International Journal of Social Science & Economic Research
Submit Paper

Title:
THE DEVELOPMENT OF AN ACCURATE AND COMPUTATIONALLY FEASIBLE MOBILENETV2 ALGORITHIM TO DIAGNOSE RETINAL DISEASES

Authors:
Jagadeepram Maddipatla, Abhishek Krishnan, David Lomelin, Edwin Kyle, Shravya Etta, Roma Arora, Deeksha Hanumanula, Tarun Samanthanam Prabhu, Shayan Wadiwala, Anjali Patel, Roshan Mohanty, Nickolas Sharma, Shalmali Rao, Sydney Williams, Nikita Benny, Parth Jaiswal, Martin Kanchev, Sudiksha Munipalli

|| ||

Jagadeepram Maddipatla, Abhishek Krishnan, David Lomelin, Edwin Kyle, Shravya Etta, Roma Arora, Deeksha Hanumanula, Tarun Samanthanam Prabhu, Shayan Wadiwala, Anjali Patel, Roshan Mohanty, Nickolas Sharma, Shalmali Rao, Sydney Williams, Nikita Benny, Parth Jaiswal, Martin Kanchev, Sudiksha Munipalli
Duke University, North Carolina

MLA 8
Krishnan, Abhishek. "THE DEVELOPMENT OF AN ACCURATE AND COMPUTATIONALLY FEASIBLE MOBILENETV2 ALGORITHIM TO DIAGNOSE RETINAL DISEASES." Int. j. of Social Science and Economic Research, vol. 7, no. 9, Sept. 2022, pp. 3186-3191, doi.org/10.46609/IJSSER.2022.v07i09.028. Accessed Sept. 2022.
APA 6
Krishnan, A. (2022, September). THE DEVELOPMENT OF AN ACCURATE AND COMPUTATIONALLY FEASIBLE MOBILENETV2 ALGORITHIM TO DIAGNOSE RETINAL DISEASES. Int. j. of Social Science and Economic Research, 7(9), 3186-3191. Retrieved from https://doi.org/10.46609/IJSSER.2022.v07i09.028
Chicago
Krishnan, Abhishek. "THE DEVELOPMENT OF AN ACCURATE AND COMPUTATIONALLY FEASIBLE MOBILENETV2 ALGORITHIM TO DIAGNOSE RETINAL DISEASES." Int. j. of Social Science and Economic Research 7, no. 9 (September 2022), 3186-3191. Accessed September, 2022. https://doi.org/10.46609/IJSSER.2022.v07i09.028.

