Resumen
Este documento presenta el diseño de una aplicación para detectar covid-19 utilizando redes neuronales convolucionales e imágenes de rayos X en dos escenarios (covid/No-covid y covid/Normal/Neumonía). Para evitar el sobreajuste, se utilizó aumento de datos, dropout, normalización por lotes y optimizador Adam. La red para tres clases se utilizó como modelo pre-entrenado ajustando solo la capa densa y de salida para obtener el modelo binario. Además, se realizó una optimización automatizada de hiper-parámetros como dropout, funciones de activación y número de neuronas. La tasa de aprendizaje se ajustó mediante callbacks para evadir óptimos locales. Las redes fueron convertidas al formato TensorFlow.js para integrarse en una aplicación híbrida utilizando Ionic y Capacitor, y se desplegaron mediante Firebase para brindar asistencia y soporte al generar diagnósticos. La aplicación obtuvo una exactitud del 98.61% y 96.48% para dos y tres clases, respectivamente, logrando mayor rendimiento que otras propuestas y utilizando menos parámetros de entrenamiento.
Citas
American College of Radiology (ACR). (March 11, 2020). ACR Recommendations for the use of chest radiography and computed tomography (CT) for suspected covid-19 infection. https://www.acr.org/Advocacy-and-Economics/ACR-Position-Statements/Recommendations-for-Chest-Radiography-and-CT-for-Suspected-covid19-Infection
Beysolow II, T. (2017). Introduction to deep learning using R. A step-by-step guide to learning and implementing deep learning models using R. Apress.
Bosowski, P., Bosowska, J., & Nalepa, J. (2021). Evolving deep ensembles for detecting covid-19 in chest X-Rays. IEEE International Conference on Image Processing (ICIP), 3772-3776. https://doi.org/10.1109/ICIP42928.2021.9506119
Chollet, F. (2018). Deep learning with Python. Manning Publications Co.
Chung, M., Bernheim, A., Mei, X., Zhang, N., Huang, M., Zeng, X., Cui, J., Xu, W., Yang, Y., Fayad, Z. A., Jacobi, A., Li, K. S., & Shan, H. (2020). CT Imaging features of 2019 novel coronavirus (2019-nCoV). Radiology, 295(1). https://doi.org/10.1148/radiol.2020200230
Chung, A. (2020). Actualmed covid-19 chest x-ray data initiative. https://github.com/agchung/Actualmed-covid-chestxray-dataset
Clevert, D. A., Unterthiner, T., & Hochreiter, S. (2016). Fast and accurate deep network learning by exponential linear units (ELUs). Johannes Kepler University, Linz, Australia, pp. 1-14. arXiv:1511.07289v5
Cohen, J., Morrison, P., & Dao, L. (2020). covid-19 image data collection: prospective predictions are the future. https://github.com/ieee8023/covid-chestxray-dataset
European Society of Radiology (ESR). (2021). [Eurorad]. https://www.eurorad.org/advanced-search?search=covid&sort_by=published_at&sort_order=DESC&page=5
Github. (2020). covid-19 Chest X-Ray Dataset Initiative. https://github.com/agchung/Figure1-covid-chestxray-dataset
Google. (2023). Firebase. https://firebase.google.com/
Gutierrez, A., Ansuategi, A., Susperregi, L., Tubío, C., Rankic, I., & Lenza, L. (2019). A benchmarking of learning strategies for pest dete and identification on tomato plants for autonomous scouting robots using internal databases. Journal of Sensors, 2019(1), 1-16. https://doi.org/10.1155/2019/5219471
Ioannis, D. A., & Tzani, B. (2020). covid-19: automatic detection from X-Ray images utilizing transfer learning with convolutional neural networks. arXiv:2003.11617
Ionic. (2023). Cross-platform mobile App development: Ionic framework. https://ionicframework.com/
Jacobi, A., Chung, M., Bernheim, A., & Eber, C. (2020). Portable chest X-ray in coronavirus disease-19 (covid-19): a pictorial review. Clinical Imaging, 64, 35-42. https://doi.org/10.1016/j.clinimag.2020.04.001
