Digital Analysis of fetal lung ultrasound using deep learning techniques
Article Sidebar
Main Article Content
Abstract
Worldwide, about 15 million infants are born each year without completing their gestational stage.According to data from the World Health Organization in the "WHO Recommendations for the care of preterm or low birth weight infants", 45% of all deaths of infants under 5 years of age, 60% to 80% are premature due to major respiratory deficiencies. Lung malformation results in induced abortion or Respiratory Distress Syndrome (RDS). RDS can be prevented by clinical studies and radiological criteria. This work addresses the task of identifying malformations using digital analysis of fetal lung images using deep learning tools in a multiclass categorization of bronchopulmonary sequestration, cystic malformations and diaphragmatic hernia, where there is a risk of misdiagnosis and death. Resulting in a model accuracy of 88.88%, from a set of 42 two-dimensional sonograms.
Article Details
References
Albinagorta Olórtegui, R., & Miranda Tapia, M. (2015). Actualización en la evaluación de la madurez pulmonar fetal por ultrasonido. Revista Peruana de Ginecología y Obstetricia, 61(4), 433–438.
Brownlee, J. (2020). 3 ways to encode categorical variables for deep learning. Machine Learning Mastery. https://machinelearningmastery.com/how-to-prepare-categorical-data-for-deep-learning-in-python/
Brownlee, J. (2020). How to use metrics for deep learning with Keras in Python. Machine Learning Mastery. https://machinelearningmastery.com/custom-metrics-deep-learning-keras-python/
Brownlee, J. (2021). Sensitivity analysis of dataset size vs. model performance. Machine Learning Mastery. https://machinelearningmastery.com/sensitivity-analysis-of-dataset-size-vs-model-performance
Chollet, F. (2017). The limitations of deep learning. In Deep learning with Python. Manning Publications.
Espinosa Arreaga, G. B., & Lucio Aldaz, C. (2020). Diagnóstico de malformaciones congénitas en embarazadas de 30 a 40 años mediante screening ecográfico en el hospital gineco obstétrico pediátrico universitario de Guayaquil. Universidad de Guayaquil, Ecuador.
Hernández Sancho, R., & Rojas Maruri, M. (2020). Secuestro pulmonar: Opciones de tratamiento desde la perspectiva de las teorías embrionarias. Acta Pediátrica de México, 41(2), 72–84.
Álvarez, L., Lozano, C., & Bravo, D. (2022). Metodología para el mantenimiento predictivo de transformadores de distribución basada en aprendizaje automático. Ingeniería, 27(3), e17742.
Vega, R., González, J., Valdés, E., González, A., del Olmo Bautista, S., & Camino, F. (2015). Malformación adenomatoide quística pulmonar: Diagnóstico prenatal. Clínica e Investigación en Ginecología y Obstetricia, 42(2), 83–85.
Wiley, V., & Lucas, T. (2018). Computer vision and image processing: A paper review. International Journal of Artificial Intelligence Research, 2(1), 29–36. https://doi.org/10.29099/ijair.v2i1.42
World Health Organization. (2022). WHO recommendations for care of the preterm or low-birth-weight infant. https://www.who.int/publications/i/item/9789240058262
Zuñiga Vico, I., Gila Sánchez, M., & Hurtado Sánchez, F. (2023). Diagnóstico ecográfico de la madurez pulmonar fetal. Journal of Physiotherapy and Medical Technology, 7, 7–18.