The Role of 3D CT Imaging in the Accurate Diagnosis of Lung Function in Coronavirus Patients
Early grading of coronavirus disease 2019 (COVID-19), as well as ventilator support machines, are prime ways to help the world fight this virus and reduce the mortality rate. To reduce the burden on physicians, we developed an automatic Computer-Aided Diagnostic (CAD) system to grade COVID-19 from C...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/3/696 |
| _version_ | 1797472015649603584 |
|---|---|
| author | Ibrahim Shawky Farahat Ahmed Sharafeldeen Mohamed Elsharkawy Ahmed Soliman Ali Mahmoud Mohammed Ghazal Fatma Taher Maha Bilal Ahmed Abdel Khalek Abdel Razek Waleed Aladrousy Samir Elmougy Ahmed Elsaid Tolba Moumen El-Melegy Ayman El-Baz |
| author_facet | Ibrahim Shawky Farahat Ahmed Sharafeldeen Mohamed Elsharkawy Ahmed Soliman Ali Mahmoud Mohammed Ghazal Fatma Taher Maha Bilal Ahmed Abdel Khalek Abdel Razek Waleed Aladrousy Samir Elmougy Ahmed Elsaid Tolba Moumen El-Melegy Ayman El-Baz |
| author_sort | Ibrahim Shawky Farahat |
| collection | DOAJ |
| description | Early grading of coronavirus disease 2019 (COVID-19), as well as ventilator support machines, are prime ways to help the world fight this virus and reduce the mortality rate. To reduce the burden on physicians, we developed an automatic Computer-Aided Diagnostic (CAD) system to grade COVID-19 from Computed Tomography (CT) images. This system segments the lung region from chest CT scans using an unsupervised approach based on an appearance model, followed by 3D rotation invariant Markov–Gibbs Random Field (MGRF)-based morphological constraints. This system analyzes the segmented lung and generates precise, analytical imaging markers by estimating the MGRF-based analytical potentials. Three Gibbs energy markers were extracted from each CT scan by tuning the MGRF parameters on each lesion separately. The latter were healthy/mild, moderate, and severe lesions. To represent these markers more reliably, a Cumulative Distribution Function (CDF) was generated, then statistical markers were extracted from it, namely, 10th through 90th CDF percentiles with 10% increments. Subsequently, the three extracted markers were combined together and fed into a backpropagation neural network to make the diagnosis. The developed system was assessed on 76 COVID-19-infected patients using two metrics, namely, accuracy and Kappa. In this paper, the proposed system was trained and tested by three approaches. In the first approach, the MGRF model was trained and tested on the lungs. This approach achieved <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>95.83</mn></mrow></semantics></math></inline-formula>% accuracy and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>93.39</mn></mrow></semantics></math></inline-formula>% kappa. In the second approach, we trained the MGRF model on the lesions and tested it on the lungs. This approach achieved <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>91.67</mn></mrow></semantics></math></inline-formula>% accuracy and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>86.67</mn></mrow></semantics></math></inline-formula>% kappa. Finally, we trained and tested the MGRF model on lesions. It achieved 100% accuracy and 100% kappa. The results reported in this paper show the ability of the developed system to accurately grade COVID-19 lesions compared to other machine learning classifiers, such as k-Nearest Neighbor (KNN), decision tree, naïve Bayes, and random forest. |
| first_indexed | 2024-03-09T19:56:31Z |
| format | Article |
| id | doaj.art-96ccc416507942238859f62e09a6d85c |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T19:56:31Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-96ccc416507942238859f62e09a6d85c2023-11-24T00:55:51ZengMDPI AGDiagnostics2075-44182022-03-0112369610.3390/diagnostics12030696The Role of 3D CT Imaging in the Accurate Diagnosis of Lung Function in Coronavirus PatientsIbrahim Shawky Farahat0Ahmed Sharafeldeen1Mohamed Elsharkawy2Ahmed Soliman3Ali Mahmoud4Mohammed Ghazal5Fatma Taher6Maha Bilal7Ahmed Abdel Khalek Abdel Razek8Waleed Aladrousy9Samir Elmougy10Ahmed Elsaid Tolba11Moumen El-Melegy12Ayman El-Baz13BioImaging Laboratory, Department of Bioengineering, University of Louisville, Louisville, KY 40292, USABioImaging Laboratory, Department of Bioengineering, University of Louisville, Louisville, KY 40292, USABioImaging Laboratory, Department of Bioengineering, University of Louisville, Louisville, KY 40292, USABioImaging Laboratory, Department of Bioengineering, University of Louisville, Louisville, KY 40292, USABioImaging Laboratory, Department of Bioengineering, University of Louisville, Louisville, KY 40292, USAElectrical, Computer, and Biomedical Engineering Department, College of Engineering, Abu Dhabi University, Abu Dhabi 59911, United Arab EmiratesCollege of Technological Innovation, Zayed University, Dubai 19282, United Arab EmiratesDepartment of Diagnostic Radiology, Faculty of Medicine, Mansoura University, Mansoura 35516, EgyptDepartment of Diagnostic Radiology, Faculty of Medicine, Mansoura University, Mansoura 35516, EgyptComputer Science Department, Faculty of Computers and Information, Mansoura University, Mansoura 35516, EgyptComputer Science Department, Faculty of Computers and Information, Mansoura University, Mansoura 35516, EgyptComputer Science Department, Faculty of Computers and Information, Mansoura University, Mansoura 35516, EgyptDepartment of Electrical Engineering, Assiut University, Assiut 71511, EgyptBioImaging Laboratory, Department of Bioengineering, University of Louisville, Louisville, KY 40292, USAEarly grading of coronavirus disease 2019 (COVID-19), as well as ventilator support machines, are prime ways to help the world fight this virus and reduce the mortality