Automated COVID-19 detection with convolutional neural networks
Abstract This paper focuses on addressing the urgent need for efficient and accurate automated screening tools for COVID-19 detection. Inspired by existing research efforts, we propose two framework models to tackle this challenge. The first model combines a conventional CNN architecture as a featur...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-06-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-37743-4 |
| _version_ | 1797789775743156224 |
|---|---|
| author | Aphelele Dumakude Absalom E. Ezugwu |
| author_facet | Aphelele Dumakude Absalom E. Ezugwu |
| author_sort | Aphelele Dumakude |
| collection | DOAJ |
| description | Abstract This paper focuses on addressing the urgent need for efficient and accurate automated screening tools for COVID-19 detection. Inspired by existing research efforts, we propose two framework models to tackle this challenge. The first model combines a conventional CNN architecture as a feature extractor with XGBoost as the classifier. The second model utilizes a classical CNN architecture with a Feedforward Neural Network for classification. The key distinction between the two models lies in their classification layers. Bayesian optimization techniques are employed to optimize the hyperparameters of both models, enabling a “cheat-start” to the training process with optimal configurations. To mitigate overfitting, transfer learning techniques such as Dropout and Batch normalization are incorporated. The CovidxCT-2A dataset is used for training, validation, and testing purposes. To establish a benchmark, we compare the performance of our models with state-of-the-art methods reported in the literature. Evaluation metrics including Precision, Recall, Specificity, Accuracy, and F1-score are employed to assess the efficacy of the models. The hybrid model demonstrates impressive results, achieving high precision (98.43%), recall (98.41%), specificity (99.26%), accuracy (99.04%), and F1-score (98.42%). The standalone CNN model exhibits slightly lower but still commendable performance, with precision (98.25%), recall (98.44%), specificity (99.27%), accuracy (98.97%), and F1-score (98.34%). Importantly, both models outperform five other state-of-the-art models in terms of classification accuracy, as demonstrated by the results of this study. |
| first_indexed | 2024-03-13T01:55:27Z |
| format | Article |
| id | doaj.art-6a04a2885fb34070858e9818722e964c |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-13T01:55:27Z |
| publishDate | 2023-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-6a04a2885fb34070858e9818722e964c2023-07-02T11:14:45ZengNature PortfolioScientific Reports2045-23222023-06-0113113010.1038/s41598-023-37743-4Automated COVID-19 detection with convolutional neural networksAphelele Dumakude0Absalom E. Ezugwu1School of Mathematics, Statistics, and Computer Science, University of KwaZulu-Natal, King Edward Avenue, Pietermaritzburg CampusUnit for Data Science and Computing, North-West UniversityAbstract This paper focuses on addressing the urgent need for efficient and accurate automated screening tools for COVID-19 detection. Inspired by existing research efforts, we propose two framework models to tackle this challenge. The first model combines a conventional CNN architecture as a feature extractor with XGBoost as the classifier. The second model utilizes a classical CNN architecture with a Feedforward Neural Network for classification. The key distinction between the two models lies in their classification layers. Bayesian optimization techniques are employed to optimize the hyperparameters of both models, enabling a “cheat-start” to the training process with optimal configurations. To mitigate overfitting, transfer learning techniques such as Dropout and Batch normalization are incorporated. The CovidxCT-2A dataset is used for training, validation, and testing purposes. To establish a benchmark, we compare the performance of our models with state-of-the-art methods reported in the literature. Evaluation metrics including Precision, Recall, Specificity, Accuracy, and F1-score are employed to assess the efficacy of the models. The hybrid model demonstrates impressive results, achieving high precision (98.43%), recall (98.41%), specificity (99.26%), accuracy (99.04%), and F1-score (98.42%). The standalone CNN model exhibits slightly lower but still commendable performance, with precision (98.25%), recall (98.44%), specificity (99.27%), accuracy (98.97%), and F1-score (98.34%). Importantly, both models outperform five other state-of-the-art models in terms of classification accuracy, as demonstrated by the results of this study.https://doi.org/10.1038/s41598-023-37743-4 |
| spellingShingle | Aphelele Dumakude Absalom E. Ezugwu Automated COVID-19 detection with convolutional neural networks Scientific Reports |
| title | Automated COVID-19 detection with convolutional neural networks |
| title_full | Automated COVID-19 detection with convolutional neural networks |
| title_fullStr | Automated COVID-19 detection with convolutional neural networks |
| title_full_unstemmed | Automated COVID-19 detection with convolutional neural networks |
| title_short | Automated COVID-19 detection with convolutional neural networks |
| title_sort | automated covid 19 detection with convolutional neural networks |
| url | https://doi.org/10.1038/s41598-023-37743-4 |
| work_keys_str_mv | AT apheleledumakude automatedcovid19detectionwithconvolutionalneuralnetworks AT absalomeezugwu automatedcovid19detectionwithconvolutionalneuralnetworks |