Covid-19 Detection by X-Ray Images Using Deep Residual Network with Optimize Segmentation
Keywords:
CNN, X-ray Images, LSTM-RNN, Extreme Leaner, Machine Lerning, Covid-19Abstract
For the purpose of COVID-19 lesion segmentation, the Covid-SegNet model has been suggested. The design of the UNet has been improved and is now known as the CovidSegNet. The receptive field of the encoder in the UNet is constantly restricted to a minimal size. As a result, the issue of a tiny receptive field is addressed with Covid-SegNet by the use of the atrous spatial pyramid pooling technique. down order to zero down on the fine-grained characteristics, the channel and spatial-wise attention processes are also used. In addition to this, the ablation research is carried out to emphasize the significance of these alterations to the UNet model. The ReSE- Net algorithm is suggested for use in the fourth research for the purpose of lung segmentation in chest x-rays. Additionally, it is the encoder-decoder architecture that is improved upon and based on UNet. It makes use of residual learning in both the encoder and the decoder, whereas the attention layer is implemented in the encoder in order to re-calibrate the features. The ReSE-Net algorithm is tested using three different chest x-ray datasets before being verified using a CT-scan dataset. In addition, ablation research is carried out in order to emphasize the influence that the attention mechanism has on the model that is being offered. In addition, a non-parametric statistical test is carried out to validate the findings’ significant statistical relevance. In both the intra-dataset and cross-dataset evaluations, the performance of the suggested model was superior than that of the UNet model. In the fifth investigation, a method known as transfer learning is used for the purpose of lung segmentation. As an encoder, the suggested EfficientUNet model makes use of a modified version of the pre-trained EfficientNet-B4 network. In addition to this, an ablation study is carried out to illustrate the effects of the modifications made to the encoder and the decoder. In addition, when compared to the performance of the ReSE-Net model in the cross-dataset generalization test, the EfficientUNet model demonstrated superior results. The performance of EfficientUNet was superior to that of all the models suggested in similar research, including the design of UNet. Through illness identification and lung segmentation applications, this thesis demonstrates the promise of deep learning for chest x-ray interpretation.
Downloads
References
E. E. D. Hemdan, M. A. Shouman, and M. E. Karar.G. Jain, D. Mittal, D. Thakur, and M. K. Mittal, “A deep learning approach to detect Covid-19 coronavirus with X-Ray images,” Biocy- bernetics and biomedical engineering, vol. 40, no. 4, pp. 1391–1405, 2020.
R. Jain, M. Gupta, S. Taneja, and D. J. Hemanth, “Deep learning- based detection and analysis of COVID-19 on chest X-ray images,” Applied Intelligence, vol. 51, pp. 1690–1700, 2021.
M. Markom, M. Taha, A. Adom, A. Sukor, A. Nasir, H. Yazid. Markom, and A. M, “A review: deep learning classification performance of normal and COVID-19 chest X-ray images,” In Journal of Physics: Conference Series, vol. 2071, no. 1, pp. 12 003–12 003, 2021.
M. E. Sahin, “Deep learning-based approach for detecting COVID-19 in chest X-rays,” Biomedical Signal Processing and Control, vol. 78, pp. 103 977–103 977, 2022.
A. Bashar, G. B. Latif, G. Brahim, N. Mohammad, and J. Alghazo, “COVID-19 pneumonia detection using optimized deep learning techniques,” Diagnostics, vol. 11, no. 11, 1972.
T. Jung and N. Vij, “Early diagnosis and real-time monitoring of regional lung function changes to prevent chronic obstructive pulmonary disease progression to severe emphysema,” Journal of Clinical Medicine, vol. 10, no. 24, pp. 5811–5811, 2021.
A. Sharma, K. Singh, and D. Koundal, “A novel fusion-based convolutional neural network approach for classification of COVID-19 from chest X-ray images,” Biomedical Signal Processing and Control, vol. 77, pp. 103 778–103 778, 2022.
S. Asif, Y. Wenhui, H. Jin, and S. Jinhai, “Classification of COVID-19 from chest X-ray images using deep convolutional neural network,” 2020 IEEE 6th international conference on computer and communications (ICCC), pp. 426–433, 2020.
S. Mahajan, Raina, X. Gao, and A. K. Pandit, “COVID-19 detection using hybrid deep learning model in chest x-rays images,” Concurrency and Computation: Practice and Experience, vol. 34, no. 5, pp. 6747– 6747, 2022.
E. E. Hemdan, M. Shouman, and M. E. Karar, 2020.
A. Narin, C. Kaya, and Z. Pamuk, “Automatic detection of coronavirus disease (covid-19) using x-ray images and deep convolutional neural networks,” Pattern Analysis and Applications, vol. 24, pp. 1207–1220, 2021.
S. Chakraborty, B. Murali, and A. K. Mitra, “An efficient deep learning model to detect COVID-19 using chest X-ray images,” International Journal of Environmental Research and Public Health, vol. 19, no. 4, 2013.
N. Brandi, Ciccarese, M. Rimondi, C. Balacchi, C. Modolon, Sportoletti, and R. Golfieri, “An imaging overview of COVID-19 ards in ICU patients and its complications: a pictorial review,” Diagnostics, vol. 12, no. 4, pp. 846–846, 2022.
S. Agrawal, V. Honnakasturi, M. Nara, and N. Patil, “Utilizing Deep Learning Models and Transfer Learning for COVID-19 Detection from X-Ray Images,” SN Computer Science, vol. 4, no. 4, pp. 326–326, 2023.
I. Apostolopoulos and T. A. Mpesiana, pp. 635–640, 2020.
S. Vj, “Deep learning algorithm for COVID-19 classification using chest X-ray images,” Computational and Mathematical Methods in Medicine, 2021.
M. Loey, S. El-Sappagh, and S. Mirjalili, “Bayesian-based optimized deep learning model to detect COVID-19 patients using chest X-ray image data,” Computers in Biology and Medicine, vol. 142, pp. 105 213– 105 213, 2022.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
