Covid-19 Diagnosis Based on CT Images Through Deep Learning and Data Augmentation

Ruiwen Hu, Tianrun Wang, Yaxing Jing, Tangyu Xu, Feiyu Chen

Abstract


Coronavirus disease 2019(Covid-19) has made people around the world suffer. And there are many researchers make efforts on deep learning methods based on CT imgaes, but the limitation of  this work is the lackage of the dataset, which is not easy to obtain. In this study, we try to use data augmentation to compensate this weakness. In the first part, we use traditional DenseNet-169, and the result shows that data augmentation can help improve the calculating speed and the accuracy. In the second part, we combine Self-trans and DenseNet-169, and the result shows that when doing data augmentation, many model performance metrics have been improved. In the third part, we use UNet++, which reaches accuracy of 0.8645. Apart from this, we think GAN and CNN may also make difference.


Keywords


Covid-19; DenseNet-169; Data Augmentation; CT Images

Full Text:

PDF

References


Technicolor, T. , Related, S. , Technicolor, T. , & Related, S.. ImageNet Classification with Deep Convolutional Neural Networks [50].

Shorten, C., & Khoshgoftaar, T. M.. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1).

Iandola, F., Moskewicz, M., Karayev, S., Girshick, R., & Keutzer, K.. (2014). Densenet: implementing efficient convnet descriptor pyramids. Eprint Arxiv.

Ardakani, A. A., Kanafi, A. R., Acharya, U. R., Khadem, N., & Mohammadi, A.. (2020). Application of deep learning technique to manage covid-19 in routine clinical practice using ct images: results of 10 convolutional neural networks. Computers in Biology and Medicine, 121.

Li, Z., Zhao, S., Chen, Y., Luo, F., Kang, Z., Cai, S., ... & Li, Y. (2021). A deep-learning-based framework for severity assessment of COVID-19 with CT images. Expert Systems with Applications, 185, 115616.

Zhou, L., Li, Z., Zhou, J., Li, H., & Gao, X.. (2020). A rapid, accurate and machine-agnostic segmentation and quantification method for ct-based covid-19 diagnosis. IEEE Transactions on Medical Imaging, 39(8), 2638–2652.

Taylor, L., & Nitschke, G. (2018). Improving Deep Learning with Generic Data Augmentation. In 2018 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 1542–1547).

Sameena Pathan, P.C. Siddalingaswamy, Preetham Kumar, Manohara Pai M M, Tanweer Ali, U. Rajendra Acharya, Novel ensemble of optimized CNN and dynamic selection techniques for accurate Covid-19 screening using chest CT images, Computers in Biology and Medicine, Volume 137,2021,104835, ISSN 0010-4825.

Md. Kamrul Hasan, Md. Tasnim Jawad, Kazi Nasim Imtiaz Hasan, Sajal Basak Partha, Md. Masum Al Masba, Shumit Saha, Mohammad Ali Moni, COVID-19 identification from volumetric chest CT scans using a progressively resized 3D-CNN incorporating segmentation, augmentation, and class-rebalancing, Informatics in Medicine Unlocked, Volume 26,2021,100709.

Ş. Öztürk, U. Özkaya, M. Barstuğan Classification of Coronavirus (COVID‐19) from X‐ray and CT images using shrunken features Int. J. Imag. Syst. Technol., 31 (2021), pp. 5-15.

C. Priya, S.M.H. Sithi Shameem Fathima, N.

Kirubanandasarathy, A. Valanarasid, M.H. Safana Begam, N. Aiswarya, Automatic optimized CNN based COVID-19 lung infection segmentation from CT image, Materials Today: Proceedings,2021.

Ilyas LAHSAINI, Mostafa EL HABIB DAHO, Mohamed Amine CHIKH, Deep transfer learning based classification model for covid-19 using chest CT-scans, Pattern Recognition Letters, Volume 152,2021, Pages 122-128, ISSN 0167-8655.

Pham TD. A comprehensive study on classification of COVID-19 on computed tomography with pretrained convolutional neural networks. Sci Rep. 2020 Oct 9;10(1):16942.

He, XH., Yang, XY., Zhang, SH., Zhao, JY., Zhang, YC., Xing, E., Xie, PT., Sample-Efficient Deep Learning for COVID-19 Diagnosis Based on CT ScansmedRxiv 2020.04.13.20063941.

Halgurd S. Maghdid, Aras T. Asaad, Kayhan Zrar Ghafoor, Ali Safaa Sadiq, Seyedali Mirjalili, and Muhammad Khurram Khan "Diagnosing COVID-19 pneumonia from x-ray and CT images using deep learning and transfer learning algorithms", Proc. SPIE 11734, Multimodal Image Exploitation and Learning 2021, 117340E (12 April 2021).

Hong, G., Chen, X., Chen, J. et al. A multi-scale gated multi-head attention depth-wise separable CNN model for recognizing COVID-19. Sci Rep 11, 18048 (2021).

M. Polsinelli, L. Cinque, G. Placidi A Light CNN for Detecting COVID-19 from CT Scans of the Chest arXiv preprint arXiv: 2004. 12837 (2020).

S. Hu et al., "Weakly Supervised Deep Learning for COVID-19 Infection Detection and Classification From CT Images," in IEEE Access, vol. 8, pp. 118869-118883, 2020.

Rohit Kundu, Pawan Kumar Singh, Seyedali Mirjalili, Ram Sarkar, COVID-19 detection from lung CT-Scans using a fuzzy integral-based CNN ensemble, Computers in Biology and Medicine, Volume 138, 2021, 104895.

A.A. Ardakani, U.R. Acharya, S. Habibollahi, A. Mohammadi COVIDiag: a clinical CAD system to diagnose COVID-19 pneumonia based on CT findings Eur. Radiol., 31 (1) (2021), pp. 121-130.

He, XH., et al. "Sample-efficient deep learning for COVID-19 diagnosis based on CT scans." medrxiv (2020).

Jason Brownlee. “How to Configure the Learning Rate When Training Deep Learning Neural Networks”.

Yan, W., “A Summary of Semi Supervised Learning”.

Shorten, C., Khoshgoftaar, T.M. A survey on Image Data Augmentation for Deep Learning. J Big Data 6, 60 (2019).

Pham, T.D. “A comprehensive study on classification of COVID-19 on computed tomography with pretrained convolutional neural networks”. Sci Rep 10, 16942 (2020).

Goodfellow, Ian, et al. "Generative adversarial nets." Advances in neural information processing systems 27 (2014).

Iandola, F., et al. "Densenet: Implementing efficient convnet descriptor pyramids." arXiv preprint arXiv:1404.1869 (2014).

Liu, Z., et al. "Swin transformer: Hierarchical vision transformer using shifted windows." arXiv preprint arXiv: 2103. 14030 (2021).

Li, XM., et al. "H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes." IEEE transactions on medical imaging 37.12 (2018): 2663-2674.

Zhang, HY., et al. "mixup: Beyond empirical risk minimization." arXiv preprint arXiv:1710.09412 (2017).

A. Krizhevsky, I. Sutskever, G.E. Hinton Imagenet classification with deep convolutional neural networks Commun. ACM, 60 (6) (2017), pp. 84-90.




DOI: http://dx.doi.org/10.18686/aem.v11i3.299

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.