Detección temprana de glaucoma mediante modelos híbridos basados en aprendizaje profundo en imágenes de fondo de ojo

Leandro Enrique Ramírez-Cenepo; John Antony Ruiz-Cueva; Jhosep Sánchez-Flores; Kelvin Lleins Rojas-Córdova; Monica Gabriela Leveau-Paredes; Augusto Ricardo Llontop-Reategui

doi:10.51252/rcsi.v6i2.1642

Autores/as

Leandro Enrique Ramírez-Cenepo Universidad Nacional de San Martín https://orcid.org/0009-0007-4118-5805
John Antony Ruiz-Cueva Universidad Nacional de San Martín https://orcid.org/0000-0002-6820-8006
Jhosep Sánchez-Flores Universidad Nacional de San Martín
Kelvin Lleins Rojas-Córdova Universidad Nacional de San Martín https://orcid.org/0009-0001-4097-3961
Monica Gabriela Leveau-Paredes Universidad Nacional de San Martín https://orcid.org/0009-0001-8476-247X
Augusto Ricardo Llontop-Reategui Universidad Nacional de San Martín

DOI:

https://doi.org/10.51252/rcsi.v6i2.1642

Palabras clave:

análisis de imágenes retinianas, clasificación multiclase, diagnóstico automatizado, transferencia de aprendizaje, visión por computadora

Resumen

El glaucoma es una de las principales causas de ceguera irreversible, por lo que su detección temprana es esencial para prevenir la pérdida visual. La investigación tuvo como objetivo desarrollar y evaluar modelos híbridos de aprendizaje profundo para la clasificación multiclase del glaucoma mediante imágenes de fondo de ojo. Se utilizaron 6014 imágenes retinianas de bases públicas, sometidas a depuración, balanceo y partición estratificada. Las arquitecturas VGG16, ResNet50 y EfficientNet-B0 se emplearon como extractores de características combinados con Cascaded Deep Forest. La evaluación incluyó validación cruzada estratificada de 10 pliegues y una prueba independiente. VGG16 + CDF obtuvo el mejor desempeño, con una accuracy promedio de 0.9320, mayor estabilidad y mejor generalización. Las pruebas estadísticas confirmaron diferencias significativas entre los modelos, demostrando que el enfoque híbrido constituye una alternativa robusta para la clasificación automatizada del glaucoma.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

Abramovich, O., Pizem, H., Fhima, J., Berkowitz, E., Gofrit, B., Baskin, M., Meisel, M., Eijgen, J. Van, Blumenthal, E., & Behar, J. (2026). Hillel Yaffe Glaucoma Dataset (HYGD): A Gold-Standard Annotated Fundus Dataset for Glaucoma Detection. PhysioNet. https://doi.org/https://doi.org/10.13026/m92s-0z95

Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019). Optuna: A Next-generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2623–2631. https://doi.org/10.1145/3292500.3330701

Aljohani, A., & Aburasain, R. Y. (2024). A hybrid framework for glaucoma detection through federated machine learning and deep learning models. BMC Medical Informatics and Decision Making, 24(1), 115. https://doi.org/10.1186/s12911-024-02518-y

Arévalo-Hernández, C. O., Arévalo-Gardini, E., Arévalo-López, L. A., Tuesta-Hidalgo, O., Romero-Vela, D. S., & Ruiz-Camus, C. E. (2023). Predicción de la fertilidad del suelo mediante aprendizaje automático en la provincia de Alto Amazonas, Perú. Revista Peruana de Investigación Agropecuaria, 3(2), e63. https://doi.org/10.56926/repia.v3i2.63

Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324

Chaurasia, A. K., Liu, G.-S., Greatbatch, C. J., Gharahkhani, P., Craig, J. E., Mackey, D. A., MacGregor, S., & Hewitt, A. W. (2025). A generalised computer vision model for improved glaucoma screening using fundus images. Eye, 39(1), 109–117. https://doi.org/10.1038/s41433-024-03388-4

Chiang, Y.-Y., Chen, C.-L., & Chen, Y.-H. (2024). Deep Learning Evaluation of Glaucoma Detection Using Fundus Photographs in Highly Myopic Populations. Biomedicines, 12(7), 1394. https://doi.org/10.3390/biomedicines12071394

Demšar, J. (2006). Statistical Comparisons of Classifiers over Multiple Data Sets. JMLR. https://www.jmlr.org/papers/v7/demsar06a.html

Fumero Batista, F. J., Diaz-Aleman, T., Sigut, J., Alayon, S., Arnay, R., & Angel-Pereira, D. (2020). RIM-ONE DL: A Unified Retinal Image Database for Assessing Glaucoma Using Deep Learning. Image Analysis & Stereology, 39(3), 161–167. https://doi.org/10.5566/ias.2346

Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, 63(1), 3–42. https://doi.org/10.1007/s10994-006-6226-1

Govindharaj, I., Santhakumar, D., Pugazharasi, K., Ravichandran, S., Vijaya Prabhu, R., & Raja, J. (2025). Enhancing glaucoma diagnosis: Generative adversarial networks in synthesized imagery and classification with pretrained MobileNetV2. MethodsX, 14, 103116. https://doi.org/10.1016/j.mex.2024.103116

Ha, A., & Park, K. H. (2019). Optical Coherence Tomography for the Diagnosis and Monitoring of Glaucoma. Asia-Pacific Journal of Ophthalmology. https://doi.org/10.22608/APO.201902

Hassan, T., Akram, M. U., Masood, M. F., & Yasin, U. (2018). BIOMISA Retinal Image Database for Macular and Ocular Syndromes (pp. 695–705). https://doi.org/10.1007/978-3-319-93000-8_79

