X-Ray Images Analysis by Medium Artificial Neural Network
Abstract
Currently the world is affected by a new strain of coronavirus called SARS-2, which is the cause of a respiratory-type infectious disease called Covid-19; the symptoms are fever, dry cough, shortness of breath, tiredness and in some more severe cases it can cause pneumonia, leading to death. According to the world health organization, the disease originated in Wuhan-China and spread rapidly throughout the world, causing serious health problems for populations without finding an effective cure or treatment to help prevent death and control its spread. Health specialists have not been able to find an effective cure that prevents the spread of the virus, although there are mechanisms to detect the disease, one of the most effective is related to the analysis of X-ray images of the chest of a patient; Manually processing a group of patient images is time consuming, so processing large volumes of images makes it impossible to promptly treat patients if the virus is detected. In the present manuscript, an X-ray image analysis mechanism is exposed, which uses artificial intelligence; and through a machine learning technique, through an algorithm based on artificial neural networks, a program is able to apply machine learning and learn to recognize patterns in chest images of infected and healthy patients, so that it can classify, predict and detect one if a new image is of a infected or healthy patient.
Downloads
Metrics
References
Abhishek, N. (2018). Reinforcement learning with Open AI, TensorFlow and Keras Using Python. In Learning (Vol. 3).
Abhishek Sharma. (2018). Confusion Matrix in Machine Learning. Www.Geeksforgeeks.Org.
Aurélien Géron. (2019). Hands-on machine learning with Scikit-Learn, Keras and TensorFlow: concepts, tools, and techniques to build intelligent systems. In O’Reilly Media.
B S, L. (2021). Data Analysis and Data Classification in Machine Learning using Linear Regression and Principal Component Analysis. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(2). https://doi.org/10.17762/turcomat.v12i2.1092
Baltazar, G. (2018). CPU vs GPU in Machine Learning.
Calvache, J. M. M., Rodríguez, A. D. E., Martínez, C. B. C., & Paucar, V. A. V. (2020). Utilidad de Pruebas de cadena de polimerasa, pruebas rápidas y Tomografías en pacientes con Covid-19. Journal of America Health, 3(2), 32–39. https://doi.org/10.37958/JAH.V3I2.28
Cristina Coello, B. N. (n.d.). Pruebas de antígeno, la nueva herramienta en la detección de la COVID-19. Retrieved July 6, 2021, from https://www.edicionmedica.ec/secciones/salud-publica/pruebas-de-antigeno-la-nueva-herramienta-en-la-deteccion-de-la-covid-19--96534
Douglass, M. J. J. (2020). Book Review: Hands-on Machine Learning with Scikit-Learn, Keras, and Tensorflow, 2nd edition by Aurélien Géron. Physical and Engineering Sciences in Medicine, 43(3). https://doi.org/10.1007/s13246-020-00913-z
Giancarlo Zaccone, Md. Rezaul Karim, A. M., Brownlee, J., Vasilev, I., Slater, D., Spacagna, G., Roelants, P., … Singh, A. (2019). Deep Learning With Python Develop Deep Learning Models On Theano And TensorFlow Using Keras. Machine Learning Using R, 26(3).
Grando, R. D., Brentano, V. B., Zanardo, A. P., Hertz, F. T., Anflor Júnior, L. C., Prietto dos Santos, J. F., … Gazzana, M. B. (2020). braz j infect dis 2 0 2 0;2 4(6):524-533 Clinical usefulness of tomographic standards for COVID-19 pneumonia diagnosis: Experience from a Brazilian reference center. https://doi.org/10.1016/j.bjid.2020.10.002
Haghighat, E., & Juanes, R. (2021). SciANN: A Keras/TensorFlow wrapper for scientific computations and physics-informed deep learning using artificial neural networks. Computer Methods in Applied Mechanics and Engineering, 373. https://doi.org/10.1016/j.cma.2020.113552
Home, & KidsHealth. (n.d.). Tomografía computada: tórax. Retrieved July 7, 2021, from https://www.brennerchildrens.org/KidsHealth/Padres/Centro-de-informacion-sobre-el-cancer/Posibles-examenes/Tomografia-computada-torax.htm?__t=2835
Infosalud. (n.d.). La tomografía de tórax es la mejor prueba para diagnosticar el coronavirus, según estudio. Retrieved July 6, 2021, from https://www.infosalus.com/asistencia/noticia-tomografia-torax-mejor-prueba-diagnosticar-coronavirus-estudio-20200227171650.html
Karlijn Willems. (2019). (Tutorial) KERAS Tutorial: DEEP LEARNING in PYTHON - DataCamp.
Liu, R., Fu, A., Deng, Z., Li, Y., & Liu, T. (2020). Promising methods for detection of novel coronavirus SARS‐CoV‐2. View, 1(1). https://doi.org/10.1002/VIW2.4
López, P., Ballesté, R., Seija, V., López, P., Ballesté, R., & Seija, V. (2020). Diagnóstico de laboratorio de COVID-19. Revista Médica Del Uruguay, 36(4), 131–155. https://doi.org/10.29193/RMU.36.4.7
Martinez, J. (2020, October). Precision, Recall, F1, Accuracy en clasificación - IArtificial.net.
Moolayil, J. (2019). Learn Keras for Deep Neural Networks. In Learn Keras for Deep Neural Networks. https://doi.org/10.1007/978-1-4842-4240-7
Müller, A. C., & Guido, S. (2015). Introduction to Machine Learning with Python and Scikit-Learn. In O’Reilly Media, Inc.
Paluszek, M., Thomas, S., Paluszek, M., & Thomas, S. (2020). What Is Deep Learning? In Practical MATLAB Deep Learning. https://doi.org/10.1007/978-1-4842-5124-9_1
Panesar, A. (2021). What Is Machine Learning? In Machine Learning and AI for Healthcare. https://doi.org/10.1007/978-1-4842-6537-6_3
Rocha, C. (n.d.). ¿Cómo se puede Diagnosticar el COVID-19? ¿Cuál es la Precisión de los Test Diagnósticos? | sociedadandaluzadeoftalmologia.es. Retrieved July 7, 2021, from https://sociedadandaluzadeoftalmologia.es/como-se-puede-diagnosticar-el-covid-19-cual-es-la-precision-de-los-test-diagnosticos/
Tablado, F. (n.d.). Inteligencia artificial: Definición, tipos y aplicaciones | Grupo Atico34. Retrieved July 6, 2021, from https://protecciondatos-lopd.com/empresas/inteligencia-artificial/
Zou, D., Cao, Y., Zhou, D., & Gu, Q. (2020). Gradient descent optimizes over-parameterized deep ReLU networks. Machine Learning, 109(3). https://doi.org/10.1007/s10994-019-05839-6
PDF (Español (España)) 484
Authors maintain the rights to the articles and are therefore free to share, copy, distribute, execute, and publicly communicate the work on their personal websites or in institutional deposits, after its publication in this journal, as long as they provide bibliographic information that certifies its publication in this journal.
The works are under one https://creativecommons.org/licenses/by-nc-nd/4.0/