Artificial intelligence applied to ophthalmology: ResNet-50 and VGG-19 in cataract and glaucoma diagnosis
DOI:
https://doi.org/10.33936/isrtic.v8i2.6641Keywords:
artificial intelligence, ophthalmology, convolutional neural networks, cataract, glaucomaAbstract
The rise of technology is producing important changes worldwide, especially in the field of artificial intelligence. Currently, large companies have taken action and are devoting a large part of their resources to the development of technologies to automate different activities, including those in the healthcare sector. In this regard, ophthalmology has captured the attention of a branch of artificial intelligence, convolutional neural networks, because it can be provided with sufficient data to guarantee high levels of prediction in the detection of ocular diseases/anomalies. In this research, twenty-four algorithms were redesigned from the ResNet-50 and VGG-19 structures, modifying the inputs (sets of 15, 25 and 35 images) and the propagation cycles (20 and 25 epochs), with the aim of optimizing the level of accuracy in the diagnosis of cataract and glaucoma; in addition, the Mann Whitney U statistic was used to compare the mean values of the parameters loss, accuracy, performance and time, managing to identify that only in the latter the differences are statistically significant. The results revealed that the most efficient algorithm in the diagnosis of cataract was developed from the VGG-19 structure with 25 images taken as input with 20 training epochs; on the other hand, adequate levels of accuracy were not obtained for the diagnosis of glaucoma.
Downloads
References
Álvarez, D., Arévalo, A., Benavides, I., Salazar, C., & Betancourth, C. (2023). Use of Trained Convolutional Neural Networks for Analysis of Symptoms Caused by Botrytis fabae Sard. Revista de Ciencias Agrícolas, 40(1), 1-13. https://doi.org/10.22267/rcia.20234001.198
Analuisa-Aroca, I., Vergara-Romero, A., & Pérez, I. (2023). Redes neuronales convolucionales ResNet-50 para la detección de gorgojo en granos de maíz. Scientia Agropecuaria, 14(3), 385-394. https://doi.org/10.17268/sci.agropecu.2023.034
Borja, M., Pérez, M., & Luna, R. (2020). Beneficios ofrecidos por la gestión del Big Data en las instituciones gubernamentales en la era de la digitalización. Revista La Propiedad Inmaterial(30). https://go.gale.com/ps/i.doid=GALE%7CA648058028&sid=googleScholar&v =2.1&it=r&linkaccess=abs&issn=16571959&p=IFME&sw=w&userGroupName =anon%7Ef426e03f&aty=open-web-entry
Carron, A., Araujo, D., Medve, G., Torres, J., & Arrúa, M. (2021). Exactitud de las fórmulas de cálculo del poder de Lente Intraocular en Cirugía de Cataratas. Comparación de 8 fórmulas. Anales de la Facultad de Ciencias Médicas (Asunción), 54(2), 25-32. https://doi.org/https://doi.org/10.18004/anales/2021.054.02.25
Cifuentes, A., Mendoza, E., Lizcano, M., Santrich, A., & Moreno-Trillos, S. (2019). Desarrollo de una red neuronal convolucional para reconocer patrones en imágenes. Investigación y Desarrollo en TIC, 10(2), 7-17. https://revistas.unisimon.edu.co/index.php/identic/article/view/4007/4359
Costales, H., Callejo-Arruejo2, A., & Rafanan, N. (2020). Development of a Prototype Application for Rice Disease Detection Using Convolutional Neural Networks. International Journal of Emerging Trends in Engineering Research, 8(10), 7076-7081. https://doi.org/10.30534/ijeter/2020/708102020
Estupiñán, J., Leyva, M., Peñafiel, A., & El Assafiri, Y. (2021). Inteligencia artificial y propiedad intelectual. Revista Universidad y Sociedad, 13(S3), 362-368. https://rus.ucf.edu.cu/index.php/rus/article/download/2490/2445/
García, K., Vélez, V., Narváez, O., & Trujillo, M. (2020). Hallazgos clínicos en retinosis pigmentaria por examen visual, campimetría y retinografía en Colombia. Ciencia y Tecnología para la Salud Visual y Ocular, 18(2), 55-64. https://doi.org/https://doi.org/10.19052/sv.vol18.iss2.6