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. https://doi.org/10.1109/CVPR.2016.90

Hicks, S. A., Strümke, I., Thambawita, V., Hammou, M., Riegler, M. A., Halvorsen, P., & Parasa, S. (2022). On evaluation metrics for medical applications of artificial intelligence. Scientific Reports, 12(1), 5979. https://doi.org/10.1038/s41598-022-09954-8

Hwang, E. E., Chen, D., Han, Y., Jia, L., & Shan, J. (2025). Utilization of Image-Based Deep Learning in Multimodal Glaucoma Detection Neural Network from a Primary Patient Cohort. Ophthalmology Science, 5(3), 100703. https://doi.org/10.1016/j.xops.2025.100703

Ilesanmi, A. E., Ilesanmi, T., & Gbotoso, G. A. (2023). A systematic review of retinal fundus image segmentation and classification methods using convolutional neural networks. Healthcare Analytics, 4, 100261. https://doi.org/10.1016/j.health.2023.100261

Ling, X. C., Chen, H. S.-L., Yeh, P.-H., Cheng, Y.-C., Huang, C.-Y., Shen, S.-C., & Lee, Y.-S. (2025). Deep Learning in Glaucoma Detection and Progression Prediction: A Systematic Review and Meta-Analysis. Biomedicines, 13(2), 420. https://doi.org/10.3390/biomedicines13020420

Meethal, N. S. K., Sisodia, V. P. S., George, R., & Khanna, R. C. (2024). Barriers and Potential Solutions to Glaucoma Screening in the Developing World: A Review. Journal of Glaucoma, 33(8S), S33–S38. https://doi.org/10.1097/IJG.0000000000002404

Ministerio de Salud. (2021). Minsa: Más del 50 % de los pacientes que tiene glaucoma no sabe que lo padece. Ministerio de Salud. https://www.gob.pe/institucion/minsa/noticias/346283-minsa-mas-del-50-de-los-pacientes-que-tiene-glaucoma-no-sabe-que-lo-padece?utm_source

Owusu-Adjei, M., Ben Hayfron-Acquah, J., Frimpong, T., & Abdul-Salaam, G. (2023). Imbalanced class distribution and performance evaluation metrics: A systematic review of prediction accuracy for determining model performance in healthcare systems. PLOS Digital Health, 2(11), e0000290. https://doi.org/10.1371/journal.pdig.0000290

Realini, T., McMillan, B., Gross, R. L., Devience, E., & Balasubramani, G. K. (2021). Assessing the Reliability of Intraocular Pressure Measurements Using Rebound Tonometry. Journal of Glaucoma, 30(8), 629–633. https://doi.org/10.1097/IJG.0000000000001892

Roboflow. (2026). GlaucomaData Computer Vision Model. Universe Roboflow. https://universe.roboflow.com/classification-8wwxf/glaucomadata/dataset/1

Saha, S., Vignarajan, J., & Frost, S. (2023). A fast and fully automated system for glaucoma detection using color fundus photographs. Scientific Reports, 13(1), 18408. https://doi.org/10.1038/s41598-023-44473-0

Schuster, A. K., Erb, C., Hoffmann, E. M., Dietlein, T., & Pfeiffer, N. (2020). The Diagnosis and Treatment of Glaucoma. Deutsches Ärzteblatt International. https://doi.org/10.3238/arztebl.2020.0225

Sharma, P., Takahashi, N., Ninomiya, T., Sato, M., Miya, T., Tsuda, S., & Nakazawa, T. (2025). A hybrid multi model artificial intelligence approach for glaucoma screening using fundus images. Npj Digital Medicine, 8(1), 130. https://doi.org/10.1038/s41746-025-01473-w

Shi, D., Zhang, W., Yang, J., Huang, S., Chen, X., Xu, P., Jin, K., Lin, S., Wei, J., Yusufu, M., Liu, S., Zhang, Q., Ge, Z., Xu, X., & He, M. (2025). A multimodal visual–language foundation model for computational ophthalmology. Npj Digital Medicine, 8(1), 381. https://doi.org/10.1038/s41746-025-01772-2

Shoukat, A., Akbar, S., Hassan, S. A., Iqbal, S., Mehmood, A., & Ilyas, Q. M. (2023). Automatic Diagnosis of Glaucoma from Retinal Images Using Deep Learning Approach. Diagnostics, 13(10), 1738. https://doi.org/10.3390/diagnostics13101738

Sidhu, Z., & Mansoori, T. (2024). Artificial intelligence in glaucoma detection using color fundus photographs. Indian Journal of Ophthalmology, 72(3), 408–411. https://doi.org/10.4103/IJO.IJO_613_23

Simonyan, K., & Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. Computer Vision and Pattern Recognition, 1. https://doi.org/https://doi.org/10.48550/arXiv.1409.1556

Świerczyński, H., Pukacki, J., Szczęsny, S., Mazurek, C., & Wasilewicz, R. (2025). Application of machine learning techniques in GlaucomAI system for glaucoma diagnosis and collaborative research support. Scientific Reports, 15(1), 7940. https://doi.org/10.1038/s41598-025-89893-2

Tan, M., & Le, Q. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning, PMLR. https://proceedings.mlr.press/v97/tan19a.html

Tham, Y.-C., Li, X., Wong, T. Y., Quigley, H. A., Aung, T., & Cheng, C.-Y. (2014). Global Prevalence of Glaucoma and Projections of Glaucoma Burden through 2040. Ophthalmology, 121(11), 2081–2090. https://doi.org/10.1016/j.ophtha.2014.05.013

Zhou, Z.-H., & Feng, J. (2019). Deep forest. National Science Review, 6(1), 74–86. https://doi.org/10.1093/nsr/nwy108