Detection of Retinal Anatomical Structures and its Application to Image Quality Assessment

• Rodrigo de Castro Michelassi USP
• Nina S. T. Hirata USP

Resumo

Given the general shortage of ophthalmologists in Brazil, automated retinal image screening emerges as a fundamental tool to promote early diagnosis of retinal diseases and prevent, for example, blindness. Motivated by this, we propose the use of YOLO-based object detection models to detect two retinal structures – the optic disc and the macular region – which play a crucial role in ophthalmological examinations. As a case study, based on detections performed on BRSET images, we determined the distances between the structures and the retinal edges. We found that the calculated distances do not always meet the minimum distance established in the Image Quality Assessment Image Field protocol. The results highlight the ability of YOLO-based models to reliably detect anatomical structures in retinal images and their potential to contribute to improving analyses that rely on these detections.

Referências

P. Burlina, A. Galdran, P. Costa, A. Cohen, and A. Campilho, “Chapter 18 - artificial intelligence and deep learning in retinal image analysis,” in Computational Retinal Image Analysis, E. Trucco, T. MacGillivray, and Y. Xu, Eds. Academic Press, 2019, pp. 379–404. [Online]. Available: [link]

M. I. Meyer, A. Galdran, A. M. Mendonça, and A. Campilho, “A Pixel-Wise Distance Regression Approach for Joint Retinal Optical Disc and Fovea Detection,” in Medical Image Computing and Computer Assisted Intervention – MICCAI, A. F. Frangi, J. A. Schnabel, C. Davatzikos, C. Alberola-López, and G. Fichtinger, Eds. Springer International Publishing, 2018, pp. 39–47.

T. Araújo, G. Aresta, A. Galdran, P. Costa, A. M. Mendonça, and A. Campilho, “UOLO - Automatic Object Detection and Segmentation in Biomedical Images,” in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Springer International Publishing, 2018, pp. 165–173.

H. Kang, S. Lee, and A. Lee, “Measuring ocular torsion and its variations using different nonmydriatic fundus photographic methods,” PLOS ONE, vol. 15, p. e0244230, 12 2020.

M. A. P. Da Silva, M. S. M. Mafalda, A. B. Alvarez, and R. F. L. Chavez, “Optic Disc Localization from Retinal Fundus Image Using Discrete Cosine and Hough Transforms,” in IEEE 23rd International Conference on Bioinformatics and Bioengineering (BIBE), 2023, pp. 134–139.

J. Singh, G. D. Joshi, and J. Sivaswamy, “Appearance-based object detection in colour retinal images,” in 15th IEEE International Conference on Image Processing, 2008, pp. 1432–1435.

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA, USA: IEEE Computer Society, 2016, pp. 779–788.

L. F. Nakayama, D. Restrepo, J. Matos, L. Z. Ribeiro, F. K. Malerbi, L. A. Celi, and C. S. Regatieri, “BRSET: A Brazilian Multilabel Ophthalmological Dataset of Retina Fundus Photos,” PLOS Digital Health, vol. 3, no. 7, pp. 1–16, 07 2024. [Online]. DOI: 10.1371/journal.pdig.0000454

H. Fang, F. Li, J. Wu, H. Fu, X. Sun, J. Son, S. Yu, M. Zhang, C. Yuan, C. Bian, B. Lei, B. Zhao, X. Xu, S. Li, F. Fumero, J. Sigut, H. Almubarak, Y. Bazi, Y. Guo, Y. Zhou, U. Baid, S. Innani, T. Guo, J. Yang, J. I. Orlando, H. Bogunović, X. Zhang, and Y. Xu, “REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screening,” 2022. [Online]. Available: [link]

J. Sivaswamy, S. R. Krishnadas, G. Datt Joshi, M. Jain, and A. U. Syed Tabish, “Drishti-GS: Retinal image dataset for optic nerve head (ONH) segmentation,” in IEEE 11th International Symposium on Biomedical Imaging (ISBI), 2014, pp. 53–56.

P. Porwal, S. Pachade, R. Kamble, M. Kokare, G. Deshmukh, V. Sahasrabuddhe, and F. Meriaudeau, “Indian Diabetic Retinopathy Image Dataset (IDRiD),” 2018. [Online]. DOI: 10.21227/H25W98

M. N. Bajwa, G. A. P. Singh, W. Neumeier, M. I. Malik, A. Dengel, and S. Ahmed, “G1020: A Benchmark Retinal Fundus Image Dataset for Computer-Aided Glaucoma Detection,” 2020. [Online]. Available: [link]

A. Almazroa, S. Alodhayb, E. Osman, E. Ramadan, M. Hummadi, M. Dlaim, M. Alkatee, K. Raahemifar, and V. Lakshminarayanan, “Retinal fundus images for glaucoma analysis: the RIGA dataset,” in Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications, J. Zhang and P.-H. Chen, Eds., vol. 10579, International Society for Optics and Photonics. SPIE, 2018, p. 105790B. [Online]. DOI: 10.1117/12.2293584

B. Bhargav Bhatkalkar, V. Nayak S, S. Shenoy, and R. Arjunan, “FundusPosNet: A Deep Learning Driven Heatmap Regression Model for the Joint Localization of Optic Disc and Fovea Centers in Color Fundus Images,” IEEE Access, vol. PP, pp. 1–1, 11 2021.

G. Jocher and J. Qiu, “Ultralytics YOLO11,” 2024. [Online]. Available: [link]