Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models

Abstract

While color fundus photos are used in routine clinical practice to diagnose ophthalmic conditions, evidence suggests that ocular imaging contains valuable information regarding the systemic health features of patients. These features can be identified through computer vision techniques including deep learning (DL) artificial intelligence (AI) models. We aim to construct a DL model that can predict systemic features from fundus images and to determine the optimal method of model construction for this task. Data were collected from a cohort of patients undergoing diabetic retinopathy screening between March 2020 and March 2021. Two models were created for each of 12 systemic health features based on the DenseNet201 architecture: one utilizing transfer learning with images from ImageNet and another from 35,126 fundus images. Here, 1277 fundus images were used to train the AI models. Area under the receiver operating characteristics curve (AUROC) scores were used to compare the model performance. Models utilizing the ImageNet transfer learning data were superior to those using retinal images for transfer learning (mean AUROC 0.78 vs. 0.65, p-value < 0.001). Models using ImageNet pretraining were able to predict systemic features including ethnicity (AUROC 0.93), age > 70 (AUROC 0.90), gender (AUROC 0.85), ACE inhibitor (AUROC 0.82), and ARB medication use (AUROC 0.78). We conclude that fundus images contain valuable information about the systemic characteristics of a patient. To optimize DL model performance, we recommend that even domain specific models consider using transfer learning from more generalized image sets to improve accuracy.

Oculomics: A Crusade Against the Four Horsemen of Chronic Disease

“…Metrics based on automated detection and segmentation of vessels, such as arteriolar and venular tortuosity, fractal dimension (a measure of vascular branching complexity and density) [ 25 , 38 – 40 ] (Yu et al’s data originates from a pre-print) and bifurcation (branching metrics) [ 41 ] can be used to predict ischemic heart disease (narrowed heart arteries) [ 42 ], hypertension [ 27 , 28 , 35 ], stroke [ 42 ] (Ma et al’s data originates from a pre-print), and peripheral vascular disease (poor blood circulation throughout the body) [ 41 ]. In addition, the optic disc rim, cup-to-disc ratio, peripapillary atrophy, and fovea were related to cardiovascular disease [ 31 , 32 ].…”

A Systematic Review and Meta-Analysis of Applying Deep Learning in the Prediction of the Risk of Cardiovascular Diseases From Retinal Images

“… 26 , 31 , 32 , 34 , 42 For gender prediction, the AUROC of the DL algorithms was between 0.704 and 0.978 among all relevant studies. 26 , 28 , 31 , 32 , 40 , 44 Among the studies that investigated the prediction of smoking status, the models achieved an AUROC that ranged from 0.71 to 0.86. 26 , 28 , 30 , 32 , 44 The DL models had an MAE between 0.61% and 1.39% for the prediction of HbA1c value 26 , 32 and an MAE between 0.652 and 1.06 mmol/l for the prediction of blood glucose level.…”

Futuristic Variations and Analysis in Fundus Images Corresponding to Biological Traits

“…The first block receives input fundus images with dimensions of 512×512×3 (width×hight×channel). The input three channels fundus image first pass through a stack of convolution neural network with given number of filters (32) and kernel size (3). The SAB block has been augmented to focus on the salient spatial regions.…”

“…The estimation of age and gender classification may not be clinically inevitable, but the study of age progression based on biological traits learning hints the potential application of DL in discovering novel associations between traits and fundus images. The DL models implementation uncovers additional features from fundus images results in better biological traits association [32].…”