TY - JOUR
T1 - Visual Field Estimation by Probabilistic Classification
AU - Chesley, Brian
AU - Barbour, Dennis L.
N1 - Funding Information:
Manuscript received December 30, 2019; revised April 3, 2020 and May 25, 2020; accepted May 26, 2020. Date of publication June 2, 2020; date of current version December 4, 2020. This work was supported in part by the Awards from the National Eye Institute, the National Center on Minority Health and Health Disparities, in part by the National Institutes of Health under Grants R01-EY09341, R01-EY09307, in part by the Horncrest Foundation, in part by awards to the Department of Ophthalmology and Visual Sciences at Washington University, in part by the NIH Vision Core under Grant P30-EY02687, in part by the Merck Research Laboratories, Pfizer, Inc., White House Station, New Jersey, and in part by unrestricted grants from Research to Prevent Blindness, Inc., New York, NY. (Corresponding author: Dennis L. Barbour.) Brian Chesley is with the Department of Mathematics and Statistics, Washington University in St. Louis, Saint Louis, MO 63130 USA (e-mail: [email protected]).
Publisher Copyright:
© 2013 IEEE.
PY - 2020/12
Y1 - 2020/12
N2 - The gold standard clinical tool for evaluating visual dysfunction in cases of glaucoma and other disorders of vision remains the visual field or threshold perimetry exam. Administration of this exam has evolved over the years into a sophisticated, standardized, automated algorithm that relies heavily on specifics of disease processes particular to common retinal disorders. The purpose of this study is to evaluate the utility of a novel general estimator applied to visual field testing. A multidimensional psychometric function estimation tool was applied to visual field estimation. This tool is built on semiparametric probabilistic classification rather than multiple logistic regression. It combines the flexibility of nonparametric estimators and the efficiency of parametric estimators. Simulated visual fields were generated from human patients with a variety of diagnoses, and the errors between simulated ground truth and estimated visual fields were quantified. Error rates of the estimates were low, typically within 2 dB units of ground truth on average. The greatest threshold errors appeared to be confined to the portions of the threshold function with the highest spatial frequencies. This method can accurately estimate a variety of visual field profiles with continuous threshold estimates, potentially using a relatively small number of stimuli.
AB - The gold standard clinical tool for evaluating visual dysfunction in cases of glaucoma and other disorders of vision remains the visual field or threshold perimetry exam. Administration of this exam has evolved over the years into a sophisticated, standardized, automated algorithm that relies heavily on specifics of disease processes particular to common retinal disorders. The purpose of this study is to evaluate the utility of a novel general estimator applied to visual field testing. A multidimensional psychometric function estimation tool was applied to visual field estimation. This tool is built on semiparametric probabilistic classification rather than multiple logistic regression. It combines the flexibility of nonparametric estimators and the efficiency of parametric estimators. Simulated visual fields were generated from human patients with a variety of diagnoses, and the errors between simulated ground truth and estimated visual fields were quantified. Error rates of the estimates were low, typically within 2 dB units of ground truth on average. The greatest threshold errors appeared to be confined to the portions of the threshold function with the highest spatial frequencies. This method can accurately estimate a variety of visual field profiles with continuous threshold estimates, potentially using a relatively small number of stimuli.
KW - Active machine learning
KW - diagnostics
KW - psychophysics
KW - retina
KW - threshold perimetry
KW - visual fields
UR - https://www.scopus.com/pages/publications/85097571229
U2 - 10.1109/JBHI.2020.2999567
DO - 10.1109/JBHI.2020.2999567
M3 - Article
C2 - 32750922
AN - SCOPUS:85097571229
SN - 2168-2194
VL - 24
SP - 3499
EP - 3506
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
IS - 12
M1 - 9106830
ER -