Dataset Information

Combination of snapshot hyperspectral retinal imaging and optical coherence tomography to identify Alzheimer's disease patients.

ABSTRACT: INTRODUCTION:The eye offers potential for the diagnosis of Alzheimer's disease (AD) with retinal imaging techniques being explored to quantify amyloid accumulation and aspects of neurodegeneration. To assess these changes, this proof-of-concept study combined hyperspectral imaging and optical coherence tomography to build a classification model to differentiate between AD patients and controls. METHODS:In a memory clinic setting, patients with a diagnosis of clinically probable AD (n?=?10) or biomarker-proven AD (n?=?7) and controls (n?=?22) underwent non-invasive retinal imaging with an easy-to-use hyperspectral snapshot camera that collects information from 16 spectral bands (460-620?nm, 10-nm bandwidth) in one capture. The individuals were also imaged using optical coherence tomography for assessing retinal nerve fiber layer thickness (RNFL). Dedicated image preprocessing analysis was followed by machine learning to discriminate between both groups. RESULTS:Hyperspectral data and retinal nerve fiber layer thickness data were used in a linear discriminant classification model to discriminate between AD patients and controls. Nested leave-one-out cross-validation resulted in a fair accuracy, providing an area under the receiver operating characteristic curve of 0.74 (95% confidence interval [0.60-0.89]). Inner loop results showed that the inclusion of the RNFL features resulted in an improvement of the area under the receiver operating characteristic curve: for the most informative region assessed, the average area under the receiver operating characteristic curve was 0.70 (95% confidence interval [0.55, 0.86]) and 0.79 (95% confidence interval [0.65, 0.93]), respectively. The robust statistics used in this study reduces the risk of overfitting and partly compensates for the limited sample size. CONCLUSIONS:This study in a memory-clinic-based cohort supports the potential of hyperspectral imaging and suggests an added value of combining retinal imaging modalities. Standardization and longitudinal data on fully amyloid-phenotyped cohorts are required to elucidate the relationship between retinal structure and cognitive function and to evaluate the robustness of the classification model.

SUBMITTER: Lemmens S

PROVIDER: S-EPMC7654576 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Combination of snapshot hyperspectral retinal imaging and optical coherence tomography to identify Alzheimer's disease patients.

Lemmens Sophie S Van Craenendonck Toon T Van Eijgen Jan J De Groef Lies L Bruffaerts Rose R de Jesus Danilo Andrade DA Charle Wouter W Jayapala Murali M Sunaric-Mégevand Gordana G Standaert Arnout A Theunis Jan J Van Keer Karel K Vandenbulcke Mathieu M Moons Lieve L Vandenberghe Rik R De Boever Patrick P Stalmans Ingeborg I

Alzheimer's research & therapy 20201110 1

<h4>Introduction</h4>The eye offers potential for the diagnosis of Alzheimer's disease (AD) with retinal imaging techniques being explored to quantify amyloid accumulation and aspects of neurodegeneration. To assess these changes, this proof-of-concept study combined hyperspectral imaging and optical coherence tomography to build a classification model to differentiate between AD patients and controls.<h4>Methods</h4>In a memory clinic setting, patients with a diagnosis of clinically probable AD ...[more]

PMID: 33172499

Similar Datasets

Project description:To describe the spectral-domain optical coherence tomography (SD OCT) features of peripheral retinal findings using an ultra-widefield (UWF) steering technique to image the retinal periphery.Observational study.A total of 68 patients (68 eyes) with 19 peripheral retinal features.Spectral-domain OCT-based structural features.Nineteen peripheral retinal features, including vortex vein, congenital hypertrophy of the retinal pigment epithelium, pars plana, ora serrata pearl, typical cystoid degeneration (TCD), cystic retinal tuft, meridional fold, lattice and cobblestone degeneration, retinal hole, retinal tear, rhegmatogenous retinal detachment, typical degenerative senile retinoschisis, peripheral laser coagulation scars, ora tooth, cryopexy scars (retinal tear and treated retinoblastoma scar), bone spicules, white without pressure, and peripheral drusen, were identified by peripheral clinical examination. Near-infrared scanning laser ophthalmoscopy images and SD OCT of these entities were registered to UWF color photographs.Spectral-domain OCT resolved structural features of all peripheral findings. Dilated hyporeflective tubular structures within the choroid were observed in the vortex vein. Loss of retinal lamination, neural retinal attenuation, retinal pigment epithelium loss, or hypertrophy was seen in several entities, including congenital hypertrophy of the retinal pigment epithelium, ora serrata pearl, TCD, cystic retinal tuft, meridional fold, lattice, and cobblestone degenerations. Hyporeflective intraretinal spaces, indicating cystoid or schitic fluid, were seen in ora serrata pearl, ora tooth, TCD, cystic retinal tuft, meridional fold, retinal hole, and typical degenerative senile retinoschisis. The vitreoretinal interface, which often consisted of lamellae-like structures of the condensed cortical vitreous near or adherent to the neural retina, appeared clearly in most peripheral findings, confirming its association with many low-risk and vision-threatening pathologies, such as lattice degeneration, meridional folds, retinal breaks, and rhegmatogenous retinal detachments.Ultra-widefield steering-based SD OCT imaging of the retinal periphery is feasible with current commercially available devices and provides detailed anatomic information of the peripheral retina, including benign and pathologic entities, not previously imaged. This imaging technique may deepen our structural understanding of these entities and their potentially associated macular and systemic pathologies, and may influence decision-making in clinical practice, particularly in areas with teleretinal capabilities but poor access to retinal specialists.

Dataset Information

Combination of snapshot hyperspectral retinal imaging and optical coherence tomography to identify Alzheimer's disease patients.

Publications

Combination of snapshot hyperspectral retinal imaging and optical coherence tomography to identify Alzheimer's disease patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets