Cargando…

Identifying the Retinal Layers Linked to Human Contrast Sensitivity Via Deep Learning

PURPOSE: Luminance contrast is the fundamental building block of human spatial vision. Therefore contrast sensitivity, the reciprocal of contrast threshold required for target detection, has been a barometer of human visual function. Although retinal ganglion cells (RGCs) are known to be involved in...

Descripción completa

Detalles Bibliográficos
Autores principales: Shamsi, Foroogh, Liu, Rong, Owsley, Cynthia, Kwon, MiYoung
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Association for Research in Vision and Ophthalmology 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8859491/
https://www.ncbi.nlm.nih.gov/pubmed/35179554
http://dx.doi.org/10.1167/iovs.63.2.27
_version_ 1784654473342222336
author Shamsi, Foroogh
Liu, Rong
Owsley, Cynthia
Kwon, MiYoung
author_facet Shamsi, Foroogh
Liu, Rong
Owsley, Cynthia
Kwon, MiYoung
author_sort Shamsi, Foroogh
collection PubMed
description PURPOSE: Luminance contrast is the fundamental building block of human spatial vision. Therefore contrast sensitivity, the reciprocal of contrast threshold required for target detection, has been a barometer of human visual function. Although retinal ganglion cells (RGCs) are known to be involved in contrast coding, it still remains unknown whether the retinal layers containing RGCs are linked to a person's contrast sensitivity (e.g., Pelli-Robson contrast sensitivity) and, if so, to what extent the retinal layers are related to behavioral contrast sensitivity. Thus the current study aims to identify the retinal layers and features critical for predicting a person's contrast sensitivity via deep learning. METHODS: Data were collected from 225 subjects including individuals with either glaucoma, age-related macular degeneration, or normal vision. A deep convolutional neural network trained to predict a person's Pelli-Robson contrast sensitivity from structural retinal images measured with optical coherence tomography was used. Then, activation maps that represent the critical features learned by the network for the output prediction were computed. RESULTS: The thickness of both ganglion cell and inner plexiform layers, reflecting RGC counts, were found to be significantly correlated with contrast sensitivity (r = 0.26 ∼ 0.58, Ps < 0.001 for different eccentricities). Importantly, the results showed that retinal layers containing RGCs were the critical features the network uses to predict a person's contrast sensitivity (an average R(2) = 0.36 ± 0.10). CONCLUSIONS: The findings confirmed the structure and function relationship for contrast sensitivity while highlighting the role of RGC density for human contrast sensitivity.
format Online
Article
Text
id pubmed-8859491
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher The Association for Research in Vision and Ophthalmology
record_format MEDLINE/PubMed
spelling pubmed-88594912022-02-22 Identifying the Retinal Layers Linked to Human Contrast Sensitivity Via Deep Learning Shamsi, Foroogh Liu, Rong Owsley, Cynthia Kwon, MiYoung Invest Ophthalmol Vis Sci Visual Psychophysics and Physiological Optics PURPOSE: Luminance contrast is the fundamental building block of human spatial vision. Therefore contrast sensitivity, the reciprocal of contrast threshold required for target detection, has been a barometer of human visual function. Although retinal ganglion cells (RGCs) are known to be involved in contrast coding, it still remains unknown whether the retinal layers containing RGCs are linked to a person's contrast sensitivity (e.g., Pelli-Robson contrast sensitivity) and, if so, to what extent the retinal layers are related to behavioral contrast sensitivity. Thus the current study aims to identify the retinal layers and features critical for predicting a person's contrast sensitivity via deep learning. METHODS: Data were collected from 225 subjects including individuals with either glaucoma, age-related macular degeneration, or normal vision. A deep convolutional neural network trained to predict a person's Pelli-Robson contrast sensitivity from structural retinal images measured with optical coherence tomography was used. Then, activation maps that represent the critical features learned by the network for the output prediction were computed. RESULTS: The thickness of both ganglion cell and inner plexiform layers, reflecting RGC counts, were found to be significantly correlated with contrast sensitivity (r = 0.26 ∼ 0.58, Ps < 0.001 for different eccentricities). Importantly, the results showed that retinal layers containing RGCs were the critical features the network uses to predict a person's contrast sensitivity (an average R(2) = 0.36 ± 0.10). CONCLUSIONS: The findings confirmed the structure and function relationship for contrast sensitivity while highlighting the role of RGC density for human contrast sensitivity. The Association for Research in Vision and Ophthalmology 2022-02-18 /pmc/articles/PMC8859491/ /pubmed/35179554 http://dx.doi.org/10.1167/iovs.63.2.27 Text en Copyright 2022 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
spellingShingle Visual Psychophysics and Physiological Optics
Shamsi, Foroogh
Liu, Rong
Owsley, Cynthia
Kwon, MiYoung
Identifying the Retinal Layers Linked to Human Contrast Sensitivity Via Deep Learning
title Identifying the Retinal Layers Linked to Human Contrast Sensitivity Via Deep Learning
title_full Identifying the Retinal Layers Linked to Human Contrast Sensitivity Via Deep Learning
title_fullStr Identifying the Retinal Layers Linked to Human Contrast Sensitivity Via Deep Learning
title_full_unstemmed Identifying the Retinal Layers Linked to Human Contrast Sensitivity Via Deep Learning
title_short Identifying the Retinal Layers Linked to Human Contrast Sensitivity Via Deep Learning
title_sort identifying the retinal layers linked to human contrast sensitivity via deep learning
topic Visual Psychophysics and Physiological Optics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8859491/
https://www.ncbi.nlm.nih.gov/pubmed/35179554
http://dx.doi.org/10.1167/iovs.63.2.27
work_keys_str_mv AT shamsiforoogh identifyingtheretinallayerslinkedtohumancontrastsensitivityviadeeplearning
AT liurong identifyingtheretinallayerslinkedtohumancontrastsensitivityviadeeplearning
AT owsleycynthia identifyingtheretinallayerslinkedtohumancontrastsensitivityviadeeplearning
AT kwonmiyoung identifyingtheretinallayerslinkedtohumancontrastsensitivityviadeeplearning