Detection of Covid-19 from Chest CT Images using Xception Architecture: A Deep Transfer Learning based Approach
Covid-19 infection, which first appeared in Wuhan, China in December 2019, affected the whole world in a short time like three months. The disease caused by the virus called SARS-CoV-2 affects many organs, especially the lungs, brain, liver and kidney, and causes a large number of deaths. Early dete...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sakarya University
2021-06-01
|
| Series: | Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/tr/download/article-file/1664654 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850099994162364416 |
|---|---|
| author | Özlem Polat |
| author_facet | Özlem Polat |
| author_sort | Özlem Polat |
| collection | DOAJ |
| description | Covid-19 infection, which first appeared in Wuhan, China in December 2019, affected the whole world in a short time like three months. The disease caused by the virus called SARS-CoV-2 affects many organs, especially the lungs, brain, liver and kidney, and causes a large number of deaths. Early detection of Covid-19 using computer-aided methods will ensure that the patient reaches the right treatment without wasting time, and the spread of the disease will be controlled. This study proposes a solution for detecting Covid-19 using chest computed tomography (CT) scan images. Firstly, image features are extracted using Xception network, convolutional neural network (CNN) based transfer learning architecture, then classification process is performed with a fully connected neural network (FCNN) added at the end of this architecture. The classification model was tested ten times on the publicly available SARS-CoV-2-CT-scan dataset containing 2482 CT images labelled as covid and non-covid. The precision, recall, f1-score and accuracy metrics were used as performance measures. While obtaining an average of 98.89% accuracy, in the best case, 99.59% classification performance was achieved. Xception outperforms other methods in the literature. The results promise that the proposed method can be evaluated as a clinical option helping experts in the detection of Covid-19 from CT images. |
| format | Article |
| id | doaj-art-eacf0f3266c647d09f7b6573be76e5f3 |
| institution | DOAJ |
| issn | 2147-835X |
| language | English |
| publishDate | 2021-06-01 |
| publisher | Sakarya University |
| record_format | Article |
| series | Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi |
| spelling | doaj-art-eacf0f3266c647d09f7b6573be76e5f32025-08-20T02:40:23ZengSakarya UniversitySakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi2147-835X2021-06-0125380081010.16984/saufenbilder.90388628Detection of Covid-19 from Chest CT Images using Xception Architecture: A Deep Transfer Learning based ApproachÖzlem Polat0https://orcid.org/0000-0002-9395-4465Cumhuriyet Üniversitesi | Cumhuriyet UniversityCovid-19 infection, which first appeared in Wuhan, China in December 2019, affected the whole world in a short time like three months. The disease caused by the virus called SARS-CoV-2 affects many organs, especially the lungs, brain, liver and kidney, and causes a large number of deaths. Early detection of Covid-19 using computer-aided methods will ensure that the patient reaches the right treatment without wasting time, and the spread of the disease will be controlled. This study proposes a solution for detecting Covid-19 using chest computed tomography (CT) scan images. Firstly, image features are extracted using Xception network, convolutional neural network (CNN) based transfer learning architecture, then classification process is performed with a fully connected neural network (FCNN) added at the end of this architecture. The classification model was tested ten times on the publicly available SARS-CoV-2-CT-scan dataset containing 2482 CT images labelled as covid and non-covid. The precision, recall, f1-score and accuracy metrics were used as performance measures. While obtaining an average of 98.89% accuracy, in the best case, 99.59% classification performance was achieved. Xception outperforms other methods in the literature. The results promise that the proposed method can be evaluated as a clinical option helping experts in the detection of Covid-19 from CT images.https://dergipark.org.tr/tr/download/article-file/1664654covid-19classificationdeep learningxception |
| spellingShingle | Özlem Polat Detection of Covid-19 from Chest CT Images using Xception Architecture: A Deep Transfer Learning based Approach Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi covid-19 classification deep learning xception |
| title | Detection of Covid-19 from Chest CT Images using Xception Architecture: A Deep Transfer Learning based Approach |
| title_full | Detection of Covid-19 from Chest CT Images using Xception Architecture: A Deep Transfer Learning based Approach |
| title_fullStr | Detection of Covid-19 from Chest CT Images using Xception Architecture: A Deep Transfer Learning based Approach |
| title_full_unstemmed | Detection of Covid-19 from Chest CT Images using Xception Architecture: A Deep Transfer Learning based Approach |
| title_short | Detection of Covid-19 from Chest CT Images using Xception Architecture: A Deep Transfer Learning based Approach |
| title_sort | detection of covid 19 from chest ct images using xception architecture a deep transfer learning based approach |
| topic | covid-19 classification deep learning xception |
| url | https://dergipark.org.tr/tr/download/article-file/1664654 |
| work_keys_str_mv | AT ozlempolat detectionofcovid19fromchestctimagesusingxceptionarchitectureadeeptransferlearningbasedapproach |