Vascular retinal biomarkers improves the detection of the likely cerebral amyloid status from hyperspectral retinal images

Abstract Introduction This study investigates the relationship between retinal image features and β‐amyloid (Aβ) burden in the brain with the aim of developing a noninvasive method to predict the deposition of Aβ in the brain of patients with Alzheimer's disease. Methods Retinal images from 20...

Full description

Saved in:
Bibliographic Details
Main Authors: Sayed Mehran Sharafi, Jean‐Philippe Sylvestre, Claudia Chevrefils, Jean‐Paul Soucy, Sylvain Beaulieu, Tharick A. Pascoal, Jean Daniel Arbour, Marc‐André Rhéaume, Alain Robillard, Céline Chayer, Pedro Rosa‐Neto, Sulantha S. Mathotaarachchi, Ziad S. Nasreddine, Serge Gauthier, Frédéric Lesage
Format: Article
Language:English
Published: Wiley 2019-01-01
Series:Alzheimer’s & Dementia: Translational Research & Clinical Interventions
Subjects:
Online Access:https://doi.org/10.1016/j.trci.2019.09.006
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849688387610476544
author Sayed Mehran Sharafi
Jean‐Philippe Sylvestre
Claudia Chevrefils
Jean‐Paul Soucy
Sylvain Beaulieu
Tharick A. Pascoal
Jean Daniel Arbour
Marc‐André Rhéaume
Alain Robillard
Céline Chayer
Pedro Rosa‐Neto
Sulantha S. Mathotaarachchi
Ziad S. Nasreddine
Serge Gauthier
Frédéric Lesage
author_facet Sayed Mehran Sharafi
Jean‐Philippe Sylvestre
Claudia Chevrefils
Jean‐Paul Soucy
Sylvain Beaulieu
Tharick A. Pascoal
Jean Daniel Arbour
Marc‐André Rhéaume
Alain Robillard
Céline Chayer
Pedro Rosa‐Neto
Sulantha S. Mathotaarachchi
Ziad S. Nasreddine
Serge Gauthier
Frédéric Lesage
author_sort Sayed Mehran Sharafi
collection DOAJ
description Abstract Introduction This study investigates the relationship between retinal image features and β‐amyloid (Aβ) burden in the brain with the aim of developing a noninvasive method to predict the deposition of Aβ in the brain of patients with Alzheimer's disease. Methods Retinal images from 20 cognitively impaired and 26 cognitively unimpaired cases were acquired (3 images per subject) using a hyperspectral retinal camera. The cerebral amyloid status was determined from binary reads by a panel of 3 expert raters on 18F‐florbetaben positron‐emission tomography (PET) studies. Image features from the hyperspectral retinal images were calculated, including vessels tortuosity and diameter and spatial‐spectral texture measures in different retinal anatomical regions. Results Retinal venules of amyloid‐positive subjects (Aβ+) showed a higher mean tortuosity compared with the amyloid‐negative (Aβ−) subjects. Arteriolar diameter of Aβ+ subjects was found to be higher than the Aβ− subjects in a zone adjacent to the optical nerve head. Furthermore, a significant difference between texture measures built over retinal arterioles and their adjacent regions were observed in Aβ+ subjects when compared with the Aβ−. A classifier was trained to automatically discriminate subjects combining the extracted features. The classifier could discern Aβ+ subjects from Aβ− subjects with an accuracy of 85%. Discussion Significant differences in texture measures were observed in the spectral range 450 to 550 nm which is known as the spectral region known to be affected by scattering from amyloid aggregates in the retina. This study suggests that the inclusion of metrics related to the retinal vasculature and tissue‐related textures extracted from vessels and surrounding regions could improve the discrimination performance of the cerebral amyloid status.
format Article
id doaj-art-beb153866b404fe8938cbc0f7a7c8308
institution DOAJ
issn 2352-8737
language English
publishDate 2019-01-01
publisher Wiley
record_format Article
series Alzheimer’s & Dementia: Translational Research & Clinical Interventions
spelling doaj-art-beb153866b404fe8938cbc0f7a7c83082025-08-20T03:22:00ZengWileyAlzheimer’s & Dementia: Translational Research & Clinical Interventions2352-87372019-01-015161061710.1016/j.trci.2019.09.006Vascular retinal biomarkers improves the detection of the likely cerebral amyloid status from hyperspectral retinal imagesSayed Mehran Sharafi0Jean‐Philippe Sylvestre1Claudia Chevrefils2Jean‐Paul Soucy3Sylvain Beaulieu4Tharick A. Pascoal5Jean Daniel Arbour6Marc‐André Rhéaume7Alain Robillard8Céline Chayer9Pedro Rosa‐Neto10Sulantha S. Mathotaarachchi11Ziad S. Nasreddine12Serge Gauthier13Frédéric Lesage14Genie Electrique Polytechnique MontrealMontrealQuebecCanadaOptina DiagnosticsMontrealQuebecCanadaOptina DiagnosticsMontrealQuebecCanadaMontreal Neurological Institute, McGill UniversityMontrealQuebecCanadaDépartement de médecine nucléaire, Hôpital Maisonneuve‐RosemontMontrealQuebecCanadaTranslational Neuroimaging Laboratory, McGill Centre for Studies in AgingDouglas Mental Health University InstituteMontrealQuebecCanadaClinique ophtalmologique 2121MontrealQuebecCanadaClinique ophtalmologique 2121MontrealQuebecCanadaDépartement de psychiatrieHôpital Maisonneuve‐RosemontMontrealQuebecCanadaDépartement de psychiatrieHôpital Maisonneuve‐RosemontMontrealQuebecCanadaTranslational Neuroimaging LaboratoryMcGill Centre for