Automatic Retinal Image Analysis (ARIA)

Introduction to Automatic Retinal Image Analysis (ARIA)

 

Selected Peer-reviewed Publications and Awards (Relevant to ARIA technology only)

 

CUHK Develops Automatic Retinal Image Analysis Technology for Identifying Autism Making Objective Screening and Early Intervention Possible 中大成功研發「全自動視網膜圖像分析」技術計算自閉症風險 可用於自閉症篩查 及早為患者提供治療

The Faculty of Medicine at The Chinese University of Hong Kong (CU Medicine) has successfully developed the Automatic Retinal Image Analysis (ARIA) technology to assess the risk of autism spectrum disorder (Autism). It is done by analysing the captured retinal images to identify if there are any retinal characteristics such as those related to thinning of the retinal nerve fibre layer of the children’s eyes. The research team hopes that ARIA technology can be used as a risk assessment tool for autism screening and provide early intervention instead of waiting for a lengthy diagnosis so that a difference can be made through a long term positive impact on the life of autistic children. Results of the study can be found in the journal EClinicalMedicine published by The Lancet. (A machine learning approach for retinal images analysis as an objective screening method for children with autism spectrum disorder”, EClinicalMedicine 2020, 100588)

  20210104_1

 

Introduction to ARIA-eWMH

ARIA-eWMH was developed to assess the risk of severe age-related white matter hyperintensities (ARWMH) in the brain based on automatic retinal images analysis (ARIA), using cerebral magnetic resonance imaging (MRI) as a gold standard and achieved more than 90% sensitivity and specificity. [1] White matter hyperintensities (WMH) in the brain are the consequence of cerebral small vessel disease (SVD). WMH volume is significantly associated with multiple cognitive domains, including memory, conceptualization,  motor abnormalities and visual practical skills. [2, 3] Longitudinal studies have confirmed that worsening of white matter lesions contributes to brain atrophy and cognitive decline. [4] WMH may progress but it may also regress over time as shown by repeated MRI studies. [5, 6] WHM was shown to be a core feature of Alzheimer’s disease and WMH volumes may start to appear approximately 5-6 years prior to expected symptom onset. [7, 8, 9]  Cerebral beta-amyloid protein, which is believed to be one of the plausible explanations of Alzheimer’s disease, is significantly associated with WMH volume (p=0.03) and apolipoprotein E (APOE) ε4 status (p=0.002) in the preclinical stage.[10] Elahi et al. (2021) suggest that APOE ε4 affects capillary health in humans and that retinal capillary measures could serve as surrogates for brain capillaries. [11] 

ARIA-eWMH利用全自動視網膜圖像分析方法 (ARIA) 並以腦磁共振成像（MRI）作為分析標準，計算腦內是否有嚴重的年齡性白質病變（ARWMH）風險，這技術有超過90％的靈敏度和特異性。[1] 腦內白質病變（WMH）是腦小血管疾病的結果。WMH量與多個認知領域顯著相關，包括記憶，概念化和視覺實踐技能 [2, 3] 。縱向研究證實，白質病變的惡化導致腦萎縮和認知能力下降。[4] 從一些重複MRI研究所示，WMH可能隨著時間增加也有可能減少 [5, 6] 。WHM被證明是阿爾茨海默病的核心特徵，WMH體積可能在預期症狀發作前約5-6年開始出現。腦β-澱粉樣蛋白被認為是阿爾茨海默病的合理解釋之一，與臨床前階段的WMH體積（p = 0.03）和載脂蛋白E（APOE）ε4狀態（p = 0.002）顯著相關。[10] Elahi et al. (2021) 建議APOE ε4 影響人類的毛細血管健康，並且視網膜毛細血管測量可以作為腦毛細血管的替代物。 [11]

IMG-20181122-WA0015 

 

The Automatic Retinal Image Analysis (ARIA) technology has been licensed to Health View Bioanalytic Limited 

HVB_logo EN and CN 

 

 

 

Potential Intervention for Better Cognitive Health 

Health View Bioanalytic presented in the Hong Kong International Medical and Healthcare Fair 2019 with a theme on Biomedical Technologies that are changing Healthcare, a seminar entitled: “A Healthy Lifestyle for a Better Brain Health: Estimate Risk of Age-related White Matter Hyperintensities using ARIA-eWMH”.

