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

Sayed Mehran Sharafi1, Jean-Philippe Sylvestre2, Claudia Chevrefils2, Jean-Paul Soucy3, Sylvain Beaulieu4, Tharick A. Pascoal5, Jean Daniel Arbour6, Marc-André Rhéaume6, Alain Robillard7, Céline Chayer7, Pedro Rosa-Neto5, Sulantha S. Mathotaarachchi5, Ziad S. Nasreddine8, Serge Gauthier9, Frédéric Lesage1,10
1Genie Electrique, Polytechnique Montreal, Montreal, Quebec, Canada
2Optina Diagnostics, Montreal, Quebec, Canada
3Montreal Neurological Institute, McGill University, Montreal, Quebec, Canada
4Département de médecine nucléaire, Hôpital Maisonneuve-Rosemont, Montreal, Quebec, Canada
5Translational Neuroimaging Laboratory, McGill Centre for Studies in Aging, Douglas Mental Health University Institute, Montreal, Quebec, Canada
6Clinique ophtalmologique 2121, Montreal, Quebec, Canada
7Département de psychiatrie, Hôpital Maisonneuve-Rosemont, Montreal, Quebec, Canada
8MoCA Clinic and Institute, Greenfield Park, Quebec, Canada
9Alzheimer's Disease Research Unit, The McGill University Research Centre for Studies in Aging, Montreal, Quebec, Canada
10Research Center, Montreal Heart Institute, Montreal, Quebec, Canada

Tóm tắt

AbstractIntroductionThis 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.MethodsRetinal 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.ResultsRetinal 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%.DiscussionSignificant 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.

Tài liệu tham khảo

10.1038/nrdp.2015.56 10.1016/j.jalz.2018.02.018 10.1016/j.jalz.2017.09.009 Grundman M., 2016, Effect of amyloid imaging on the diagnosis and management of patients with cognitive decline: impact of appropriate use criteria, Dement Geriatr Cogn Disord, 41, 80, 10.1159/000441139 10.1016/j.jalz.2017.08.003 10.1016/j.cca.2016.05.014 10.1016/S1474-4422(16)00070-3 10.3389/fneur.2016.00055 10.1038/mp.2016.251 10.1016/j.clineuro.2011.02.014 10.1167/iovs.06-1029 10.1097/WCO.0b013e328334e99b 10.1016/j.neulet.2007.02.090 10.1016/S1388-2457(01)00620-4 Jiménez‐Jiménez F.J., 2014, Cerebrospinal fluid biochemical studies in patients with Parkinson's disease: toward a potential search for biomarkers for this disease, Front Cell Neurosci, 8, 369 10.1002/mds.25543 10.1016/j.exer.2014.08.006 10.1016/j.neuroimage.2010.06.020 10.2353/ajpath.2009.090159 10.1167/iovs.08-1849 10.1167/iovs.08-2384 10.1016/j.jalz.2014.04.341 10.1172/jci.insight.93621 10.1111/j.1471-4159.2007.04613.x 10.1074/jbc.M404751200 10.1177/1533317513520214 Dentchev T., 2003, Amyloid‐beta is found in drusen from some age‐related macular degeneration retinas, but not in drusen from normal retinas, Mol Vis, 9, 184 10.1016/S0140-6736(03)12981-9 10.1073/pnas.192203399 10.1021/cn500242z 10.1167/iovs.15-17406 Feke G.T., 2015, Retinal blood flow in mild cognitive impairment and Alzheimer's disease, Alzheimers Dement, 1, 144 10.1038/tp.2012.150 10.3389/fnins.2016.00536 Williams M.A., 2015, Retinal microvascular network attenuation in Alzheimer's disease, Alzheimers Dement, 1, 229 10.1016/S1350-4533(00)00074-6 Koh V., 2010, Relationship of retinal vascular tortuosity with the neuroretinal rim: the singapore malay eye study, Invest Ophthalmol Vis Sci, 51, 3736, 10.1167/iovs.09-5008 Koprowski R., 2012, Fully automatic algorithm for the analysis of vessels in the angiographic image of the eye fundus, Biomed Eng Online, 11, 35, 10.1186/1475-925X-11-35 10.1167/iovs.08-3018 Ţălu Ş., 2013, Characterization of retinal vessel networks in human retinal imagery using quantitative descriptors, Human Veter Med, 5, 52 10.1016/j.ophtha.2010.08.045 10.1016/j.atherosclerosis.2014.06.018 10.3109/08820530903400739 Kanski J.J., 2007, Clinical ophthalmology : a systematic approach Longmuir S.Q., 2009, Retinal Arterial but not Venous Tortuosity correlates with Facioscapulohumeral Muscular Dystrophy (FSHD) Severity, Invest Ophthalmol Vis Sci, 50, 5419 10.1007/s00415-014-7374-z 10.1186/s12916-014-0206-2 10.1016/j.exer.2016.04.001 Optina Diagnostics. [Online] Available at:http://optinadx.com/Accessed April 3 2019. M.Patasius V.Marozas D.Jegelevicius andA.Lukosevicius.Evaluation of tortuosity of eye blood vessels using the integral of square of derivative of curvature.IFMBE Proc 3rd Eur Med Biol Eng Conf.(EMBEC05).2005;11 M.Abdalla A.Hunter andB.Al‐Diri.Quantifying retinal blood vessels' tortuosity—Review.2015 Science and Information Conference (SAI).2015;687–693 10.1109/TSMC.1973.4309314 10.1111/j.1365-2990.2010.01139.x 10.1016/j.jalz.2013.06.009 Soucy J.‐P., 2018, 2018 Neuroscience Meeting Planner, 14