References

[1]. Bazan, J. (2021, June 25). What is Optical Coherence Tomography (OCT)?!Brooklyn. Parkslopeeye.com.https://parkslopeeye.com/what-is-optical-coherence-tomography oct/#:~:text=How%20Does%20OCT%20Work%3F
[2]. Chou, B. (2011, August 26). Digital Retinal Imaging: Practice-Building Investment. Review of Optometric Business. https://www.reviewob.com/digital-retinal-imaging-practice- building-investment/
[3]. Color Fundus Photography | Department of Ophthalmology. (2019).
[4]. Med.ubc.ca. https://ophthalmology.med.ubc.ca/patient-care/ophthalmic-photography/color-fundus- photography/
[5]. Diabetic Retinopathy | National Eye Institute. (2019). Nih.gov. https://www.nei.nih.gov/learn-about-eye-health/eye-conditions-and-diseases/diabetic-retinopathy#:~:text=Diabetic%20retinopathy%20is%20an%20eye
[6]. Fluorescein Angiography | Department of Ophthalmology. (2020).
[7]. Med.ubc.ca. https://ophthalmology.med.ubc.ca/patient-care/ophthalmic-photography/fluorescein- angiography/
[8]. Glaucoma screening in fundus image - Next Sight Retinal imaging system. (n.d.). Www.nextsight.info. Retrieved July 10, 2022, from https://www.nextsight.info/blog/blog/72-glaucoma-screening-in-fundus-image
[9]. Guo, Y., Budak, Ü., Vespa, L. J., Khorasani, E., & ?engür, A. (2018). A retinal vessel detection approach using convolution neural network with reinforcement sample learning strategy. Measurement, 125, 586–591. https://doi.org/10.1016/j.measurement.2018.05.003
[10]. Intravenous Fluorescein Angiography. (2022).
[11]. Mdsave.com.https://www.mdsave.com/procedures/intravenous-fluorescein-angiography/d482fbcc
[12]. Mayo Clinic. (2021, September 2). Cataracts - Symptoms and causes. Mayo Clinic. https://www.mayoclinic.org/diseases-conditions/cataracts/symptoms-causes/syc- 20353790
[13]. National Eye Institute. (2019). Age-Related Macular Degeneration | National Eye Institute.Nih.gov.https://www.nei.nih.gov/learn-about-eye-health/eye-conditions-and-diseases/age-related-macular-degeneration
[14]. Pranav Modi, & Tasneem Arsiwalla. (2019, January 23). Hypertensive Retinopathy. Nih.gov; StatPearls Publishing. https://www.ncbi.nlm.nih.gov/books/NBK525980/
[15]. Sandler, M., & Howard, A. (2018, April 3). MobileNetV2: The Next Generation of On- Device Computer Vision Networks. Google AI Blog. https://ai.googleblog.com/2018/04/mobilenetv2-next-generation-of-on.html
[16]. Shah, V., Lauer, A., Sundy, M., Cui, R., Hsu, J., & Lim, J. (2016, September 13). Pathologic myopia (myopic degeneration) - EyeWiki.
[17]. Aao.org. https://eyewiki.aao.org/Pathologic_myopia_(myopic_degeneration)
[18]. Sheet, S. S. M., Tan, T.-S., As’ari, M. A., Hitam, W. H. W., & Sia, J. S. Y. (2021). Retinal disease identification using upgraded CLAHE filter and transfer convolution neural network. ICT Express, 8(1), 142–150. https://doi.org/10.1016/j.icte.2021.05.002
[19]. Song, G., Jelly, E. T., Chu, K. K., Kendall, W. Y., & Wax, A. (2021). A review of low-cost and portable optical coherence tomography. Progress in Biomedical Engineering, 3(3), 032002. https://doi.org/10.1088/2516-1091/abfeb7
[20]. Stuart, A. (2020, September 1). Neuro: How to Minimize Diagnostic Errors. American Academy of Ophthalmology. https://www.aao.org/eyenet/article/neuro-how-to- minimize-diagnostic-errors
[21]. Ting, D. S. W., Cheung, C. Y.-L., Lim, G., Tan, G. S. W., Quang, N. D., Gan, A., Hamzah,H., Garcia-Franco, R., San Yeo, I. Y., Lee, S. Y., Wong, E. Y. M., Sabanayagam, C., Baskaran, M., Ibrahim, F., Tan, N. C., Finkelstein, E. A., Lamoureux, E. L., Wong, I. Y., Bressler, N. M., & Sivaprasad, S. (2017). Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes. JAMA, 318(22), 2211. https://doi.org/10.1001/jama.2017.18152
[22]. World Health Organization. (2021, October 11). Blindness and Vision Impairment. Who.int; World Health Organization: WHO.
[23]. https://www.who.int/news-room/fact- sheets/detail/blindness-and-visual-impairment

ABSTRACT:
As of October of 2021, the World Health Organization reported there being at least 1 billion people worldwide with a preventable or treatable visual impairment. A significant portion of visual impairment is caused by retinal diseases, with 3.9 million people affected by Diabetic Retinopathy (DR), 7.7 million by Glaucoma, 93 million by Cataracts, and an unspecified number affected by AMD, Hypertension, and PM (World Health Organization, 2021). Along with these numbers comes the increased demand for reliable methods of diagnosis. Currently, the costs of equipment, ophthalmologist headcounts, and procedure duration in conventional approaches are all factors contributing to the need for more practical methods of diagnosis. As a solution, the MobileNetV2 deep learning algorithm was employed to accurately and efficiently assign diagnoses early on to patients with the use of fundus images. The categorical assignment capabilities of MobileNetV2 allowed for the identification of primary retinal diseases like Diabetic Retinopathy (DR), Age- Related Macular Degeneration (AMD), Glaucoma, Cataracts, Hypertension, and Pathological Myopia (PM). The solution was also trained to identify healthy patients and those with other conditions to decrease the chances of misdiagnosis.

IJSSER is Member of