Kaggle Inc. (2023). Chest X-Ray images (Pneumonia). https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
Loey, M., Smarandache, F., & Khalifa, N. E. M. (2020). Within the lack of chest covid-19 X-ray dataset: a novel detection model based on GAN and deep transfer learning. Symmetry, 12(4), 1-19. https://doi.org/10.3390/sym12040651
Mahmud, T., Rahman, M. A., & Fattah, S. A. (2020). 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. Computers in Biology and Medicine, 122, 103869. https://doi.org/10.1016/j.compbiomed.2020.103869
Narin, A., Kaya, C., & Pamuk, Z. (2020). Automatic detection of coronavirus disease (covid-19) using X-ray images and deep convolutional neural networks. arXiv:2003.10849
Ozturk, T., Talo, M., Yildirim, E. A., Baloglu, U. B., & Yildirim, O. (2020). Automated detection of covid-19 cases using deep neural networks with X-ray images. Computers in Biology and Medicine, 121, 1-11. https://doi.org/10.1016/j.compbiomed.2020.103792
Pedamonti, D. (2018). Comparison of non-linear activation functions for deep neural networks on MNIST classification task. arXiv:1804.02763v1
Radiopaedia. (2021). [covid-19]. Radiopaedia.org. https://radiopaedia.org/articles/covid-19-4?lang=us
Rahimzadeh, M., & Attar, A. (2020). A modified deep convolutional neural network for detecting covid-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2. Informatics in Medicine Unlocked, 19, 1-9. https://doi.org/10.1016/j.imu.2020.100360
Rong, G., Mendez, A., Assi, E. B., Zhao, B., & Sawan, M. (2020). Artificial Intelligence in Healthcare: review and prediction case studies. Engineering, 6(3), 291–301. https://doi.org/10.1016/j.eng.2019.08.015
Rosebrock, A. (2017). Deep learning for computer vision with Python. PyImageSearch.
SAS Institute Inc. (2023). Machine learning: What it is and why it matters SAS. https://www.sas.com/en_us/insights/analytics/machine-learning.html#machine-learning-importance
Sethy, P. K., & Behera, S. K. (2020). Detection of coronavirus disease (covid-19) based on deep features. Preprints.org. https://doi.org/10.20944/preprints202003.0300.v1
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2015). Striving for simplicity: the all convolutional net. arXiv:1412.6806v3
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from over. Journal of Machine Learning Research, 15, 1929-1958.
Tensorflow. (2023). TensorFlow.js | Machine Learning for JavaScript Developers. TensorFlow.org.
The Italian Society of Medical and Interventional Radiology (SIRM). (2020). [covid-19 database]. https://www.sirm.org/en/category/articles/covid-19-database/
Wang, J., Ma, Y., Zhang, L., Gao, R., & Wu, D. (2018). Deep learning for smart manufacturing: methods and applications. Journal of Manufacturing Systems, 48, 1-13. https://doi.org/10.1016/j.jmsy.2018.01.003
Wang, L., Lin, Z. Q., & Wong, A. (2020). covid-Net: a tailored deep convolutional neural network design for detection of covid-19 cases from chest X-Ray images. arXiv:2003.09871
World Health Organization (WHO). (June 06, 2020). Coronavirus disease (covid-19) pandemic. https://www.who.int/emergencies/diseases/novel-coronavirus-2019
World Health Organization (WHO). (2022). Coronavirus. https://www.who.int/health-topics/coronavirus#tab=tab_1
Wuest, T., Weimer, D., Irgens, C., & Thoben, K. D. (2016). Machine learning in manufacturing: advantages, challenges, and applications. Production & Manufacturing Research, 4(1), 23-45. https://doi.org/10.1080/21693277.2016.1192517
Yu, T., & Zhu, H. (2020). Hyper-Parameter optimization: a review of algorithms and applications. arXiv:2003.05689
Zhou, S., Wang, Y., Zhu, T., & Xia, L. (2020). CT features of coronavirus disease 2019 (covid-19). American Journal of Roentgenology, 214(6), 1287-1294. https://doi.org/10.2214/AJR.20.22975