IJSSER

Title: GlaucoScreen: A Novel Deep Learning-Based System for Glaucoma Detection and Progression Monitoring
Authors: Siddhartha Milkuri
\|\| \|\|
Siddhartha Milkuri Bentonville High School, 1801 SE J St, Bentonville, AR 72712, USA
MLA 8 Milkuri, Siddhartha. "GlaucoScreen: A Novel Deep Learning-Based System for Glaucoma Detection and Progression Monitoring." Int. j. of Social Science and Economic Research, vol. 9, no. 10, Oct. 2024, pp. 4351-4367, doi.org/10.46609/IJSSER.2024.v09i10.025. Accessed Oct. 2024. APA 6 Milkuri, S. (2024, October). GlaucoScreen: A Novel Deep Learning-Based System for Glaucoma Detection and Progression Monitoring. Int. j. of Social Science and Economic Research, 9(10), 4351-4367. Retrieved from https://doi.org/10.46609/IJSSER.2024.v09i10.025 Chicago Milkuri, Siddhartha. "GlaucoScreen: A Novel Deep Learning-Based System for Glaucoma Detection and Progression Monitoring." Int. j. of Social Science and Economic Research 9, no. 10 (October 2024), 4351-4367. Accessed October, 2024. https://doi.org/10.46609/IJSSER.2024.v09i10.025.
References [1] . Allison, K., Patel, D., & Besharim, C. (2021). The Value of Annual Glaucoma Screening for High-Risk Adults Ages 60 to 80. Cureus. https://doi.org/10.7759/cureus.18710 [2] . Boyd, K. (2019, August 28). What Is Glaucoma? American Academy of Ophthalmology. https://www.aao.org/eye-health/diseases/what-is-glaucoma [3] . Brusini, P. (2008, January 1). Monitoring glaucoma progression (C. Nucci, L. Cerulli, N. N. Osborne, & G. Bagetta, Eds.). ScienceDirect; Elsevier. https://www.sciencedirect.com/science/article/abs/pii/S0079612308011060?via%3Dihub [4] . Chua, J., Baskaran, M., Ong, P. G., Zheng, Y., Wong, T. Y., Aung, T., & Cheng, C.-Y. (2015). Prevalence, Risk Factors, and Visual Features of Undiagnosed Glaucoma. JAMA Ophthalmology, 133(8), 938. https://doi.org/10.1001/jamaophthalmol.2015.1478 [5] . Diaz-Pinto, A., Morales, S., Naranjo, V., Köhler, T., Mossi, J., & Navea, A. (2019). CNNs for Automatic Glaucoma Assessment using Fundus Images: An Extensive Validation. Figshare.com. https://doi.org/10.6084/m9.figshare.7613135.v1 [6] . Glaucoma Tests: What To Expect & How To Interpret Results. (2022, March 9). Cleveland Clinic. https://my.clevelandclinic.org/health/diagnostics/22514-glaucoma-tests [7] . Google Cloud. (2019, January 28). Advanced Guide to Inception v3 on Cloud TPU \| Cloud TPU \| Google Cloud. Google Cloud. https://cloud.google.com/tpu/docs/inception-v3-advanced [8] . Huang, X., Kong, X., Shen, Z., Ouyang, J., Li, Y., Jin, K., & Ye, J. (2023). GRAPE: A multi-modal dataset of longitudinal follow-up visual field and fundus images for glaucoma management. Scientific Data, 10(1), 520. https://doi.org/10.1038/s41597-023-02424-4 [9] . Madhumalini, M., & Devi, T. M. (2022). Detection of Glaucoma from Fundus Images Using Novel Evolutionary-Based Deep Neural Network. Journal of Digital Imaging. https://doi.org/10.1007/s10278-021-00577-5 [10] . Mishra, R. K., Reddy, G. Y. S., & Pathak, H. (2021). The Understanding of Deep Learning: A Comprehensive Review. Mathematical Problems in Engineering, 2021, 1–15. https://doi.org/10.1155/2021/5548884 [11] . O’shea, K., & Nash, R. (2015). An Introduction to Convolutional Neural Networks. https://arxiv.org/pdf/1511.08458.pdf [12] . Porwal, P., Pachade, S., Kamble, R., Kokare, M., Deshmukh, G., Sahasrabuddhe, V., & Meriaudeau, F. (2018). Indian Diabetic Retinopathy Image Dataset (IDRiD): A Database for Diabetic Retinopathy Screening Research. Data, 3(3), 25. https://doi.org/10.3390/data3030025 [13] . Rewri, P. (2023). Towards better management of glaucoma in India. Indian Journal of Ophthalmology, 71(3), 686. https://doi.org/10.4103/IJO.IJO_379_23 [14] . Shroff, M. (2023, May 16). Know your Neural Network architecture more by understanding these terms. Medium. https://medium.com/@shroffmegha6695/know-your-neural-network-architecture-more-by-understanding-these-terms-67faf4ea0efb#:~:text=in%20deep%20learning.- [15] . Skalicky, S., & Goldberg, I. (2008). Depression and Quality of Life in Patients With Glaucoma: A Cross-sectional Analysis Using the Geriatric Depression Scale-15, Assessment of Function Related to Vision, and the Glaucoma Quality of Life-15. Journal of Glaucoma, 17(7), 546–551. https://doi.org/10.1097/ijg.0b013e318163bdd1 [16] . Susanna, R., De Moraes, C. G., Cioffi, G. A., & Ritch, R. (2015). Why Do People (Still) Go Blind from Glaucoma? Translational Vision Science & Technology, 4(2). https://doi.org/10.1167/tvst.4.2.1 [17] . Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2015). Rethinking the Inception Architecture for Computer Vision. ArXiv.org. https://arxiv.org/abs/1512.00567 [18] . U-Net: Convolutional Networks for Biomedical Image Segmentation. (2015). Uni-Freiburg.de. https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/ [19] . Zhang, J. (2019, October 18). UNet Line by Line Explanation. Medium. https://towardsdatascience.com/unet-line-by-line-explanation-9b191c76baf5
ABSTRACT: Glaucoma, an eye disease that causes damage to the optic nerve, is the second-leading cause of blindness worldwide. Swift diagnosis and treatment of glaucoma is crucial to prevent any glaucoma-induced vision loss; however, this is not usually achievable in developing countries due to their lack of medical personnel and resources. This research aims to solve this through GlaucoScreen, an inexpensive, accessible system for both reliable glaucoma detection and accurate real-time progression monitoring. The first component of the GlaucoScreen system is the smartphone attachment. This attachment allows for the cheap and precise capture of a retinal fundus. The retinal fundus image (RFI) is then uploaded onto the mobile application to be processed by three different deep learning models. First, in order to reduce the computation needed by subsequent models and emphasize diagnostic features, the optic disk region of the RFI is localized and segmented out by the optic disk segmentation model. This model, employing the U-Net architecture, has an intersection-over-union score of 95.11%. The segmented optic disk image is then analyzed by the glaucoma detection model, which has an accuracy of 98.68%, and finally the progression categorization model, which has an accuracy of 95.88%. The glaucoma detection model utilizes a novel convolutional neural network architecture, while the progression categorization model utilizes the InceptionV3 architecture. GlaucoScreen is unique in that it monitors the progression state of glaucoma, which is crucial for its treatment, while also providing a cost-effective method of retrieving RFIs. Through GlaucoScreen, anyone from anywhere around the world will have access to quality glaucoma care.

IJSSER is Member of