Prediction of progressive lens performance from neural network simulations

Abstract

Purpose: Presbyopia, with its gradual loss of accommodation amplitude, is part of the natural human aging process and commonly corrected using progressive addition lenses (PALs). However, the pre-clinical simulation of visual performance is difficult. Therefore, the purpose of this study is to present a framework to predict visual acuity (VA) based on a convolutional neural network (CNN) and to further to compare PAL designs. Method: A simple two hidden layer CNN was trained to classify the gap orientations of Landolt Cs by combining the feature extraction abilities of a CNN with psychophysical staircase methods. The simulation was validated regarding its predictability of clinical VA from induced spherical defocus (between ±1.5 D,step size: 0.5 D) from 39 subjectively measured eyes. Afterwards, a simulation for a presbyopic eye corrected by either a generic hard or a soft PAL design (addition power: 2.5 D) was performed including lower and higher order aberrations. Result: The validation revealed consistent offset of +0.20 logMAR ±0.035 logMAR from simulated VA. Bland-Altman analysis from offset-corrected results showed limits of agreement (±1,96 SD) of -0.08 logMAR and +0.07 logMAR, which is comparable to clinical repeatability of VA assessment. The application of the simulation for PALs confirmed a bigger far zone for generic hard design, but did not reveal zone width differences for the intermediate or near zone. Furthermore, a horizontal area of better VA at the mid of the PAL was found, which confirms the importance for realistic performance simulations using object-based aberration and physiological performance measures as VA. Conclusion: The proposed holistic simulation tool was shown to act as an accurate model for subjective visual performance. Further, the simulation's application for PALs indicated its potential as an effective method to compare visual performance of different optical designs. Moreover, the simulation provides the basis to incorporate neural aspects of visual perception and thus simulate the VA including neural processing in future.

Rendering algorithms for aberrated human vision simulation

“…The main differentiating property of these lenses from traditional spectacle lenses is the continuous change in optical power over their surfaces, which significantly increases the complexity of designing a lens that properly treats the vision of the individual. Vision simulation methods are a quick and inexpensive way to evaluate the performance of various PAL designs in virtual environments [34,42,[85][86][87]. The success of the procedure can be further improved if the knowledge of the user's visual aberrations can be included in the simulation.…”