oculomix: Hierarchical Sampling for Retinal-Based Systemic Disease Prediction

TL;DR

Oculomix introduces a hierarchical sampling strategy for data augmentation in retinal imaging, improving systemic disease prediction by preserving patient-specific attributes and leveraging clinical priors.

Contribution

The paper proposes a novel hierarchical sampling method, Oculomix, that enhances transformer training for systemic disease prediction from retinal images by incorporating clinical priors.

Findings

Oculomix outperforms traditional augmentation methods by up to 3% in AUROC.

The method effectively preserves patient-specific attributes during augmentation.

Validation on a large diverse dataset demonstrates its practical utility.

Abstract

Oculomics - the concept of predicting systemic diseases, such as cardiovascular disease and dementia, through retinal imaging - has advanced rapidly due to the data efficiency of transformer-based foundation models like RETFound. Image-level mixed sample data augmentations, such as CutMix and MixUp, are frequently used for training transformers, yet these techniques perturb patient-specific attributes, such as medical comorbidity and clinical factors, since they only account for images and labels. To address this limitation, we propose a hierarchical sampling strategy, Oculomix, for mixed sample augmentations. Our method is based on two clinical priors. First (exam level), images acquired from the same patient at the same time point share the same attributes. Second (patient level), images acquired from the same patient at different time points have a soft temporal trend, as morbidity generally increases over time. Guided by these priors, our method constrains the mixing space to the patient and exam levels to better preserve patient-specific characteristics and leverages their hierarchical relationships. The proposed method is validated using ViT models on a five-year prediction of major adverse cardiovascular events (MACE) in a large ethnically diverse population (Alzeye). We show that Oculomix consistently outperforms image-level CutMix and MixUp by up to 3% in AUROC, demonstrating the necessity and value of the proposed method in oculomics.