Detecção Automática do Glaucoma em Imagens Retinianas Utilizando Redes Neurais Convolucionais
Resumo
O glaucoma é uma das principais causas de cegueira no mundo, afetando o nervo óptico e causando danos progressivos. A detecção precoce é essencial para evitar a perda da visão, mas o diagnóstico manual baseado em imagens retinianas pode ser subjetivo e propenso a erros. Propõe-se o uso de deep learning com o modelo YOLOv8n para detectar o disco óptico, seguido da classificação com uma ResNet-50 refinada. O método obteve 91,7% de precisão, 91,1% de recall, 91,5% de acurácia e 82,7% no coeficiente kappa. Conclui-se que o uso da imagem completa da retina teve melhor desempenho do que o uso exclusivo da região do disco óptico, conforme confirmado pela análise de ativação do Grad-CAM.
Referências
da Saúde, M. (2021). Glaucoma: diagnóstico precoce e tratamento evitam perda da visão. [link]. Acesso em: 26 novembro 2024.
da Silva Torres, R. and Falcao, A. X. (2006). Content-based image retrieval: theory and applications. RITA, 13(2):161–185.
Elmannai, H., Alhussan, A. A., Ayadi, M., Ksibi, A., et al. (2024). An improved deep learning framework for automated optic disc localization and glaucoma detection. CMES-Computer Modeling in Engineering & Sciences, 140(2).
Hayreh, S. S. (2007). Neovascular glaucoma. Progress in retinal and eye research, 26(5):470–485.
Kiefer, R., Abid, M., Ardali, M. R., Steen, J., and Amjadian, E. (2023). A catalog of public glaucoma datasets for machine learning applications: A detailed description and analysis of public glaucoma datasets available to machine learning engineers tackling glaucoma-related problems using retinal fundus images and oct images. In Proceedings of the 2023 7th International Conference on Information System and Data Mining.
Kubrak, T. (2024). Automated detection of glaucoma and diagnostic features for justraigs challenge. In 2024 IEEE International Symposium on Biomedical Imaging (ISBI), pages 1–3. IEEE.
Lin, H., Apostolidis, C., and Katsaggelos, A. K. (2024). Brighteye: Glaucoma screening with color fundus photographs based on vision transformer. In 2024 IEEE International Symposium on Biomedical Imaging (ISBI), pages 1–4. IEEE.
Mehmood, M., Naveed, K., Aurangzeb, K., Khan, H. A., Alhussein, M., and Naqvi, S. S. (2023). Eddense-net: Fully dense encoder decoder network for joint segmentation of optic cup and disc. arXiv preprint arXiv:2308.10192.
Pattanaik, S., Behera, S., Majhi, S. K., Pradhan, R., and Dwibedy, P. (2025). An ensemble stacked bi-lstm with resnet50 method for glaucoma classification in iot framework: An ensemble method for glaucoma classification iot framework. Journal of Scientific & Industrial Research (JSIR), 84(1):24–35.
Powers, D. M. (2020). Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061.
Ruby Elizabeth, J., Kesavaraja, D., and Ebenezer Juliet, S. (2024). A deep learning model based glaucoma detection using retinal images. Journal of Intelligent & Fuzzy Systems, (Preprint):1–12.
Sanghavi, J. and Kurhekar, M. (2024). An efficient framework for optic disk segmentation and classification of glaucoma on fundus images. Biomedical Signal Processing and Control, 89:105770.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pages 618–626.
Shanmugam, P., Raja, J., and Pitchai, R. (2021). An automatic recognition of glaucoma in fundus images using deep learning and random forest classifier. Applied Soft Computing, 109:107512.
Silva, I. M. (2016). Diagnóstico do glaucoma congênito–revisão sistemática. Trabalho de Conclusão de Curso (Graduação) - Medicina (Faculdade de Medicina).
Sivakumar, R. and Penkova, A. (2025). Enhancing glaucoma detection through multi-modal integration of retinal images and clinical biomarkers. Engineering Applications of Artificial Intelligence, 143:110010.
Sułot, D., Alonso-Caneiro, D., Ksieniewicz, P., Krzyzanowska-Berkowska, P., and Iskander, D. R. (2021). Glaucoma classification based on scanning laser ophthalmoscopic images using a deep learning ensemble method. Plos one, 16(6):e0252339.
Tamim, N., Elshrkawey, M., and Nassar, H. (2021). Accurate diagnosis of diabetic retinopathy and glaucoma using retinal fundus images based on hybrid features and genetic algorithm. Applied Sciences, 11(13):6178.
Tan, O., Greenfield, D. S., Francis, B. A., Varma, R., Schuman, J. S., Huang, D., and Choi, D. (2024). A hybrid deep learning classification of perimetric glaucoma using peripapillary nerve fiber layer reflectance and other oct parameters from three anatomy regions. ArXiv.
Wang, S., Kim, B., Kang, J., and Eom, D.-S. (2024). Precision diagnosis of glaucoma with vllm ensemble deep learning. Applied Sciences, 14(11):4588.
