Using Transfer Learning for Automatic Detection of Covid-19 from Chest X-Ray Images

Abstract:

The hasty spread of the perilous coronavirus has resulted in a significant loss of human life and unprecedented public health challenges around the world. Early screening of COVID-19 followed by an immediate medical response can halt the spread of the infection. The deep learning algorithms coupled with chest X-ray images provide fast and accurate results. This study aims to fine-tune seven pre-trained models for COVID-19 detection using chest X-ray radiographs. A sample of 3428 chest X-ray images comprising 1626 COVID-19 images was used to train and validate the models. The Inception V3 model outperformed the other models with an accuracy of 99.42%.

• Periodical: Advances in Science and Technology (Volume 124)
• Pages: 147-155
• DOI: https://doi.org/10.4028/p-4zt8lr
• Online since: February 2023
• Authors: H. Mary Shyni*, E. Chitra
• Keywords: COVID-19 Detection, Data Augmentation, Pre-Trained Models, Transfer Learning, X-Ray Image

References

[1] Uddin, Azher, et al. Study on convolutional neural network to detect COVID-19 from chest X-rays., Mathematical Problems in Engineering 2021 (2021).

DOI: 10.1155/2021/3366057

[2] Keni, Raghuvir, et al. COVID-19: emergence, spread, possible treatments, and global burden., Frontiers in public health (2020): 216.

DOI: 10.3389/fpubh.2020.00216

[3] Arellano, Matías Cam, and Oscar E. Ramos. Deep Learning Model to Identify COVID-19 Cases from Chest Radiographs., 2020 IEEE XXVII International Conference on Electronics, Electrical Engineering and Computing (INTERCON). IEEE, (2020).

DOI: 10.1109/intercon50315.2020.9220237

[4] Zhang, Jianpeng, et al. Viral pneumonia screening on chest X-rays using confidence-aware anomaly detection., IEEE transactions on medical imaging 40.3 (2020): 879-890.

DOI: 10.1109/tmi.2020.3040950

[5] Arias-Londoño, Julián D., et al. Artificial Intelligence applied to chest X-Ray images for the automatic detection of COVID-19. A thoughtful evaluation approach., Ieee Access 8 (2020): 226811-226827.

DOI: 10.1109/access.2020.3044858

[6] Fred, Herbert L. Drawbacks and limitations of computed tomography: views from a medical educator., Texas Heart Institute Journal 31.4 (2004): 345.

[7] Silva, Pedro, et al. COVID-19 detection in CT images with deep learning: A voting-based scheme and cross-datasets analysis., Informatics in medicine unlocked 20 (2020): 100427.

DOI: 10.1016/j.imu.2020.100427

[8] Narin, Ali, Ceren Kaya, and Ziynet Pamuk. Automatic detection of coronavirus disease (covid-19) using x-ray images and deep convolutional neural networks., Pattern Analysis and Applications 24.3 (2021): 1207-1220.

DOI: 10.1007/s10044-021-00984-y

[9] Ahmed, Imran, Awais Ahmad, and Gwanggil Jeon. An IoT-based deep learning framework for early assessment of COVID-19., IEEE Internet of Things Journal 8.21 (2020): 15855-15862.

DOI: 10.1109/jiot.2020.3034074

[10] Taresh, Mundher Mohammed, et al. Transfer learning to detect covid-19 automatically from x-ray images using convolutional neural networks., International Journal of Biomedical Imaging 2021 (2021).

DOI: 10.1101/2020.08.25.20182170

[11] Jaiswal, Aayush, et al. Classification of the COVID-19 infected patients using DenseNet201 based deep transfer learning., Journal of Biomolecular Structure and Dynamics 39.15 (2021): 5682-5689.

DOI: 10.1080/07391102.2020.1788642

[12] Shorfuzzaman, Mohammad, and Mehedi Masud. On the detection of covid-19 from chest x-ray images using cnn-based transfer learning., CMC-Computers Materials & Continua (2020): 1359-1381.

DOI: 10.32604/cmc.2020.011326

[13] Haghanifar, Arman, et al. Covid-cxnet: Detecting covid-19 in frontal chest x-ray images using deep learning., arXiv preprint arXiv:2006.13807 (2020).

DOI: 10.1007/s11042-022-12156-z

[14] Nayak, Soumya Ranjan, et al. Application of deep learning techniques for detection of COVID-19 cases using chest X-ray images: A comprehensive study., Biomedical Signal Processing and Control 64 (2021): 102365.

DOI: 10.1016/j.bspc.2020.102365

[15] Tang, Shanjiang, et al. EDL-COVID: ensemble deep learning for COVID-19 case detection from chest x-ray images., Ieee Transactions On Industrial Informatics 17.9 (2021): 6539-6549.

DOI: 10.1109/tii.2021.3057683

[16] Hemdan, Ezz El-Din, Marwa A. Shouman, and Mohamed Esmail Karar. Covidx-net: A framework of deep learning classifiers to diagnose covid-19 in x-ray images., arXiv preprint arXiv:2003.11055 (2020).

[17] Apostolopoulos, Ioannis D., and Tzani A. Mpesiana. Covid-19: automatic detection from x-ray images utilizing transfer learning with convolutional neural networks., Physical and engineering sciences in medicine 43.2 (2020): 635-640.

DOI: 10.1007/s13246-020-00865-4

[18] Shastri, Sourabh, et al. CheXImageNet: a novel architecture for accurate classification of Covid-19 with chest x-ray digital images using deep convolutional neural networks., Health and Technology (2022): 1-12.

DOI: 10.1007/s12553-021-00630-x

[19] Ikechukwu, A. Victor, et al. ResNet-50 vs VGG-19 vs training from scratch: A comparative analysis of the segmentation and classification of Pneumonia from chest X-ray images., Global Transitions Proceedings 2.2 (2021): 375-381.

DOI: 10.1016/j.gltp.2021.08.027

[20] Farooq, Muhammad, and Abdul Hafeez. Covid-resnet: A deep learning framework for screening of covid19 from radiographs., arXiv preprint arXiv:2003.14395 (2020).

[21] Ahuja, Sakshi, et al. Deep transfer learning-based automated detection of COVID-19 from lung CT scan slices., Applied Intelligence 51.1 (2021): 571-585.

DOI: 10.1007/s10489-020-01826-w

[22] El Asnaoui, Khalid, and Youness Chawki. Using X-ray images and deep learning for automated detection of coronavirus disease., Journal of Biomolecular Structure and Dynamics 39.10 (2021): 3615-3626.

DOI: 10.1080/07391102.2020.1767212

[23] Orozco-Arias, Simon, et al. Measuring performance metrics of machine learning algorithms for detecting and classifying transposable elements., Processes 8.6 (2020): 638.

DOI: 10.3390/pr8060638

[24] Hajian-Tilaki, Karimollah. Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation., Caspian journal of internal medicine 4.2 (2013): 627.