Deep-learning retinal vessel calibre measurements and risk of cognitive decline and dementia

Carol Y Cheung; Win Lee Edwin Wong; Saima Hilal; Cheuk Ni Kan; Bibek Gyanwali; Yih Chung Tham; Leopold Schmetterer; Dejiang Xu; Mong Li Lee; Wynne Hsu; Narayanaswamy Venketasubramanian; Boon Yeow Tan; Tien Yin Wong; Christopher P L H Chen

doi:10.1093/braincomms/fcac212

Deep-learning retinal vessel calibre measurements and risk of cognitive decline and dementia

Brain Commun. 2022 Aug 17;4(4):fcac212. doi: 10.1093/braincomms/fcac212. eCollection 2022.

Authors

Carol Y Cheung¹, Win Lee Edwin Wong^{2

3}, Saima Hilal^{2

3

4}, Cheuk Ni Kan^{2

3}, Bibek Gyanwali^{2

3

5}, Yih Chung Tham^{6

7}, Leopold Schmetterer^{6

8

9

10

11}, Dejiang Xu¹², Mong Li Lee¹², Wynne Hsu¹², Narayanaswamy Venketasubramanian¹³, Boon Yeow Tan¹⁴, Tien Yin Wong^{6

7}, Christopher P L H Chen^{2

3

15}

Affiliations

¹ Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong, China.
² Department of Pharmacology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore 117600, Singapore.
³ Memory Ageing and Cognition Centre, National University Health System, Singapore 119074, Singapore.
⁴ Saw Swee Hock School of Public Health, National University of Singapore and National University Health System, Singapore 117549, Singapore.
⁵ Department of Biochemistry, Yong Loo Lin School of Medicine, National University of Singapore, Singapore 117600, Singapore.
⁶ Singapore Eye Research Institute, Singapore National Eye Centre, Singapore 169856, Singapore.
⁷ Ophthalmology and Visual Sciences Academic Clinical Programme, Duke-NUS Medical School, Singapore 169857, Singapore.
⁸ School of Chemical and Biomedical Engineering, Nanyang Technological University, Singapore 639798, Singapore.
⁹ Department of Clinical Pharmacology, Medical University Vienna, Vienna 1090, Austria.
¹⁰ Austria Center for Medical Physics and Biomedical Engineering, Medical University Vienna, Vienna 1090, Austria.
¹¹ Institute of Molecular and Clinical Ophthalmology, Basel, Switzerland.
¹² School of Computing, National University of Singapore, Singapore 117417, Singapore.
¹³ Raffles Neuroscience Centre, Raffles Hospital, Singapore, Singapore 188770, Singapore.
¹⁴ St. Luke's Hospital, Singapore, Singapore 659674, Singapore.
¹⁵ Department of Psychological Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore 117600, Singapore.

Abstract

Previous studies have explored the associations of retinal vessel calibre, measured from retinal photographs or fundus images using semi-automated computer programs, with cognitive impairment and dementia, supporting the concept that retinal blood vessels reflect microvascular changes in the brain. Recently, artificial intelligence deep-learning algorithms have been developed for the fully automated assessment of retinal vessel calibres. Therefore, we aimed to determine whether deep-learning-based retinal vessel calibre measurements are predictive of risk of cognitive decline and dementia. We conducted a prospective study recruiting participants from memory clinics at the National University Hospital and St. Luke's Hospital in Singapore; all participants had comprehensive clinical and neuropsychological examinations at baseline and annually for up to 5 years. Fully automated measurements of retinal arteriolar and venular calibres from retinal fundus images were estimated using a deep-learning system. Cox regression models were then used to assess the relationship between baseline retinal vessel calibre and the risk of cognitive decline and developing dementia, adjusting for age, gender, ethnicity, education, cerebrovascular disease status, hypertension, hyperlipidemia, diabetes, and smoking. A total of 491 participants were included in this study, of whom 254 developed cognitive decline over 5 years. In multivariable models, narrower retinal arteriolar calibre (hazard ratio per standard deviation decrease = 1.258, P = 0.008) and wider retinal venular calibre (hazard ratio per standard deviation increase = 1.204, P = 0.037) were associated with increased risk of cognitive decline. Among participants with cognitive impairment but no dementia at baseline (n = 212), 44 progressed to have incident dementia; narrower retinal arteriolar calibre was also associated with incident dementia (hazard ratio per standard deviation decrease = 1.624, P = 0.021). In summary, deep-learning-based measurement of retinal vessel calibre was associated with risk of cognitive decline and dementia.

Keywords: cognitive decline; deep-learning system; dementia; retinal imaging; retinal vessel calibre.