavirus detection in ct images with transfer learning |
| topic | Transfer learning ResNet-18 Coronavirus COVID-CT dataset |
| url | http://journal.damascusuniversity.edu.sy/index.php/engj/article/view/2248 |
| work_keys_str_mv | AT nisreensulayman comparativestudyforautomatedcoronavirusdetectioninctimageswithtransferlearning |