Efficient Deep Learning Algorithm for Alzheimer's Disease Diagnosis using Retinal Images

Kim, Do Young; Lim, Young Jun; Park, Joon Hyeon; Sunwoo, Myung Hoon

doi:10.1109/aicas54282.2022.9869953

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tian et al 10 developed a multi-stage machine learning pipeline using vessel maps extracted from CFP images and reported an AD classification result with an AUC of 0.87. Kim et al 11 designed an end-to-end, attention-based convolutional neural network (CNN) model for CFP-based AD classification. Most recently, Cheung et al 6 trained a deep learning algorithm on CFP datasets from multi-centers for AD detection, obtaining an AUC of 0.93.…”

Section: Introductionmentioning

confidence: 99%

Eye-AD: A Graph-based Model for Early-onset Alzheimer’s Disease and Mild Cognitive Impairment Detection based on Retinal OCTA Images

Zhao,

Hao,

Kwapong

et al. 2023

Preprint

View full text Add to dashboard Cite

Alzheimer's disease (AD) is a rising healthcare challenge worldwide. There is currently no simple and affordable test to accurately detect AD at scale. In this work we propose a novel deep learning framework (Eye-AD) to detect Early-onset Alzheimer's Disease (EOAD) and Mild Cognitive Impairment (MCI), using retinal microvasculature and choriocapillaris acquired from optical coherence tomography angiography (OCTA). The proposed Eye-AD model is a multilevel graph representation approach, which utilizes the intra- and inter-instance relationships of different retinal layers. We used a total of 5,751 OCTA images obtained from 1,671 participants of a retrospective, multi-centre study to train, validate and test the Eye-AD model. The experimental results demonstrate the superior performance of our model in both EOAD detection (internal data: AUC = 0.9355, external data: AUC = 0.9007) and MCI detection (internal data: AUC =0.8630, external data: AUC = 0.8037). Furthermore, we explored the associations between retinal structural biomarkers in OCTA images and EOAD/MCI, and the results align well with the conclusions drawn from our deep learning interpretability analysis. Our findings provide further evidence that retinal OCTA imaging, coupled with artificial intelligence, will serve as a rapid, non-invasive and affordable approach for AD-related diseases detection and risk assessment.

show abstract

Section: Introductionmentioning

confidence: 99%

Eye-AD: A Graph-based Model for Early-onset Alzheimer’s Disease and Mild Cognitive Impairment Detection based on Retinal OCTA Images

Zhao,

Hao,

Kwapong

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Early detection of dementia through retinal imaging and trustworthy AI

Hao,

Kwapong,

Shen

et al. 2024

npj Digit. Med.

View full text Add to dashboard Cite

Alzheimer’s disease (AD) is a global healthcare challenge lacking a simple and affordable detection method. We propose a novel deep learning framework, Eye-AD, to detect Early-onset Alzheimer’s Disease (EOAD) and Mild Cognitive Impairment (MCI) using OCTA images of retinal microvasculature and choriocapillaris. Eye-AD employs a multilevel graph representation to analyze intra- and inter-instance relationships in retinal layers. Using 5751 OCTA images from 1671 participants in a multi-center study, our model demonstrated superior performance in EOAD (internal data: AUC = 0.9355, external data: AUC = 0.9007) and MCI detection (internal data: AUC = 0.8630, external data: AUC = 0.8037). Furthermore, we explored the associations between retinal structural biomarkers in OCTA images and EOAD/MCI, and the results align well with the conclusions drawn from our deep learning interpretability analysis. Our findings provide further evidence that retinal OCTA imaging, coupled with artificial intelligence, will serve as a rapid, noninvasive, and affordable dementia detection.

show abstract

Efficient Deep Learning Algorithm for Alzheimer's Disease Diagnosis using Retinal Images

Cited by 2 publications

References 10 publications

Eye-AD: A Graph-based Model for Early-onset Alzheimer’s Disease and Mild Cognitive Impairment Detection based on Retinal OCTA Images

Eye-AD: A Graph-based Model for Early-onset Alzheimer’s Disease and Mild Cognitive Impairment Detection based on Retinal OCTA Images

Early detection of dementia through retinal imaging and trustworthy AI

Contact Info

Product

Resources

About