Abstract
Since COVID-19 appeared in 2019, detection methods based on medical images depend on the criteria of the specialist. This paper shows the optimization process of an autonomous image-based learning system. To improve the classification of positive images for COVID-19, obtained from a simple chest tomography, expert judgment and singular value decomposition are used. A computed tomography scan generates images in dicom format that must be converted to jpg or bmp format, so it is necessary to determine which format has better resolution. With the new processed images, matrix of size 145 × 145, a dataset is formed to train the neural network. When obtaining the neural network model, a reduction in training times between processed and unprocessed images is observed. Likewise, the predictions of the neural network, developed in python, for the detection of COVID-19 with processed images indicate results over 98%. Another important result is that singular value decomposition can be used to determine that images in bmp format provide more detail than images in jpg format, working with 90% of the original information in the image. Finally, the image classification is improved and the neural network is optimized.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Proaño, C.: On the macroeconomic and social impact of the coronavirus pandemic in Latin America and the developing world. Intereconomics 55, 159–162 (2020)
Sun, J., Aghemo, A., Forner, A., Valenti, L.: COVID-19 and liver disease. Liver Int. 40(6), 1278–1281 (2020)
Karaye, I., Horney, J.: The impact of social vulnerability on COVID-19 in the US: an analysis of spatially varying relationships. Am. J. Prev. Med. 59(3), 317–325 (2020)
Molina, N., Mejias, M.: Social impact of COVID-19 in Brazil and Ecuador: where reality surpasses the statistics. Edumecentro 12(3), 277–283 (2020)
Calvache, J., Rodríguez, A., Martínez, C., Paucar, V.: Usefulness of polymerase chain tests, rapid tests and CT scans in patients with Covid-19. J. Am. Health 3(2), 32–39 (2020)
Pareja, J., Anicama, S., Perez, P., Pecho, S., Amado, J.: Importance of the implementation of the chest tomography to contribute to the early diagnosis and timely triage of patients with COVID-19 in Peruvian hospitals. Acta Méd. Peruana 37(2), 239–241 (2020)
Pham, T.: A comprehensive study on classification of COVID-19 on computed tomography with pretrained convolutional neural networks. Sci. Rep. 10(1), 1–8 (2020)
Gorina, A., Berenguer, I., Salgado, A., Álvarez, J.: The management of scientific information provided by the criteria of experts. Ciencias de la Información 45(2), 39–47 (2014)
Badii, M., Castillo, J., Guillen, A.: Optimal sample size. Innovaciones de negocios 5(9), 53–65 (2017)
Lyra, D., Carvalho, J., Azevedo, J.: Enhanced reconstruction of magnetic resonance data using singular value decomposition approximation. Ingeniería 17(2), 35–45 (2012)
MathWorks homepage. https://la.mathworks.com/help/matlab/ref/double.svd.html;jsessionid=7c0d111aa3913e4333866507c1e9. Accessed 21 Nov 2016
Li, Y., Ma, W., Zhao, Y.: Application of digital image processing technology based on artificial intelligence in the analysis of medical images. Invest. Clin. 60(6), 1548–1561 (2019)
Smith, L.N.: A disciplined approach to neural network hyper-parameters: Part 1-learning rate, batch size, momentum, and weight decay, pp. 1–21. ArXiv, arXiv:1803.09820 (2018)
Colab. https://colab.research.google.com/. Accessed 23 Mar 2021
Singh, D., Kumar, V., Kaur, M.: Classification of COVID-19 patients from chest CT images using multi-objective differential evolution–based convolutional neural networks. Eur. J. Clin. Microbiol. Infect. Dis. 39(7), 1379–1389 (2020)
Varela, S., Melin, P.: A new approach for classifying coronavirus COVID-19 based on its manifestation on chest X-rays using texture features and neural networks. Inf. Sci. 545, 403–414 (2021)
Mahmud, T., Rahman, M., Fattah, S.: CovXNet: a multi-dilation convolutional neural network for automatic COVID-19 and other pneumonia detection from chest X-ray images with transferable multi-receptive feature optimization. Comput. Biol. Med. 122, 103869 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Matlab and Python code used in this study is available in: https://drive.google.com/drive/folders/1rF5z-F22Gz0Vn_g3Y6uwq_bStaVFNTdq?usp=sharing.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bastidas-Chalán, R., Medina, P. (2022). Optimization of an Autonomous Learning Model for Detection COVID-19 Using Medical Images. In: Botto-Tobar, M., Cruz, H., Díaz Cadena, A., Durakovic, B. (eds) Emerging Research in Intelligent Systems. CIT 2021. Lecture Notes in Networks and Systems, vol 405. Springer, Cham. https://doi.org/10.1007/978-3-030-96043-8_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-96043-8_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96042-1
Online ISBN: 978-3-030-96043-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)