Browsing by Author "Polascik, Bryce W"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Choroidal Structural Analysis in Alzheimer's Disease, Mild Cognitive Impairment, and Cognitively Healthy Controls.
    (Am J Ophthalmol, 2020-10-08) Robbins, Cason B; Grewal, Dilraj S; Thompson, Atalie C; Powers, James H; Soundararajan, Srinath; Koo, Hui Yan; Yoon, Stephen P; Polascik, Bryce W; Liu, Andy; Agrawal, Rupesh; Fekrat, Sharon
    PURPOSE: To assess choroidal structural parameters in symptomatic Alzheimer's disease (AD), mild cognitive impairment (MCI), and cognitively healthy controls. DESIGN: Prospective cross-sectional study. METHODS: Setting: Outpatient neurological disorders clinic. STUDY POPULATION: One hundred and twelve eyes of 67 individuals with AD, 143 eyes of 74 individuals with MCI, and 248 eyes of 137 controls. Individuals with diabetes, glaucoma, or retinal pathology were excluded. OBSERVATION PROCEDURE: High-definition EDI foveal scans were obtained using Zeiss Cirrus HD-5000 AngioPlex (Carl Zeiss Meditec, Dublin, CA). Subfoveal choroidal thickness (SFCT) was measured by two masked graders with a third adjudicator. Total choroidal area (TCA), luminal area (LA), and choroidal vascularity index (CVI) were calculated after image binarization. MAIN OUTCOME MEASURES: Association of choroidal parameters with AD, MCI, or controls using generalized estimating equations, adjusted for age and sex. RESULTS: After adjustment for age, sex, and visual acuity, TCA was significantly greater in AD (ß 2.73, p = 0.001) and MCI (ß 4.38, p < 0.001) compared to controls, LA was significantly greater in AD (ß 1.68, p = 0.001) and MCI (ß 2.69, p < 0.001) compared to controls, and CVI was significantly lower in MCI (ß -0.58, p = 0.002) compared to controls. SFCT was similar among AD, MCI, and controls on multivariable analysis (p > 0.05). CONCLUSIONS: TCA, LA, and CVI may differ between individuals with AD, MCI, and healthy cognition, whereas SFCT may not differ between these groups. TCA, LA, and CVI deserve further study in individuals along the Alzheimer's continuum.
  • Thumbnail Image
    ItemOpen Access
    Convolutional neural network to identify symptomatic Alzheimer's disease using multimodal retinal imaging.
    (The British journal of ophthalmology, 2020-11-26) Wisely, C Ellis; Wang, Dong; Henao, Ricardo; Grewal, Dilraj S; Thompson, Atalie C; Robbins, Cason B; Yoon, Stephen P; Soundararajan, Srinath; Polascik, Bryce W; Burke, James R; Liu, Andy; Carin, Lawrence; Fekrat, Sharon
    BACKGROUND/AIMS:To develop a convolutional neural network (CNN) to detect symptomatic Alzheimer's disease (AD) using a combination of multimodal retinal images and patient data. METHODS:Colour maps of ganglion cell-inner plexiform layer (GC-IPL) thickness, superficial capillary plexus (SCP) optical coherence tomography angiography (OCTA) images, and ultra-widefield (UWF) colour and fundus autofluorescence (FAF) scanning laser ophthalmoscopy images were captured in individuals with AD or healthy cognition. A CNN to predict AD diagnosis was developed using multimodal retinal images, OCT and OCTA quantitative data, and patient data. RESULTS:284 eyes of 159 subjects (222 eyes from 123 cognitively healthy subjects and 62 eyes from 36 subjects with AD) were used to develop the model. Area under the receiving operating characteristic curve (AUC) values for predicted probability of AD for the independent test set varied by input used: UWF colour AUC 0.450 (95% CI 0.282, 0.592), OCTA SCP 0.582 (95% CI 0.440, 0.724), UWF FAF 0.618 (95% CI 0.462, 0.773), GC-IPL maps 0.809 (95% CI 0.700, 0.919). A model incorporating all images, quantitative data and patient data (AUC 0.836 (CI 0.729, 0.943)) performed similarly to models only incorporating all images (AUC 0.829 (95% CI 0.719, 0.939)). GC-IPL maps, quantitative data and patient data AUC 0.841 (95% CI 0.739, 0.943). CONCLUSION:Our CNN used multimodal retinal images to successfully predict diagnosis of symptomatic AD in an independent test set. GC-IPL maps were the most useful single inputs for prediction. Models including only images performed similarly to models also including quantitative data and patient data.