Automatic detection and prediction of nAMD activity change in retinal OCT using Siamese networks and Wasserstein Distance for ordinality
This work addresses the need for timely treatment management in nAMD, a leading cause of vision loss in older adults, by providing automated tools for severity change detection and prediction, though it is incremental as it builds on existing deep learning methods for medical imaging.
The paper tackled the problem of detecting and predicting changes in neovascular age-related macular degeneration (nAMD) severity from longitudinal retinal OCT scans, using a Vision Transformer-based Siamese network for detection and a Wasserstein Distance-based loss for forecasting, with both models ranking high on a public challenge leaderboard.
Neovascular age-related macular degeneration (nAMD) is a leading cause of vision loss among older adults, where disease activity detection and progression prediction are critical for nAMD management in terms of timely drug administration and improving patient outcomes. Recent advancements in deep learning offer a promising solution for predicting changes in AMD from optical coherence tomography (OCT) retinal volumes. In this work, we proposed deep learning models for the two tasks of the public MARIO Challenge at MICCAI 2024, designed to detect and forecast changes in nAMD severity with longitudinal retinal OCT. For the first task, we employ a Vision Transformer (ViT) based Siamese Network to detect changes in AMD severity by comparing scan embeddings of a patient from different time points. To train a model to forecast the change after 3 months, we exploit, for the first time, an Earth Mover (Wasserstein) Distance-based loss to harness the ordinal relation within the severity change classes. Both models ranked high on the preliminary leaderboard, demonstrating that their predictive capabilities could facilitate nAMD treatment management.