Convolutional neural network to identify symptomatic Alzheimer’s disease using multimodal retinal imaging

• Published in: British journal of ophthalmology Vol. 106; no. 3; pp. 388 - 395
• Main Authors: 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
• Format: Journal Article
• Language: English
• Published: BMA House, Tavistock Square, London, WC1H 9JR BMJ Publishing Group Ltd 01.03.2022; BMJ Publishing Group LTD
• Subjects: Alzheimer Disease - diagnostic imaging; Alzheimer's disease; Biomarkers; Clinical science; diagnostic tests/investigation; Fluorescein Angiography - methods; Humans; imaging; Machine learning; Medical diagnosis; Medical imaging; Neural networks; Neural Networks, Computer; Patients; Retina; Retina - diagnostic imaging; Retinal Vessels; Tomography; Tomography, Optical Coherence - methods; United States > US; California; retina; diagnostic tests/investigation; imaging
• ISSN: 0007-1161; 1468-2079; 1468-2079
• DOI: 10.1136/bjophthalmol-2020-317659

Background/AimsTo develop a convolutional neural network (CNN) to detect symptomatic Alzheimer’s disease (AD) using a combination of multimodal retinal images and patient data.MethodsColour 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.Results284 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).ConclusionOur 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.