Detecting central fixation by means of artificial neural networks in a pediatric vision screener using retinal birefringence scanning

Abstract

BackgroundReliable detection of central fixation and eye alignment is essential in the diagnosis of amblyopia (“lazy eye”), which can lead to blindness. Our lab has developed and reported earlier a pediatric vision screener that performs scanning of the retina around the fovea and analyzes changes in the polarization state of light as the scan progresses. Depending on the direction of gaze and the instrument design, the screener produces several signal frequencies that can be utilized in the detection of central fixation. The objective of this study was to compare artificial neural networks with classical statistical methods, with respect to their ability to detect central fixation reliably.MethodsA classical feedforward, pattern recognition, two-layer neural network architecture was used, consisting of one hidden layer and one output layer. The network has four inputs, representing normalized spectral powers at four signal frequencies generated during retinal birefringence scanning. The hidden layer contains four neurons. The output suggests presence or absence of central fixation. Backpropagation was used to train the network, using the gradient descent algorithm and the cross-entropy error as the performance function. The network was trained, validated and tested on a set of controlled calibration data obtained from 600 measurements from ten eyes in a previous study, and was additionally tested on a clinical set of 78 eyes, independently diagnosed by an ophthalmologist.ResultsIn the first part of this study, a neural network was designed around the calibration set. With a proper architecture and training, the network provided performance that was comparable to classical statistical methods, allowing perfect separation between the central and paracentral fixation data, with both the sensitivity and the specificity of the instrument being 100%. In the second part of the study, the neural network was applied to the clinical data. It allowed reliable separation between normal subjects and affected subjects, its accuracy again matching that of the statistical methods.ConclusionWith a proper choice of a neural network architecture and a good, uncontaminated training data set, the artificial neural network can be an efficient classification tool for detecting central fixation based on retinal birefringence scanning.

Artificial Intelligence Meets Neuro-Ophthalmology

“…AI-techniques have been developed and used to model ocular motor data, 59 predict features associated with congenital nystagmus, 60 and detect strabismus. [61][62][63][64][65][66][67][68][69][70][71][72][73] These techniques could potentially be extended to other causes of ocular misalignment, such as ocular motor cranial nerve palsies.…”

“…These methods require specialized skills by an ophthalmologist or orthoptist who may not always be available. AI-techniques have been developed and used to model ocular motor data, 59 predict features associated with congenital nystagmus, 60 and detect strabismus 61–73 . These techniques could potentially be extended to other causes of ocular misalignment, such as ocular motor cranial nerve palsies.…”

Portable hardware & software technologies for addressing ophthalmic health disparities: A systematic review

“…88 Finally, Gramatikov et al created an artificial neural network to classify retinal birefringence scanning data in the pediatric diagnosis of amblyopia with comparable results to classical statistical methods. 89…”

The Impact of Artificial Intelligence and Deep Learning in Eye Diseases: A Review

“…The review included a total of 69 studies, of which one study was about exophthalmos (13), three about strabismus (14)(15)(16), two studies about eyelid tumors (17,18), three about keratoconus (19)(20)(21), seven about cataracts (22)(23)(24)(25)(26)(27)(28), three about pediatric cataracts (29)(30)(31), one about myopia (32), nine about glaucoma (33)(34)(35)(36)(37)(38)(39)(40)(41), nine studies were about DR (11,34,39,(42)(43)(44)(45)(46)(47), nine about AMD (34,(48)(49)(50)(51)(52)(53)(54)(55), two about retinal detachment (56,57), one about retinal vein occlusion (58), 12 about ROP (59-70), and seven were about teleophthalmology…”

“…This could be beneficial in telemedical evaluation and screening. On the contrary, for in-office evaluation, the CNN could be applied to eye-tracking data (16) or to retinal birefringence scanning (17).…”