MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features
COVID-19 is a respiratory disease that causes infection in both lungs and the upper respiratory tract. The World Health Organization (WHO) has declared it a global pandemic because of its rapid spread across the globe. The most common way for COVID-19 diagnosis is real-time reverse transcription-pol...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Published: |
Nature Publishing Group
2021
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/102251/ |
| _version_ | 1848863753805758464 |
|---|---|
| author | Dey, Arijit Chattopadhyay, Soham Pawan Kumar Singh Ahmadian, Ali Ferrara, Massimiliano Senu, Norazak Sarkar, Ram |
| author_facet | Dey, Arijit Chattopadhyay, Soham Pawan Kumar Singh Ahmadian, Ali Ferrara, Massimiliano Senu, Norazak Sarkar, Ram |
| author_sort | Dey, Arijit |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | COVID-19 is a respiratory disease that causes infection in both lungs and the upper respiratory tract. The World Health Organization (WHO) has declared it a global pandemic because of its rapid spread across the globe. The most common way for COVID-19 diagnosis is real-time reverse transcription-polymerase chain reaction (RT-PCR) which takes a significant amount of time to get the result. Computer based medical image analysis is more beneficial for the diagnosis of such disease as it can give better results in less time. Computed Tomography (CT) scans are used to monitor lung diseases including COVID-19. In this work, a hybrid model for COVID-19 detection has developed which has two key stages. In the first stage, we have fine-tuned the parameters of the pre-trained convolutional neural networks (CNNs) to extract some features from the COVID-19 affected lungs. As pre-trained CNNs, we have used two standard CNNs namely, GoogleNet and ResNet18. Then, we have proposed a hybrid meta-heuristic feature selection (FS) algorithm, named as Manta Ray Foraging based Golden Ratio Optimizer (MRFGRO) to select the most significant feature subset. The proposed model is implemented over three publicly available datasets, namely, COVID-CT dataset, SARS-COV-2 dataset, and MOSMED dataset, and attains state-of-the-art classification accuracies of 99.15%, 99.42% and 95.57% respectively. Obtained results confirm that the proposed approach is quite efficient when compared to the local texture descriptors used for COVID-19 detection from chest CT-scan images. |
| first_indexed | 2025-11-15T13:37:56Z |
| format | Article |
| id | upm-102251 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-15T13:37:56Z |
| publishDate | 2021 |
| publisher | Nature Publishing Group |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1022512023-07-11T04:03:16Z http://psasir.upm.edu.my/id/eprint/102251/ MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features Dey, Arijit Chattopadhyay, Soham Pawan Kumar Singh Ahmadian, Ali Ferrara, Massimiliano Senu, Norazak Sarkar, Ram COVID-19 is a respiratory disease that causes infection in both lungs and the upper respiratory tract. The World Health Organization (WHO) has declared it a global pandemic because of its rapid spread across the globe. The most common way for COVID-19 diagnosis is real-time reverse transcription-polymerase chain reaction (RT-PCR) which takes a significant amount of time to get the result. Computer based medical image analysis is more beneficial for the diagnosis of such disease as it can give better results in less time. Computed Tomography (CT) scans are used to monitor lung diseases including COVID-19. In this work, a hybrid model for COVID-19 detection has developed which has two key stages. In the first stage, we have fine-tuned the parameters of the pre-trained convolutional neural networks (CNNs) to extract some features from the COVID-19 affected lungs. As pre-trained CNNs, we have used two standard CNNs namely, GoogleNet and ResNet18. Then, we have proposed a hybrid meta-heuristic feature selection (FS) algorithm, named as Manta Ray Foraging based Golden Ratio Optimizer (MRFGRO) to select the most significant feature subset. The proposed model is implemented over three publicly available datasets, namely, COVID-CT dataset, SARS-COV-2 dataset, and MOSMED dataset, and attains state-of-the-art classification accuracies of 99.15%, 99.42% and 95.57% respectively. Obtained results confirm that the proposed approach is quite efficient when compared to the local texture descriptors used for COVID-19 detection from chest CT-scan images. Nature Publishing Group 2021-12-15 Article PeerReviewed Dey, Arijit and Chattopadhyay, Soham and Pawan Kumar Singh and Ahmadian, Ali and Ferrara, Massimiliano and Senu, Norazak and Sarkar, Ram (2021) MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features. Scientific Reports, 11 (1). art. no. 24065. pp. 1-15. ISSN 2045-2322 https://www.nature.com/articles/s41598-021-02731-z 10.1038/s41598-021-02731-z |
| spellingShingle | Dey, Arijit Chattopadhyay, Soham Pawan Kumar Singh Ahmadian, Ali Ferrara, Massimiliano Senu, Norazak Sarkar, Ram MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features |
| title | MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features |
| title_full | MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features |
| title_fullStr | MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features |
| title_full_unstemmed | MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features |
| title_short | MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features |
| title_sort | mrfgro: a hybrid meta-heuristic feature selection method for screening covid-19 using deep features |
| url | http://psasir.upm.edu.my/id/eprint/102251/ http://psasir.upm.edu.my/id/eprint/102251/ http://psasir.upm.edu.my/id/eprint/102251/ |