Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Aug 17:16:2659-2667.
doi: 10.2147/OPTH.S369675. eCollection 2022.

Towards a Device Agnostic AI for Diabetic Retinopathy Screening: An External Validation Study

Divya Parthasarathy Rao  1 , Manavi D Sindal  2 , Sabyasachi Sengupta  3 , Prabu Baskaran  4 , Rengaraj Venkatesh  2 , Anand Sivaraman  5 , Florian M Savoy  6
Affiliations

Towards a Device Agnostic AI for Diabetic Retinopathy Screening: An External Validation Study

Divya Parthasarathy Rao et al. Clin Ophthalmol. .

Abstract

Purpose: To evaluate the performance of a validated Artificial Intelligence (AI) algorithm developed for a smartphone-based camera on images captured using a standard desktop fundus camera to screen for diabetic retinopathy (DR).

Participants: Subjects with established diabetes mellitus.

Methods: Images captured on a desktop fundus camera (Topcon TRC-50DX, Japan) for a previous study with 135 consecutive patients (233 eyes) with established diabetes mellitus, with or without DR were analysed by the AI algorithm. The performance of the AI algorithm to detect any DR, referable DR (RDR Ie, worse than mild non proliferative diabetic retinopathy (NPDR) and/or diabetic macular edema (DME)) and sight-threatening DR (STDR Ie, severe NPDR or worse and/or DME) were assessed based on comparisons against both image-based consensus grades by two fellowship trained vitreo-retina specialists and clinical examination.

Results: The sensitivity was 98.3% (95% CI 96%, 100%) and the specificity 83.7% (95% CI 73%, 94%) for RDR against image grading. The specificity for RDR decreased to 65.2% (95% CI 53.7%, 76.6%) and the sensitivity marginally increased to 100% (95% CI 100%, 100%) when compared against clinical examination. The sensitivity for detection of any DR when compared against image-based consensus grading and clinical exam were both 97.6% (95% CI 95%, 100%). The specificity for any DR detection was 90.9% (95% CI 82.3%, 99.4%) as compared against image grading and 88.9% (95% CI 79.7%, 98.1%) on clinical exam. The sensitivity for STDR was 99.0% (95% CI 96%, 100%) against image grading and 100% (95% CI 100%, 100%) as compared against clinical exam.

Conclusion: The AI algorithm could screen for RDR and any DR with robust performance on images captured on a desktop fundus camera when compared to image grading, despite being previously optimized for a smartphone-based camera.

Keywords: Deep Learning; imaging; retina; screening; smartphone.

PubMed Disclaimer

Conflict of interest statement

Divya Parthasarathy Rao, Anand Sivaraman and Florian M Savoy are Employees of Remidio Innovative Solutions. Medios Technologies, Singapore, where the AI has been developed, and Remidio Innovative Solutions Inc. USA, are wholly owned subsidiaries of Remidio Innovative Solutions Pvt Ltd, India. Dr Sabyasachi Sengupta reports personal fees from Novartis, India, Bayer, Intas, Allergan, outside the submitted work. The authors report no other conflicts of interest in this work.

Figures

Figure 1
Figure 1
STARD flowchart: AI output for RDR against clinical assessment and image-based grading.
Figure 2
Figure 2
Images of true positive (A), false positive (B), false negative (C) and true negative (D) subject with activation maps for image triggering positive diagnosis.
Figure 3
Figure 3
Retinal image photographs from Remidio FOP and Topcon camera.
See this image and copyright information in PMC

References

    1. Huemer J, Wagner SK, Sim DA. The evolution of diabetic retinopathy screening programmes: a chronology of retinal photography from 35 mm slides to artificial intelligence. Clin Ophthalmol. 2020;14:2021–2035. doi: 10.2147/OPTH.S261629 - DOI - PMC - PubMed
    1. International Council of Ophthalmology. Guidelines for diabetic eye care. Available from: https://www.urmc.rochester.edu/MediaLibraries/URMCMedia/eye-institute/im.... Accessed March 28, 2022.
    1. Rosses APO, Ben ÂJ, Souzade CF, et al. Diagnostic performance of retinal digital photography for diabetic retinopathy screening in primary care. Fam Pract. 2017;34(5):546–551. doi: 10.1093/fampra/cmx020 - DOI - PubMed
    1. Sosale B, Aravind SR, Murthy H, et al. Simple, Mobile-based Artificial Intelligence Algorithm in the detection of Diabetic Retinopathy (SMART) study. BMJ Open Diabetes Res Care. 2020;8:e000892. doi: 10.1136/bmjdrc-2019-000892 - DOI - PMC - PubMed
    1. Nielsen KB, Lautrup ML, Andersen JKH, Savarimuthu TR, Grauslund J. Deep learning–based algorithms in screening of diabetic retinopathy: a systematic review of diagnostic performance. Ophthalmol Retina. 2019;3(4):294–304. doi: 10.1016/j.oret.2018.10.014 - DOI - PubMed

LinkOut - more resources