Recognition of Covid-19 Over CT Images Using CNN and Transfer Learning
Keywords:
Deep Learning, Transformer, Convolutional neural network, Computed Tomography, and Corona.Abstract
The emergence of COVID-19, a novel corona virus pneumonia, in 2019 has a significant impact on the growth of the global economy and the lives of individuals. Deep learning networks have been developed as a new, widely utilised image processing technique they have been employed as an unique detection approach in clinical practise to retrieve medical info from CT pictures. Yet, because to the medical features of Corona virus Computed tomography scans. As a result, Using the current deep learning method, diagnosis is tough. The global feature extraction advantage of the Transformer module and CNNs module is provided, and the concurrent trans model (TransCNN Net) based on Transformer is employed to fully use the local extraction of features capabilities of the CNN Model.. This is done in line with the COVID-19's medical characteristics on the CT scans. By extracting features from two branches and fusing them in opposite directions, the cross-fusion notion results in a bi-directional feature fusion structure. .A feature fusion module then joins the parallel branch structures to create a model that can identify scale-dependent properties. The classification accuracy of covid data is 96.7, which is greater than Transform Network (Diet-B). The outcomes show increased accuracy. A new approach for diagnosing COVID-19 is also provided by this model, and by it encourages the growth of instantaneous identification pulmonary issues brought on by a corona infection by integrating machine learning with medical imaging. This approach enables an accurate and speedy diagnosis, saving precious lives.
Downloads
References
Z. Ye, Y. Zhang, Y.i. Wang, Z. Huang, B. Song, Chest CT manifestations of new coronavirus disease 2019 (COVID-19): a pictorial review[J], Eur. Radiol. 30 (8) (2020) 4381–4389
A.J. Rodriguez-Morales, J.A. Cardona-Ospina, E. Guti´errez-Ocampo, R. VillamizarPena, Travel Med. Infect. Dis. 34 (2020) 101623.
Z. Lin, Z. Luo, L. Zhao, et al., Multi-scale convolution target detection algorithm with feature pyramid[J], J. ZheJiang Univ. (Eng. Sci.) 53 (3) (2019) 533–540.
Cheng Weiyue, Zhang Xueqin, Lin Kezheng, et al. Deep Convolutional Neural Network Algorithm with Fusing Global and Local Features. [J/OL]. Journal of Frontiers of Computer Science and Technology: 1-11 [2021-09-02].
F. Yu, V. Koltun, Multi-scale context aggregation by dilated convolutions [J]. arXiv preprint arXiv:1511.071 22, 2015.
H.T. Cheng, L. Koc, J. Harmsen, et al., Wide & deep learning for recommender systems[C], in: Proceedings of the 1st workshop on deep learning for recommender systems, 2016, pp. 7-10.
B. Singh, L.S. Davis, An analysis of scale invariance in object detection snip[C], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. (2018:) 3578–3587.
T.Y. Lin, P. Dollar, ´ R. Girshick, et al., Feature pyramid networks for object detection[C], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017:) 2117–2125.
S.-H. Wang, M. Attique Khan, V. Govindaraj, S. L. Fernandes, Z. Zhu, Y.-D. Zhang, Deep rank-based average pooling network for COVID-19 recognition[J], Comput. Mater. Continua 70 (2) (2022) 2797–2813.
S.H. Wang, X. Zhang, Y.D. Zhang, DSSAE: Deep stacked sparse auto encoder analytical model for COVID19 diagnosis by fractional Fourier entropy[J], ACM Trans. Manage. Inform. Syst. (TMIS) 13 (1) (2021) 1– 20.
S.-H. Wang, Z. Zhu, Y.-D. Zhang, Patch Shuffle convolutional neural network for COVID-19 explainable diagnosis[J], Front. Public Health 9 (2021).
Z. Huang, X. Liu, R. Wang, M. Zhang, X. Zeng, J. Liu, Y. Yang, X. Liu, H. Zheng, D. Liang, Z. Hu, FaNet: fast assessment network for the novel coronavirus (COVID19) pneumonia based on 3D CT imaging and clinical symptoms[J], Appl. Intell. 51 (5) (2021) 2838–2849.
