Development and Validation of a Novel Prognostic Model for Predicting AMD Progression Using Longitudinal Fundus Images

TL;DR

This paper introduces a novel deep learning approach that predicts AMD progression from longitudinal fundus images without prior feature extraction, outperforming previous models in accuracy and interpretability.

Contribution

The study presents a new deep learning model combining InceptionV3 and RNN with interval scaling to predict disease progression from uneven longitudinal imaging data, eliminating the need for prior feature extraction.

Findings

Achieved high sensitivity (0.878) and specificity (0.887) in predicting AMD progression.

Area under ROC was 0.950, indicating excellent predictive performance.

Model outperformed previous prognostic methods for AMD progression.

Abstract

Prognostic models aim to predict the future course of a disease or condition and are a vital component of personalized medicine. Statistical models make use of longitudinal data to capture the temporal aspect of disease progression; however, these models require prior feature extraction. Deep learning avoids explicit feature extraction, meaning we can develop models for images where features are either unknown or impossible to quantify accurately. Previous prognostic models using deep learning with imaging data require annotation during training or only utilize a single time point. We propose a novel deep learning method to predict the progression of diseases using longitudinal imaging data with uneven time intervals, which requires no prior feature extraction. