Please use this identifier to cite or link to this item:
Title: Retinal photograph-based deep learning detection of refractive error
Authors: Chen, Yibing
Keywords: Engineering::Bioengineering
Issue Date: 2023
Publisher: Nanyang Technological University
Source: Chen, Y. (2023). Retinal photograph-based deep learning detection of refractive error. Final Year Project (FYP), Nanyang Technological University, Singapore.
Abstract: Refractive error is the major cause of visual impairments, affecting nearly 123.7 million population at all ages worldwide. Early detection is critical for effective treatment via spectacle prescriptions. However, the existing unaddressed limitations of traditional screening methods for refractive error, particularly in developing countries, may potentially affect patients’ quality of life. The increasing implementation of Artificial Intelligence (AI) in ophthalmology has offered space for innovative and advanced systems, enabling faster diagnosis and early treatment. This project demonstrates the potential of the retinal fundus image-based screening tool to improve the traditional eye care pathway and reduce the burden on healthcare professionals. Though further research is necessary before implementing the model in real-life situations, the algorithm offers a novel diagnostic tool with improved accuracy for refractive error detection. Overall, the development of retinal photograph-based deep learning model for refractive error detection represents a promising step forward in the field of ophthalmology.
Schools: School of Chemical and Biomedical Engineering 
Fulltext Permission: embargo_restricted_20240525
Fulltext Availability: With Fulltext
Appears in Collections:CCEB Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
CHEN YIBING_FYP report.pdf
  Until 2024-05-25
1.39 MBAdobe PDFUnder embargo until May 25, 2024

Page view(s)

Updated on Apr 17, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.