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

Abstract

IntroductionThis 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.

Alzheimer’s Retinopathy: Seeing Disease in the Eyes

“…Intriguingly, a similar study from More and colleagues, the team that initially developed the rHSI technique in murine models (More and Vince, 2015;More et al, 2016), found the largest deviation in rHSI signatures between MCI patients and controls, irrespective of other ocular conditions such as cataracts or glaucoma (More et al, 2019). The same technique was able to distinguish cerebral Aβ+ subjects from Aβ− subjects with 85% accuracy based on retinal vascular measures including vessel tortuosity and diameter (Sharafi et al, 2019).…”

Hyperspectral Imaging and the Retina: Worth the Wave?

“…1A3), 54 and tunable laser sources (TLS; Fig. 1A3) 30,32,[55][56][57][58][59][60][61][62][63] became more common and enabled narrow-band imaging. The latter is also being used in transluminance and autofluorescence mode on retinal flatmounts.…”

“…33,46 LCTF and TLS are among the most used in the history of HSI, with commercially available, ready-to-use imagers on the market. 33,46,47,56,58,59,61,[63][64][65] Less common ways to tune the wavelength output of a device is the acousto-optic tunable filter, where the diffraction of crystals is altered by acoustic waves (Fig. 1A3), 66 and a dual-slit scanning monochromator (Fig.…”

“…A variant of linear discriminant analysis produces a "hyperspectral score" that is assumed to be an estimate for retinal amyloid load. 56 Sharafi et al 61 also treat amyloid status as a classification problem and extract a wide range of retinal vessel and texture features from the images, rather than feeding preprocessed spectra directly to the model. These features serve as input to the support vector machine classifier that discriminates amyloid positive patients from amyloid negative individuals.…”

“…These features serve as input to the support vector machine classifier that discriminates amyloid positive patients from amyloid negative individuals. 61…”