The following are selected references on potential preventive interventions from the WHO Guidelines and other sources:

  • Physical Activity
    • Association between exercise and the risk of dementia: results from a nationwide longitudinal study in China. BMJ Open. 2017 Dec 4;7(12):e017497. doi: 10.1136/bmjopen-2017-017497
  • Nutrition Intervention
    • Adherence to a Mediterranean-Style Diet and Effects on Cognition in Adults: A Qualitative Evaluation and Systematic Review of Longitudinal and Prospective Trials. Front. Nutr., 22 July 2016 | https://doi.org/10.3389/fnut.2016.00022
    • Adherence to a Mediterranean-type dietary pattern and cognitive decline in a community population. Am J Clin Nutr. 2011 Mar;93(3):601-7. doi: 10.3945/ajcn.110.007369. Epub 2010 Dec 22.
    • Mediterranean diet, healthy eating index 2005, and cognitive function in middle-aged and older Puerto Rican adults. J Acad Nutr Diet. 2013 Feb;113(2):276-81.e1-3. doi: 10.1016/j.jand.2012.10.014.
    • Mediterranean Diet and Age-Related Cognitive Decline: A Randomized Clinical Trial. JAMA Intern Med. 2015 Jul;175(7):1094-1103. doi: 10.1001/jamainternmed.2015.1668
  • Social Activity
    • Empty-nest-related psychological distress is associated with the progression of brain white matter lesions and cognitive impairment in the elderly. Sci Rep. 2017 Mar 3;7:43816. doi: 10.1038/srep43816.
  • Weight Management
  • Traditional Chinese Medicine
    • Effectiveness of Traditional Chinese Medicine (TCM) treatments on the cognitive functioning of elderly persons with mild cognitive impairment associated with white matter lesions. Shanghai Arch Psychiatry. 2015 Oct;27(5):289-95. doi: 10.11919/j.issn.1002-0829.215109.
  • Intellectual Activity
    • Association of Daily Intellectual Activities With Lower Risk of Incident Dementia Among Older Chinese Adults, JAMA Psychiatry. 2018;75(7):697-703. doi:10.1001/jamapsychiatry.2018.0657

 

Clinical Trials Evidence of Significant Benefits from Multidomain Lifestyle Interventions

The two-year FINGER trial (NCT01041989) is the first large, long-term, multicenter RCT showing a significant effect of the multidomain lifestyle intervention against cognitive decline among older adults who had increased risk of dementia [12]. The FINGER trial enrolled 1260 older adults aged 60–77 years, recruited from previous population-based surveys. Inclusion criteria were as follows: increased risk of dementia based on the CAIDE (Cardiovascular Risk Factors, Aging and Dementia) Dementia Risk Score (≥6 points) [13]; and cognitive performance at the mean level or slightly lower than expected for age. Participants were randomized into the multidomain intervention or control group. The multidomain intervention was delivered by trained professionals through both individual sessions and group activities, and it consisted of dietary counselling, exercise, cognitive training, social activities, and monitoring and management of vascular and metabolic risk factors. The control group was offered regular health advice.

The primary outcome of the trial was a change in cognitive performance measured by a neuropsychological test battery (NTB) composite score, and secondary cognitive outcomes included domain-specific NTB scores.

Results

  • After two years, the intervention showed significant beneficial effects on the NTB composite score (25% more improvement compared to control), as well as on executive functioning (83% more improvement), processing speed (150% more improvement), and complex memory tasks (40% more improvement).
  • Furthermore, the intervention group had a lower risk of cognitive decline.
  • Follow-ups at 5 and 7 years have been recently completed to determine long-term effects (data analysis is ongoing). The multidomain intervention was safe and well accepted, with high adherence and a low drop-out rate (12%), supporting the feasibility of lifestyle interventions in older at-risk adults.
  • Other benefits: included body mass index (BMI) reduction [12], improved adherence to dietary guidelines and recommendations [14], and increase in physical activity [12] and health-related quality of life [15]. The intervention also improved lowered the risk of multimorbidity as well as the risk of developing new chronic diseases [16]. APOE ε4 carriers got clear benefits from the intervention [17].

 

References

  1. Lau A, Mok V, Lee J, Fan Y, Zeng J, Lam b, Wong A, Kwok C, Lai M, Zee B, “Retinal image analytics detects white matter hyperintensities in healthy adults”, Annals of Clinical and Translational Neurology, Volume 6, Issue 1, January 2019, Pages 98-105
  2. Inzitari D, Pracucci G, Poggesi A, et al. “Changes in white matter as determinant of global functional decline in older independent outpatients: Three years follow-up of LADIS (leukoaraiosis and disability) study cohort”. BMJ Clinical research 2009; 339: b2477
  3. Prins ND, Scheltens P, “White matter hyperintensities, cognitive impairment and dementia: an update”, Nat Rev Neurol. 2015 Mar;11(3):157-65
  4. Schmidt R, Ropele S, Enzinger C, Petrovic K, Smith S, Schmidt H, Matthews PM, Fazekas F: “White matter lesion progression, brain atrophy, and cognitive decline: The Austrian stroke prevention study”. Ann Neurol 2005;58:610-616
  5. Cho AH, Kim HR, Kim W, Yang DW “White Matter Hyperintensity in Ischemic Stroke Patients: It May Regress Over Time”, Journal of Stroke 2015; 17(1): 60-66.
  6. Ramirez J, McNeely AA, Berezuk C, Gao F, and Black SE, “Dynamic Progression of White Matter Hyperintensities in Alzheimer’s Disease and Normal Aging: Results from the Sunnybrook Dementia Study”, Frontiers in Aging Neuroscience, March 2016, Volume 8, Article 62.
  7. Brickman AM “Contemplating Alzheimer’s disease and the contribution of white matter hyperintensities”, Curr Neurol Neurosci Rep (2013) 13:415
  8. Lee S, Viqar F, Zimmerman ME, Narkhede A, et al.; Dominantly Inherited Alzheimer Network, “White matter hyperintensities are a core feature of Alzheimer’s disease: Evidence from the dominantly inherited Alzheimer network”, Ann Neurol. 2016 Jun;79(6):929-39.
  9. Araque Caballero MÁ, Suárez-Calvet M, Duering Met al., “White matter diffusion alterations precede symptom onset in autosomal dominant Alzheimer’s disease”, Brain 2018 Oct 1;141(10):3065-3080
  10. Kandel BM, Avants BB, Gee JC, McMillan CT, Erus G, Doshi J, Davatzikos C, Wolk DA, “White matter hyperintensities are more highly associated with preclinical Alzheimer’s disease than imaging and cognitive markers of neurodegeneration”, Alzheimers Dement (Amst). 2016 Apr 7;4:18-27
  11. Elahi FM, Ashimatey SB, Bennett DJ, et al. Retinal imaging demonstrates reduced capillary density in clinically unimpaired APOE ε4 gene carriers. Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring. 2021;13(1):e12181. doi:https://doi.org/10.1002/dad2.12181
  12. Ngandu T, Lehtisalo J, Solomon A, Levalahti E, Ahtiluoto S, Antikainen R, et al. A 2 year multidomain intervention of diet, exercise, cognitive training, and vascular risk monitoring versus control to prevent cognitive decline in at-risk elderly people (FINGER): a randomised controlled trial. Lancet 2015;385:2255–2263.
  13. Kivipelto M, Ngandu T, Laatikainen T, Winblad B, Soininen H, Tuomilehto J. Risk score for the prediction of dementia risk in 20 years among middle aged people: a longitudinal, population-based study. Lancet Neurol 2006;5:735–741.
  14. Lehtisalo J, Ngandu T, Valve P, Antikainen R, Laatikainen T, Strandberg T, et al. Nutrient intake and dietary changes during a 2-year multi-domain lifestyle intervention among older adults: secondary analysis of the Finnish Geriatric Intervention Study to Prevent Cognitive Impairment and Disability (FINGER) randomised controlled trial. Br J Nutr 2017;118:291–302.
  15. Strandberg T, Levalahti E, Ngandu T, Solomon A, Kivipelto M, Lehtisalo J, et al. Health-related quality of life in a multidomain intervention trial to prevent cognitive decline (FINGER). European Geriatric Medicine 2017;8:164–167.
  16. Marengoni A, Rizzuto D, Fratiglioni L, Antikainen R, Laatikainen T, Lehtisalo J, et al. The Effect of a 2-Year Intervention Consisting of Diet, Physical Exercise, Cognitive Training, and Monitoring of Vascular Risk on Chronic Morbidity-the FINGER Randomized Controlled Trial. J Am Med Dir Assoc 2018;19:360.e1.
  17. Solomon A, Turunen H, Ngandu T, Peltonen M, Levalahti E, Helisalmi S, et al. Effect of the Apolipoprotein E Genotype on Cognitive Change During a Multidomain Lifestyle Intervention: A Subgroup Analysis of a Randomized Clinical Trial. JAMA Neurol 2018;75:462–470.

 

Reports by Media on ARIA Technology Advancement

WP_20161213_23_12_54_Pro_LI

 

 Hong Kong Awards for Industries – Technological Achievement Award 2016

Presentation1

 

Theory into reality: Hong Kong researchers devise five-minute optical test for stroke risk
Press – SCMP on 6 May 2016

SCMP picture 1

 
Press – 明報 – 6 May 2016

MingPao picture 1

 

 Ming Pao 2016-05-07@ARIA

 
 

  Press – 明報 – 25 Sept 2015 

Health View Bioanalytic ARIA Ming Pao 2015-09-25 Cleaned

 

 

5th Bank of China “Technology Start-up ” Merit Award『香港創新科技及製造業聯合總會』(FITMI) 第五屆中銀香港『初創科技』潛能大獎 2015 - 『優異獎』

FITMI Award 2015 - certificate

 

DSC06002

 

 

CUHK Newsletter – Jan 2013

ARIA - A glimpse of our body

ARIA - Image for AMD123ARIA - Retinal Images of Dry and Wet AMD