rate. To reduce the burden on physicians, we developed an automatic Computer-Aided Diagnostic (CAD) system to grade COVID-19 from Computed Tomography (CT) images. This system segments the lung region from chest CT scans using an unsupervised approach based on an appearance model, followed by 3D rotation invariant Markov–Gibbs Random Field (MGRF)-based morphological constraints. This system analyzes the segmented lung and generates precise, analytical imaging markers by estimating the MGRF-based analytical potentials. Three Gibbs energy markers were extracted from each CT scan by tuning the MGRF parameters on each lesion separately. The latter were healthy/mild, moderate, and severe lesions. To represent these markers more reliably, a Cumulative Distribution Function (CDF) was generated, then statistical markers were extracted from it, namely, 10th through 90th CDF percentiles with 10% increments. Subsequently, the three extracted markers were combined together and fed into a backpropagation neural network to make the diagnosis. The developed system was assessed on 76 COVID-19-infected patients using two metrics, namely, accuracy and Kappa. In this paper, the proposed system was trained and tested by three approaches. In the first approach, the MGRF model was trained and tested on the lungs. This approach achieved <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>95.83</mn></mrow></semantics></math></inline-formula>% accuracy and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>93.39</mn></mrow></semantics></math></inline-formula>% kappa. In the second approach, we trained the MGRF model on the lesions and tested it on the lungs. This approach achieved <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>91.67</mn></mrow></semantics></math></inline-formula>% accuracy and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>86.67</mn></mrow></semantics></math></inline-formula>% kappa. Finally, we trained and tested the MGRF model on lesions. It achieved 100% accuracy and 100% kappa. The results reported in this paper show the ability of the developed system to accurately grade COVID-19 lesions compared to other machine learning classifiers, such as k-Nearest Neighbor (KNN), decision tree, naïve Bayes, and random forest.https://www.mdpi.com/2075-4418/12/3/696COVID-19SARS-CoV-2machine learningneural networkComputer Assisted Diagnosis (CAD)Markov–Gibbs Random Field (MGRF) |
| spellingShingle | Ibrahim Shawky Farahat Ahmed Sharafeldeen Mohamed Elsharkawy Ahmed Soliman Ali Mahmoud Mohammed Ghazal Fatma Taher Maha Bilal Ahmed Abdel Khalek Abdel Razek Waleed Aladrousy Samir Elmougy Ahmed Elsaid Tolba Moumen El-Melegy Ayman El-Baz The Role of 3D CT Imaging in the Accurate Diagnosis of Lung Function in Coronavirus Patients Diagnostics COVID-19 SARS-CoV-2 machine learning neural network Computer Assisted Diagnosis (CAD) Markov–Gibbs Random Field (MGRF) |
| title | The Role of 3D CT Imaging in the Accurate Diagnosis of Lung Function in Coronavirus Patients |
| title_full | The Role of 3D CT Imaging in the Accurate Diagnosis of Lung Function in Coronavirus Patients |
| title_fullStr | The Role of 3D CT Imaging in the Accurate Diagnosis of Lung Function in Coronavirus Patients |
| title_full_unstemmed | The Role of 3D CT Imaging in the Accurate Diagnosis of Lung Function in Coronavirus Patients |
| title_short | The Role of 3D CT Imaging in the Accurate Diagnosis of Lung Function in Coronavirus Patients |
| title_sort | role of 3d ct imaging in the accurate diagnosis of lung function in coronavirus patients |
| topic | COVID-19 SARS-CoV-2 machine learning neural network Computer Assisted Diagnosis (CAD) Markov–Gibbs Random Field (MGRF) |
| url | https://www.mdpi.com/2075-4418/12/3/696 |
| work_keys_str_mv | AT ibrahimshawkyfarahat theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT ahmedsharafeldeen theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT mohamedelsharkawy theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT ahmedsoliman theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT alimahmoud theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT mohammedghazal theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT fatmataher theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT mahabilal theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT ahmedabdelkhalekabdelrazek theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT waleedaladrousy theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT samirelmougy theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT ahmedelsaidtolba theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT moumenelmelegy theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT aymanelbaz theroleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT ibrahimshawkyfarahat roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT ahmedsharafeldeen roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT mohamedelsharkawy roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT ahmedsoliman roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT alimahmoud roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT mohammedghazal roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT fatmataher roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT mahabilal roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT ahmedabdelkhalekabdelrazek roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT waleedaladrousy roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT samirelmougy roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT ahmedelsaidtolba roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT moumenelmelegy roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients AT aymanelbaz roleof3dctimagingintheaccuratediagnosisoflungfunctionincoronaviruspatients |