TY - JOUR
T1 - Detecting central fixation by means of artificial neural networks in a pediatric vision screener using retinal birefringence scanning
AU - Gramatikov, Boris I.
N1 - Funding Information:
This work, as well as the development of the Pediatric Vision Screener, was supported by an Individual Biomedical Research Award from The Hartwell Foundation, gifts from Robert and Maureen Feduniak, Dewey and Janet Gargiulo, David and Helen Leighton, Richard and Victoria Baks, Robert and Diane Levy, by Research to Prevent Blindness, and by the Knights Templar Eye Foundation.
Publisher Copyright:
© 2017 The Author(s).
PY - 2017/4/27
Y1 - 2017/4/27
N2 - Background: Reliable 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. Methods: A 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. Results: In 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. Conclusion: With 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.
AB - Background: Reliable 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. Methods: A 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. Results: In 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. Conclusion: With 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.
KW - Amblyopia
KW - Artificial neural networks
KW - Birefringence
KW - Fixation detection
KW - Retina
KW - Strabismus
KW - Vision screener
UR - http://www.scopus.com/inward/record.url?scp=85018342144&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85018342144&partnerID=8YFLogxK
U2 - 10.1186/s12938-017-0339-6
DO - 10.1186/s12938-017-0339-6
M3 - Article
C2 - 28449714
AN - SCOPUS:85018342144
SN - 1475-925X
VL - 16
JO - BioMedical Engineering Online
JF - BioMedical Engineering Online
IS - 1
M1 - 52
ER -