# AI-Based Retinal Image Analysis for the Detection of Choroidal Neovascular Age-Related Macular Degeneration (AMD) and Its Association with Brain Health

## TL;DR

This study uses AI to detect advanced AMD in retinal images and finds a link between AMD and brain health risks like white matter hyperintensities and depression.

## Contribution

The novel contribution is an AI method for detecting AMD and neovascular AMD, along with CNV segmentation, and demonstrating its association with brain health risks.

## Key findings

- The AI model achieved high accuracy in detecting referable AMD and neovascular AMD with strong performance metrics.
- Segmentation of choroidal neovascularisation showed good global and mean accuracy metrics.
- AMD and neovascular AMD were significantly associated with increased risks of white matter hyperintensities and depression.

## Abstract

Purpose: This study aims to develop a method for detecting referable (intermediate and advanced) age-related macular degeneration (AMD) and neovascular AMD, as well as providing an automatic segmentation of choroidal neovascularisation (CNV) on colour fundus retinal images. We also demonstrated that brain health risk scores estimated by AI-based Retinal Image Analysis (ARIA), such as white matter hyperintensities and depression, are significantly associated with AMD and neovascular AMD. Methods: A primary dataset of 1480 retinal images was collected from Zhongshan Hospital of Fudan University for training and 10-fold cross-validation. Additionally, two validation subdataset comprising 238 images (retinal images and wide-field images) were used. Using fluorescein angiography-based labels, we applied the InceptionResNetV2 deep network with the ARIA method to detect AMD, and a transfer ResNet50_Unet was used to segment CNV. The risks of cerebral white matter hyperintensities and depression were estimated using an AI-based Retinal Image Analysis approach. Results: In a 10-fold cross-validation, we achieved sensitivities of 97.4% and 98.1%, specificities of 96.8% and 96.1%, and accuracies of 97.0% and 96.4% in detecting referable AMD and neovascular AMD, respectively. In the external validation, we achieved accuracies of 92.9% and 93.7% and AUCs of 0.967 and 0.967, respectively. The performances on two validation sub-datasets show no statistically significant difference in detecting referable AMD (p = 0.704) and neovascular AMD (p = 0.213). In the segmentation of CNV, we achieved a global accuracy of 93.03%, a mean accuracy of 91.83%, a mean intersection over union (IoU) of 68.7%, a weighted IoU of 89.63%, and a mean boundary F1 (BF) of 67.77%. Conclusions: The proposed method shows promising results as a highly efficient and cost-effective screening tool for detecting neovascular and referable AMD on both retinal and wide-field images, and providing critical insights into CNV. Its implementation could be particularly valuable in resource-limited settings, enabling timely referrals, enhancing patient care, and supporting decision-making across AMD classifications. In addition, we demonstrated that AMD and neovascular AMD are significantly associated with increased risks of WMH and depression.