Literature DB >> 32382145

Evaluation of an AI system for the detection of diabetic retinopathy from images captured with a handheld portable fundus camera: the MAILOR AI study.

T W Rogers1, J Gonzalez-Bueno2, R Garcia Franco3, E Lopez Star3, D Méndez Marín3, J Vassallo4, V C Lansingh3,5, S Trikha6, N Jaccard2.   

Abstract

OBJECTIVES: To evaluate the performance of an artificial intelligence (AI) system (Pegasus, Visulytix Ltd., UK*) at the detection of diabetic retinopathy (DR) from images captured by a handheld portable fundus camera.
METHODS: A cohort of 6404 patients (~80% with diabetes mellitus) was screened for retinal diseases using a handheld portable fundus camera (Pictor Plus, Volk Optical Inc., USA) at the Mexican Advanced Imaging Laboratory for Ocular Research. The images were graded for DR by specialists according to the Scottish DR grading scheme. The performance of the AI system was evaluated, retrospectively, in assessing referable DR (RDR) and proliferative DR (PDR) and compared with the performance on a publicly available desktop camera benchmark dataset.
RESULTS: For RDR detection, Pegasus performed with an 89.4% (95% CI: 88.0-90.7) area under the receiver operating characteristic (AUROC) curve for the MAILOR cohort, compared with an AUROC of 98.5% (95% CI: 97.8-99.2) on the benchmark dataset. This difference was statistically significant. Moreover, no statistically significant difference was found in performance for PDR detection with Pegasus achieving an AUROC of 94.3% (95% CI: 91.0-96.9) on the MAILOR cohort and 92.2% (95% CI: 89.4-94.8) on the benchmark dataset.
CONCLUSIONS: Pegasus showed good transferability for the detection of PDR from a curated desktop fundus camera dataset to real-world clinical practice with a handheld portable fundus camera. However, there was a substantial, and statistically significant, decrease in the diagnostic performance for RDR when using the handheld device.

Entities:  

Mesh:

Year:  2020        PMID: 32382145      PMCID: PMC8026959          DOI: 10.1038/s41433-020-0927-8

Source DB:  PubMed          Journal:  Eye (Lond)        ISSN: 0950-222X            Impact factor:   3.775


  1 in total

1.  Grading diabetic retinopathy (DR) using the Scottish grading protocol.

Authors:  Sonia Zachariah; William Wykes; David Yorston
Journal:  Community Eye Health       Date:  2015
  1 in total
  5 in total

Review 1.  Aligning mission to digital health strategy in academic medical centers.

Authors:  Adam B Cohen; Lisa Stump; Harlan M Krumholz; Margaret Cartiera; Sanchita Jain; L Scott Sussman; Allen Hsiao; Walter Lindop; Anita Kuo Ying; Rebecca L Kaul; Thomas J Balcezak; Welela Tereffe; Matthew Comerford; Daniel Jacoby; Neema Navai
Journal:  NPJ Digit Med       Date:  2022-06-02

2.  A novel deep learning conditional generative adversarial network for producing angiography images from retinal fundus photographs.

Authors:  Alireza Tavakkoli; Sharif Amit Kamran; Khondker Fariha Hossain; Stewart Lee Zuckerbrod
Journal:  Sci Rep       Date:  2020-12-09       Impact factor: 4.379

3.  Validation of an Automated Screening System for Diabetic Retinopathy Operating under Real Clinical Conditions.

Authors:  Soledad Jimenez-Carmona; Pedro Alemany-Marquez; Pablo Alvarez-Ramos; Eduardo Mayoral; Manuel Aguilar-Diosdado
Journal:  J Clin Med       Date:  2021-12-21       Impact factor: 4.241

4.  Developments in the detection of diabetic retinopathy: a state-of-the-art review of computer-aided diagnosis and machine learning methods.

Authors:  Ganeshsree Selvachandran; Shio Gai Quek; Raveendran Paramesran; Weiping Ding; Le Hoang Son
Journal:  Artif Intell Rev       Date:  2022-04-26       Impact factor: 9.588

5.  THEIA™ development, and testing of artificial intelligence-based primary triage of diabetic retinopathy screening images in New Zealand.

Authors:  E Vaghefi; S Yang; L Xie; S Hill; O Schmiedel; R Murphy; D Squirrell
Journal:  Diabet Med       Date:  2020-09-27       Impact factor: 4.359

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.