Minireviews
Copyright ©The Author(s) 2025.
World J Methodol. Dec 20, 2025; 15(4): 107166
Published online Dec 20, 2025. doi: 10.5662/wjm.v15.i4.107166
Table 2 Various algorithms used in diabetic retinopathy as follows
Study conducted
Algorithms used
Identified and diagnosed
A retrospective study by Liu et al[46], 2022, using traditional fundus images EfficientNet-B5DME
A retrospective study by Dai et al[47], 2021ResNet and Mask R-CNNDR grading
A retrospective study by Lee et al[48], 2021OpthAI, AirDoc, Eyenuk, Retina AI Health, RetmarkerReferable DR detection
A prospective study by Heydon et al[49], 2020EyeArt v2.1Referable DR detection
A prospective study by Gulshan et al[50], 2019Inception-v3Referable DR detection
Akram et al[51] proposed an automated moduleMESSIDOR database usedProposed an automated module for the grading of diabetic maculopathy