Yunitasari, D. A., Sigit, R., and Harsono, T. (2021). Glaucoma detection based on cup-to-disc ratio in retinal fundus image using support vector machine. In 2021 International Electronics Symposium (IES), pages 368–373.
da Silva Torres, R. and Falcao, A. X. (2006). Content-based image retrieval: theory and applications. RITA, 13(2):161–185.
Elmannai, H., Alhussan, A. A., Ayadi, M., Ksibi, A., et al. (2024). An improved deep learning framework for automated optic disc localization and glaucoma detection. CMES-Computer Modeling in Engineering & Sciences, 140(2).
Hayreh, S. S. (2007). Neovascular glaucoma. Progress in retinal and eye research, 26(5):470–485.
Kiefer, R., Abid, M., Ardali, M. R., Steen, J., and Amjadian, E. (2023). A catalog of public glaucoma datasets for machine learning applications: A detailed description and analysis of public glaucoma datasets available to machine learning engineers tackling glaucoma-related problems using retinal fundus images and oct images. In Proceedings of the 2023 7th International Conference on Information System and Data Mining.
Kubrak, T. (2024). Automated detection of glaucoma and diagnostic features for justraigs challenge. In 2024 IEEE International Symposium on Biomedical Imaging (ISBI), pages 1–3. IEEE.
Lin, H., Apostolidis, C., and Katsaggelos, A. K. (2024). Brighteye: Glaucoma screening with color fundus photographs based on vision transformer. In 2024 IEEE International Symposium on Biomedical Imaging (ISBI), pages 1–4. IEEE.
Mehmood, M., Naveed, K., Aurangzeb, K., Khan, H. A., Alhussein, M., and Naqvi, S. S. (2023). Eddense-net: Fully dense encoder decoder network for joint segmentation of optic cup and disc. arXiv preprint arXiv:2308.10192.
Pattanaik, S., Behera, S., Majhi, S. K., Pradhan, R., and Dwibedy, P. (2025). An ensemble stacked bi-lstm with resnet50 method for glaucoma classification in iot framework: An ensemble method for glaucoma classification iot framework. Journal of Scientific & Industrial Research (JSIR), 84(1):24–35.
Powers, D. M. (2020). Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061.
Ruby Elizabeth, J., Kesavaraja, D., and Ebenezer Juliet, S. (2024). A deep learning model based glaucoma detection using retinal images. Journal of Intelligent & Fuzzy Systems, (Preprint):1–12.
Sanghavi, J. and Kurhekar, M. (2024). An efficient framework for optic disk segmentation and classification of glaucoma on fundus images. Biomedical Signal Processing and Control, 89:105770.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pages 618–626.
Shanmugam, P., Raja, J., and Pitchai, R. (2021). An automatic recognition of glaucoma in fundus images using deep learning and random forest classifier. Applied Soft Computing, 109:107512.
Silva, I. M. (2016). Diagnóstico do glaucoma congênito–revisão sistemática. Trabalho de Conclusão de Curso (Graduação) - Medicina (Faculdade de Medicina).
Sivakumar, R. and Penkova, A. (2025). Enhancing glaucoma detection through multi-modal integration of retinal images and clinical biomarkers. Engineering Applications of Artificial Intelligence, 143:110010.
Sułot, D., Alonso-Caneiro, D., Ksieniewicz, P., Krzyzanowska-Berkowska, P., and Iskander, D. R. (2021). Glaucoma classification based on scanning laser ophthalmoscopic images using a deep learning ensemble method. Plos one, 16(6):e0252339.
Tamim, N., Elshrkawey, M., and Nassar, H. (2021). Accurate diagnosis of diabetic retinopathy and glaucoma using retinal fundus images based on hybrid features and genetic algorithm. Applied Sciences, 11(13):6178.
Tan, O., Greenfield, D. S., Francis, B. A., Varma, R., Schuman, J. S., Huang, D., and Choi, D. (2024). A hybrid deep learning classification of perimetric glaucoma using peripapillary nerve fiber layer reflectance and other oct parameters from three anatomy regions. ArXiv.
Wang, S., Kim, B., Kang, J., and Eom, D.-S. (2024). Precision diagnosis of glaucoma with vllm ensemble deep learning. Applied Sciences, 14(11):4588.
Yunitasari, D. A., Sigit, R., and Harsono, T. (2021). Glaucoma detection based on cup-to-disc ratio in retinal fundus image using support vector machine. In 2021 International Electronics Symposium (IES), pages 368–373.
Publicado
09/06/2025
Como Citar
GOMES, Jeanderson de Sousa; BRITO, Luis Eduardo Silva; DALÍLIA, Alcilene; VELOSO, Romuere Rodrigues; CARVALHO, Antônio Oseas de; ARAUJO, Flavio H. D..
Detecção Automática do Glaucoma em Imagens Retinianas Utilizando Redes Neurais Convolucionais. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 25. , 2025, Porto Alegre/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 629-640.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2025.7694.