Studies in Aging Douglas Mental Health University InstituteMontrealQuebecCanadaTranslational Neuroimaging LaboratoryMcGill Centre for Studies in Aging Douglas Mental Health University InstituteMontrealQuebecCanadaMoCA Clinic and InstituteGreenfield ParkQuebecCanadaAlzheimer's Disease Research UnitThe McGill University Research Centre for Studies in AgingMontrealQuebecCanadaGenie Electrique Polytechnique MontrealMontrealQuebecCanadaAbstract Introduction This study investigates the relationship between retinal image features and β‐amyloid (Aβ) burden in the brain with the aim of developing a noninvasive method to predict the deposition of Aβ in the brain of patients with Alzheimer's disease. Methods Retinal images from 20 cognitively impaired and 26 cognitively unimpaired cases were acquired (3 images per subject) using a hyperspectral retinal camera. The cerebral amyloid status was determined from binary reads by a panel of 3 expert raters on 18F‐florbetaben positron‐emission tomography (PET) studies. Image features from the hyperspectral retinal images were calculated, including vessels tortuosity and diameter and spatial‐spectral texture measures in different retinal anatomical regions. Results Retinal venules of amyloid‐positive subjects (Aβ+) showed a higher mean tortuosity compared with the amyloid‐negative (Aβ−) subjects. Arteriolar diameter of Aβ+ subjects was found to be higher than the Aβ− subjects in a zone adjacent to the optical nerve head. Furthermore, a significant difference between texture measures built over retinal arterioles and their adjacent regions were observed in Aβ+ subjects when compared with the Aβ−. A classifier was trained to automatically discriminate subjects combining the extracted features. The classifier could discern Aβ+ subjects from Aβ− subjects with an accuracy of 85%. Discussion Significant differences in texture measures were observed in the spectral range 450 to 550 nm which is known as the spectral region known to be affected by scattering from amyloid aggregates in the retina. This study suggests that the inclusion of metrics related to the retinal vasculature and tissue‐related textures extracted from vessels and surrounding regions could improve the discrimination performance of the cerebral amyloid status.https://doi.org/10.1016/j.trci.2019.09.006Multispectral fundus imagingAlzheimerBeta amyloidRetinaImage processingMachine learning
spellingShingle Sayed Mehran Sharafi
Jean‐Philippe Sylvestre
Claudia Chevrefils
Jean‐Paul Soucy
Sylvain Beaulieu
Tharick A. Pascoal
Jean Daniel Arbour
Marc‐André Rhéaume
Alain Robillard
Céline Chayer
Pedro Rosa‐Neto
Sulantha S. Mathotaarachchi
Ziad S. Nasreddine
Serge Gauthier
Frédéric Lesage
Vascular retinal biomarkers improves the detection of the likely cerebral amyloid status from hyperspectral retinal images
Alzheimer’s & Dementia: Translational Research & Clinical Interventions
Multispectral fundus imaging
Alzheimer
Beta amyloid
Retina
Image processing
Machine learning
title Vascular retinal biomarkers improves the detection of the likely cerebral amyloid status from hyperspectral retinal images
title_full Vascular retinal biomarkers improves the detection of the likely cerebral amyloid status from hyperspectral retinal images
title_fullStr Vascular retinal biomarkers improves the detection of the likely cerebral amyloid status from hyperspectral retinal images
title_full_unstemmed Vascular retinal biomarkers improves the detection of the likely cerebral amyloid status from hyperspectral retinal images
title_short Vascular retinal biomarkers improves the detection of the likely cerebral amyloid status from hyperspectral retinal images
title_sort vascular retinal biomarkers improves the detection of the likely cerebral amyloid status from hyperspectral retinal images
topic Multispectral fundus imaging
Alzheimer
Beta amyloid
Retina
Image processing
Machine learning
url https://doi.org/10.1016/j.trci.2019.09.006
work_keys_str_mv AT sayedmehransharafi vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT jeanphilippesylvestre vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT claudiachevrefils vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT jeanpaulsoucy vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT sylvainbeaulieu vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT tharickapascoal vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT jeandanielarbour vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT marcandrerheaume vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT alainrobillard vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT celinechayer vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT pedrorosaneto vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT sulanthasmathotaarachchi vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT ziadsnasreddine vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT sergegauthier vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages
AT fredericlesage vascularretinalbiomarkersimprovesthedetectionofthelikelycerebralamyloidstatusfromhyperspectralretinalimages