Table 1.

Automated keratoconus detection methods.

Reference	Achievement	Method	Dataset	Results
[5] Dhaini, A.R.; et al., 2018	Corneal haze and demarcation line measurement.	Image analysis and machine learning	140 Keratoconus eyes for actual patients	The mean demarcation line is 295.9 ± 59.8 microns, and it is 314.5 ± 48.4 microns by medical personal.
[6] Daud, M.M.; et al., 2020	Keratoconus detection method	Digital image analysis processing	140 cases captured by smartphone	Accuracy of 96.03%
[7] Ali, A.H.; et al., 2018	Keratoconus supervised learning and detection	Support vector machine using image processing techniques	240 cases were attained from Al-Amal Eye Clinic in Baghdad utilizing a Pentacam	Accuracy of 90%
[9] Askarian, B.; et al., 2018	Diagnostic method for keratoconus detection	Usage of a smartphone	175 images of keratoconus cases	Accuracies of 93%, 67% in severe, and moderate cases, respectively.
The proposed method	Automated keratoconus detection	Depth calculation from 3D corneal image and machine learning	268 Corneal images of Keratoconus and normal cases	Accuracy is 97.8%