Multisource Smart Computer-Aided System for Mining COVID-19 Infection Data
In this paper, we approach the problem of detecting and diagnosing COVID-19 infections using multisource scan images including CT and X-ray scans to assist the healthcare system during the COVID-19 pandemic. Here, a computer-aided diagnosis (CAD) system is proposed that utilizes analysis of the CT o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Healthcare |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9032/10/1/109 |
| _version_ | 1797493663713984512 |
|---|---|
| author | Mohammad T. Abou-Kreisha Humam K. Yaseen Khaled A. Fathy Ebeid A. Ebeid Kamal A. ElDahshan |
| author_facet | Mohammad T. Abou-Kreisha Humam K. Yaseen Khaled A. Fathy Ebeid A. Ebeid Kamal A. ElDahshan |
| author_sort | Mohammad T. Abou-Kreisha |
| collection | DOAJ |
| description | In this paper, we approach the problem of detecting and diagnosing COVID-19 infections using multisource scan images including CT and X-ray scans to assist the healthcare system during the COVID-19 pandemic. Here, a computer-aided diagnosis (CAD) system is proposed that utilizes analysis of the CT or X-ray to diagnose the impact of damage in the respiratory system per infected case. The CAD was utilized and optimized by hyper-parameters for shallow learning, e.g., SVM and deep learning. For the deep learning, mini-batch stochastic gradient descent was used to overcome fitting problems during transfer learning. The optimal parameter list values were found using the naïve Bayes technique. Our contributions are (i) a comparison among the detection rates of pre-trained CNN models, (ii) a suggested hybrid deep learning with shallow machine learning, (iii) an extensive analysis of the results of COVID-19 transition and informative conclusions through developing various transfer techniques, and (iv) a comparison of the accuracy of the previous models with the systems of the present study. The effectiveness of the proposed CAD is demonstrated using three datasets, either using an intense learning model as a fully end-to-end solution or using a hybrid deep learning model. Six experiments were designed to illustrate the superior performance of our suggested CAD when compared to other similar approaches. Our system achieves 99.94, 99.6, 100, 97.41, 99.23, and 98.94 accuracy for binary and three-class labels for the CT and two CXR datasets. |
| first_indexed | 2024-03-10T01:23:16Z |
| format | Article |
| id | doaj.art-c437166016874e6189f1136ffd2bac2a |
| institution | Directory Open Access Journal |
| issn | 2227-9032 |
| language | English |
| last_indexed | 2024-03-10T01:23:16Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Healthcare |
| spelling | doaj.art-c437166016874e6189f1136ffd2bac2a2023-11-23T13:55:52ZengMDPI AGHealthcare2227-90322022-01-0110110910.3390/healthcare10010109Multisource Smart Computer-Aided System for Mining COVID-19 Infection DataMohammad T. Abou-Kreisha0Humam K. Yaseen1Khaled A. Fathy2Ebeid A. Ebeid3Kamal A. ElDahshan4Mathematics Department, Faculty of Science, Al-Azhar University, Cairo 11651, EgyptMathematics Department, Faculty of Science, Al-Azhar University, Cairo 11651, EgyptMathematics Department, Faculty of Science, Al-Azhar University, Cairo 11651, EgyptMathematics Department, Faculty of Science, Al-Azhar University, Cairo 11651, EgyptMathematics Department, Faculty of Science, Al-Azhar University, Cairo 11651, EgyptIn this paper, we approach the problem of detecting and diagnosing COVID-19 infections using multisource scan images including CT and X-ray scans to assist the healthcare system during the COVID-19 pandemic. Here, a computer-aided diagnosis (CAD) system is proposed that utilizes analysis of the CT or X-ray to diagnose the impact of damage in the respiratory system per infected case. The CAD was utilized and optimized by hyper-parameters for shallow learning, e.g., SVM and deep learning. For the deep learning, mini-batch stochastic gradient descent was used to overcome fitting problems during transfer learning. The optimal parameter list values were found using the naïve Bayes technique. Our contributions are (i) a comparison among the detection rates of pre-trained CNN models, (ii) a suggested hybrid deep learning with shallow machine learning, (iii) an extensive analysis of the results of COVID-19 transition and informative conclusions through developing various transfer techniques, and (iv) a comparison of the accuracy of the previous models with the systems of the present study. The effectiveness of the proposed CAD is demonstrated using three datasets, either using an intense learning model as a fully end-to-end solution or using a hybrid deep learning model. Six experiments were designed to illustrate the superior performance of our suggested CAD when compared to other similar approaches. Our system achieves 99.94, 99.6, 100, 97.41, 99.23, and 98.94 accuracy for binary and three-class labels for the CT and two CXR datasets.https://www.mdpi.com/2227-9032/10/1/109computer-aided diagnosis (CAD)COVID-19data miningdeep learningdiagnosismachine learning |
| spellingShingle | Mohammad T. Abou-Kreisha Humam K. Yaseen Khaled A. Fathy Ebeid A. Ebeid Kamal A. ElDahshan Multisource Smart Computer-Aided System for Mining COVID-19 Infection Data Healthcare computer-aided diagnosis (CAD) COVID-19 data mining deep learning diagnosis machine learning |
| title | Multisource Smart Computer-Aided System for Mining COVID-19 Infection Data |
| title_full | Multisource Smart Computer-Aided System for Mining COVID-19 Infection Data |
| title_fullStr | Multisource Smart Computer-Aided System for Mining COVID-19 Infection Data |
| title_full_unstemmed | Multisource Smart Computer-Aided System for Mining COVID-19 Infection Data |
| title_short | Multisource Smart Computer-Aided System for Mining COVID-19 Infection Data |
| title_sort | multisource smart computer aided system for mining covid 19 infection data |
| topic | computer-aided diagnosis (CAD) COVID-19 data mining deep learning diagnosis machine learning |
| url | https://www.mdpi.com/2227-9032/10/1/109 |
| work_keys_str_mv | AT mohammadtaboukreisha multisourcesmartcomputeraidedsystemforminingcovid19infectiondata AT humamkyaseen multisourcesmartcomputeraidedsystemforminingcovid19infectiondata AT khaledafathy multisourcesmartcomputeraidedsystemforminingcovid19infectiondata AT ebeidaebeid multisourcesmartcomputeraidedsystemforminingcovid19infectiondata AT kamalaeldahshan multisourcesmartcomputeraidedsystemforminingcovid19infectiondata |