Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modeling

TL;DR

This paper introduces LTSA, a Transformer-based model that leverages longitudinal medical imaging data to improve prognosis of progressive eye diseases like AMD and POAG, outperforming traditional single-image methods.

Contribution

The study presents a novel deep learning framework that models disease progression over time using irregularly spaced longitudinal images, enhancing prognosis accuracy in ophthalmology.

Findings

LTSA outperformed baseline in 19/20 AMD prognosis comparisons

LTSA outperformed baseline in 18/20 POAG prognosis comparisons

Temporal attention analysis shows recent images are most influential, but prior images add value.

Abstract

Deep learning has enabled breakthroughs in automated diagnosis from medical imaging, with many successful applications in ophthalmology. However, standard medical image classification approaches only assess disease presence at the time of acquisition, neglecting the common clinical setting of longitudinal imaging. For slow, progressive eye diseases like age-related macular degeneration (AMD) and primary open-angle glaucoma (POAG), patients undergo repeated imaging over time to track disease progression and forecasting the future risk of developing disease is critical to properly plan treatment. Our proposed Longitudinal Transformer for Survival Analysis (LTSA) enables dynamic disease prognosis from longitudinal medical imaging, modeling the time to disease from sequences of fundus photography images captured over long, irregular time periods. Using longitudinal imaging data from the Age-Related Eye Disease Study (AREDS) and Ocular Hypertension Treatment Study (OHTS), LTSA significantly outperformed a single-image baseline in 19/20 head-to-head comparisons on late AMD prognosis and 18/20 comparisons on POAG prognosis. A temporal attention analysis also suggested that, while the most recent image is typically the most influential, prior imaging still provides additional prognostic value.