Guevara, R., & Augusto, C. (2023). Aplicación de redes neuronales densas y convolucionales para detección de COVID_19 en imágenes de rayos X. Revista Conectividad, 4(2), 19-32. https://doi.org/10.37431/conectividad.v4i2.78
Hernández, I. (2024). La inteligencia artificial y su impacto en la atención oftalmológica. Revista Cubana de Oftalmología, 37, 1-3. https://revoftalmologia.sld.cu/index.php/oftalmologia/article/view/1844/pdfq
Lozada-Portilla, W., Suarez-Barón, M., & Avendaño-Fernández, E. (2021). Aplicación de redes neuronales convolucionales para la detección del tizón tardío Phytophthora infestans en papa Solanum tuberosum. Revista U.D.C.A Actualidad & Divulgación Científica, 24(2), 1-9. https://doi.org/10.31910/rudca.v24.n2.2021.1917
Magallanes, K., Plúas, L., Aguas, J., & Freire, R. (2023). La inteligencia artificial aplicada en la innovación educativa en el proceso de enseñanza y aprendizaje. LATAM Revista Latinoamericana de Ciencias Sociales y Humanidades, IV(2), 1597-1613. https://doi.org/10.56712/latam.v4i2.706
Mera-Jiménez, L., & Ochoa-Gómez, J. (2021). Redes neuronales convolucionales para la clasificación de componentes independientes de rs-fMRI. TecnoLógicas, 24(50), 1-20. https://doi.org/10.22430/22565337.1626
Perdomo-Charry, O., Pérez, A., de-la-Pava-Rodríguez, M., Ríos-Calixto, H., Arias-Vanegas, V., Lara-Ramírez, J., . . . González-Osorio, F. (2020). SOPHIA: System for Ophthalmic Image Acquisition, Transmission, and Intelligent Analysis. Revista Facultad de Ingeniería, 29(54), 1-15. https://doi.org/10.19053/01211129.v29.n54.2020.11769
Suing-Albito, G., & Barba-Guaman, L. (2023). Aplicación de métodos de deep learning en la identificación y conteo automático de animales salvajes. Revista Ibérica de Sistemas e Tecnologias de Informação, E56, 303-316. https://www.proquest.com/openview/7c46b95f421cc4491149edd9092ca5f9/1?pq-origsite=gscholar&cbl=1006393
Urióstegui-Rojas, A., López-García-Tinajero, A., Cortés-López, P., Mata-Hofmann, R., Mata-Flores, F., & Hofmann-Blancas, M. (2023). Epidemiología del glaucoma congénito primario durante 2008-2018 en el Instituto de Oftalmología "Fundación de Asistencia Privada Conde de Valenciana, IAP". Revista mexicana de oftalmología, 96(6), 241-246. https://doi.org/https://doi.org/10.24875/rmo.m22000246
Valero, J., Zúñiga, A., & Clares, J. (2021). Detección de la tuberculosis con algoritmos de Deep Learning en imágenes de radiografías del tórax. VIVE. Revista de Investigación en Salud, 4(12), 624-633. https://doi.org/10.33996/revistavive.v4i12.119
Zarranz-Ventura, J., Romero-Aroca, P., & Zapata, M. (2023). Inteligencia artificial en oftalmología. Annals d’Oftalmologia, 1(4), 166-169. https://www.scoft.cat/pdfs/Revista-Annals-Oftalmologia_CDS_2023_low.pdf
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Leonardo Paul Sanchez Davila, Ruth Evelyn Rogel Rivera, Joofre Antonio Honores Tapia, Wilmer Braulio Rivas Asanza
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles submitted to this journal for publication will be released for open access under a Creative Commons Attribution Non-Commercial No Derivative Works licence (http://creativecommons.org/licenses/by-nc-nd/4.0).
The authors retain copyright, and are therefore free to share, copy, distribute, perform and publicly communicate the work under the following conditions: Acknowledge credit for the work specified by the author and indicate if changes were made (you may do so in any reasonable way, but not in a way that suggests that the author endorses your use of his or her work. Do not use the work for commercial purposes. In case of remixing, transformation or development, the modified material may not be distributed.