A. Dosovitskiy, L. Beyer, A. Kolesnikov, et al., An image is worth 16x16 words: transformers for image recognition at scale[J]. arXiv preprint arXiv:2010. 11929, 2020.
H. Touvron, M. Cord, M. Douze, et al., Training data-efficient image transformers & distillation through attention[C], In: International Conference on Machine Learning. PMLR, 2021, 10347-10357.
A. Howard, M. Sandler, G. Chu, et al., Searching for mob-ilenetv3[C], Proceedings of the IEEE/CVF International Conference on Computer Vision. (2019) 1314–1324.
A.G. Howard, Z.u. Menglong, C. Bo, et al., Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint arXiv, 2017.
M. Sandler, A. Howard, Zhu Menglong, et al., Mobilenetv2: Inverted residuals and linear bottlenecks [C], In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018:4510-4520.
K. Han, Y. Wang, Q. Tian, et al., Ghostnet: More features from cheap operations[C], Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. (2020) 1580–1589.
Li Yunsheng, Chen Yinpeng, Dai Xiyang, et al. MicroNet: Improving Image Recognition with Extremely Low FLOPs[J]. arXiv preprint arXiv:2108. 05894, 2021.
Wu Haiping, Xiao Bin, Codella N, et al. Cvt: Introducing convolutions to vision transformers[J]. arXiv preprint arXiv:2103.15808, 2021.
B. Graham, A. El-Nouby, H. Touvron, et al., LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference[J]. arXiv preprint arXiv:2104.01136, 2021.
T. Xiao, M. Singh, E. Mintun, et al., Early convolutions help transformers see better [J]. arXiv preprint arXiv:2106.14881, 2021.
A. Vaswani, N. Shazeer, N. Parmar, et al., Attention is all you need[C], Advances in neural information processing systems, 2017, p. 5998-6008.
Y. Chen, X. Dai, D. Chen, et al., Mobile‘-Former: Bridging MobileNet and Transformer[J]. arXiv preprint arXiv: 2108. 05895, 20.
S. Lu, Z. Lu, J. Yang, M. Yang, S. Wang, A pathological brain detection system based on kernel based ELM[J], Multimedia Tools Appl. 77 (3) (2018) 3715–3728.
S. Wang, B.o. Kang, J. Ma, X. Zeng, M. Xiao, J. Guo, M. Cai, J. Yang, Y. Li, X. Meng, B.o. Xu, A deep learning algorithm using CT images to screen for Corona Virus Disease (COVID-19) [J], Eur. Radiol. 31 (8) (2021) 6096–6104.
L. Li, L. Qin, Z. Xu, et al., Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT[J], Radiology (2020).
Mangal A, Kalia S, Rajgopal H, et al. CovidAID: CO‘VID-19 detection using chest Xray[J]. arXiv preprint arXiv:2004.09803, 2020.
X. Yu, S. Lu, L. Guo, S.-H. Wang, Y.-D. Zhang, ResGNet-C: A graph convolutional neural network for detection of COVID-19[J], Neurocomputing 452 (2021) 592–605.
Akhilesh, Gadde Lohith Sai, et al. "Covid-19 Detection Using CNN Model with CT Scan Images." 2023 International Conference on Computer Communication and Informatics (ICCCI). IEEE, 2023.
Reema, Gunti, et al. "COVID-19 EDA analysis and prediction using SIR and SEIR models." International Journal of Healthcare Management (2022): 1-16.
Srinivas, Pvvs, et al. "Detection of COVID disease from CT scan images using CNN model." 2022 Second International Conference on Artificial Intelligence and Smart Energy (ICAIS). IEEE, 2022.
J. Zhang, Y. Chu, N. Zhao, Supervised framework for COVID-19 classification and lesion localization from chest CT[J], Ethiopian J. Health Dev. 34 (4) (2020).
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.
