Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Informática y Sistem...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 2 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Inteligencia artificial aplicada a la oftalmología: ResNet-50 y VGG-19 en el diagnóstico de catarata y glaucoma

Authors: Leonardo Paul Sanchez Davila; Ruth Evelyn Rogel Rivera; Joofre Antonio Honores Tapia; Wilmer Braulio Rivas Asanza;

Inteligencia artificial aplicada a la oftalmología: ResNet-50 y VGG-19 en el diagnóstico de catarata y glaucoma

Abstract

El auge de la tecnología está produciendo importantes cambios a nivel mundial, sobre todo en materia de inteligencia artificial (IA). Actualmente las grandes compañías han emprendido acciones y destinan gran parte de sus recursos al desarrollo de tecnologías que permitan automatizar diferentes actividades, entre ellas las del sector de la salud. En tal sentido, la oftalmología ha captado la atención de una rama de la IA, las redes neuronales convolucionales (RNC), debido a que puede ser provista de suficientes datos para garantizar niveles altos de predicción en la detección de enfermedades/anomalías oculares. En esta investigación se rediseñaron veinticuatro algoritmos a partir de las estructuras ResNet-50 y VGG-19, modificando las entradas (conjuntos de 15, 25 y 35 imágenes) y los ciclos de propagación (20 y 25 épocas), con el objetivo de optimizar el nivel de precisión en el diagnóstico de catarata y glaucoma; además, se utilizó el estadístico U de Mann Whitney para comparar los valores medios de los parámetros pérdida, precisión, rendimiento y tiempo, logrando identificar que solamente en este último las diferencias son estadísticamente significativas. Los resultados revelaron que el algoritmo más eficiente en el diagnóstico de catarata fue desarrollado a partir de la estructura VGG-19 con 25 imágenes tomadas como entrada con 20 épocas de entrenamiento; por su parte, no se lograron obtener niveles de precisión adecuados para el diagnóstico de glaucoma.

Keywords

catarata, glaucoma, inteligencia artificial, oftalmología, Electronic computers. Computer science, QA75.5-76.95, redes neuronales convolucionales

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
gold
Related to Research communities