A computer aided medical classification system of COVID-19 CT lung scans using convolution neural networks

被引：0
作者：
Cohen M.W. [1 ]
Gilo O. [1 ]
David L. [1 ]
机构：
[1] Braude College of Engineering, Israel
来源：
Computer-Aided Design and Applications | 2022年 / 19卷 / 03期
关键词：
Convolution neural network (CNN); COVID-19; Lung CT-scans;
D O I：
10.14733/CADAPS.2022.522-533
中图分类号：
学科分类号：
摘要：
The CT scan is an important diagnostic procedure for COVID-19. CT images tend to reveal similar features in most COVID-19 cases, including ground-glass opacity in the early stages and pulmonary consolidation in the later stages. The work presented here demonstrates the feasibility of developing a classification system for Covid-19 CT lung scans, which would assist doctors in distinguishing COVID-19 from healthy cases. Three architec-tures, ResN50, Inception-V3, and Xception, were trained, validated, and tested to achieve the highest accuracy. Furthermore, the influence of hyper-parameters on the accuracy of each model was evaluated, searching for minimal loss values. With this system, classification of CT scans can be performed. © 2022 CAD Solutions, LLC.
引用
收藏
页码：522 / 533
页数：11
相关论文
共 24 条
  • [1] Borgert J., Schmidt J.D., Schmale I., Bontus C., Gleich B., David B., Weizenecker J., Jockram J., Lauruschkat C., Mende O., Et al., Perspectives on clinical magnetic particle imaging, Biomedical Engi-neering/Biomedizinische Technik, 58, 6, pp. 551-556, (2013)
  • [2] Cheng J., Wang P.s., Li G., Hu Q.h., Lu H.q., Recent advances in efficient computation of deep convolutional neural networks, Frontiers of Information Technology & Electronic Engineering, 19, 1, pp. 64-77, (2018)
  • [3] Chin W.S., Zhuang Y., Juan Y.C., Lin C.J., A learning-rate schedule for stochastic gradient methods to matrix factorization, Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 442-455, (2015)
  • [4] Chollet F., Xception: Deep learning with depthwise separable convolutions, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1251-1258, (2017)
  • [5] (2020)
  • [6] (2020)
  • [7] Fang Y., Zhang H., Xie J., Lin M., Ying L., Pang P., Ji W., Sensitivity of chest ct for covid-19: comparison to rt-pcr, Radiology, 296, 2, pp. E115-E117, (2020)
  • [8] Geirhos R., Rubisch P., Michaelis C., Bethge M., Wichmann F.A., Brendel W., Imagenet-trained cnns are biased towards texture
  • [9] increasing shape bias improves accuracy and robustness, (2018)
  • [10] Gozes O., Frid-Adar M., Greenspan H., Browning P.D., Zhang H., Ji W., Bernheim A., Siegel E., Rapid ai development cycle for the coronavirus (covid-19) pandemic: Initial results for automated detection & patient monitoring using deep learning ct image analysis, (2020)
123