Related Experiment Video
Updated: Jun 8, 2025
Three Different Protocols of Corneal Collagen Crosslinking in Keratoconus: Conventional, Accelerated and Iontophoresis
Published on: November 12, 2015
Artificial intelligence versus conventional methods for RGP lens fitting in keratoconus
Jérémy Abadou1, Simon Dahan2, Juliette Knoeri1
1Groupe de Recherche Clinique #32, Transplantation et Thérapies Innovantes de la Cornée, Sorbonne Université, Hôpital National des 15-20, Paris, France.
Background:
To compare the efficiency of three artificial intelligence (AI) frameworks (Standard Machine Learning (ML), Multi-Layer Perceptron (MLP) and Convolution Neural Networks (CNN)) with a reference method (Mean radius of curvature (K)) to predict the posterior radius of curvature of the best-fitted rigid contact lens (RCBFL) in keratoconus eyes.
Methods:
This retrospective study included 197 keratoconus eyes of 135 patients fitted with Rose K2® (Menicon®, Nagoya, Japan) rigid contact lenses with one or more topographies available (MS39®, CSO®, Ferrara, Italy) between January 2020 and September 2022. Two types of topographic data (indices and reconstructed maps from raw data) were used for AI analysis. Three distinct approaches were utilized for leveraging AI: Standard ML methods and MLPs based on topographic indices and CNNs based on topographic maps (i.e., corneal thickness, sagittal, and tangential maps). Seventeen AI framework's accuracies were compared with the r2 determination coefficient of linear regression between predicted and best-fitted radii. Framework accuracies were compared with the Fisher z-transformation of Pearson correlation coefficients.
Results:
In multiple linear regression, only three topographic indices (i.e., 3- & 5-mm mean K and Kmax) were significantly associated with RCBFL (p ≤ 0.0001). Compared with the reference method (mean-K; r2 = 0.36), a significantly better RCBFL prediction was achieved with Random Forest using the three topographic indices, MLP using all indices, ResNet18 CNN using anterior topographic maps and CNNs using combined parameters (0.69 ≤ r2 ≤ 0.80; p < 0.05). The best accuracy was obtained with the EfficientNetB0 CNN trained with three maps (r2 = 0.80).
Conclusions:
Artificial intelligence methods, particularly CNNs, with corneal topography data of MS39® topographer, have demonstrated superiority over conventional approaches in predicting the posterior curvature radius of Rose K2® rigid contact lenses in patients with keratoconus.
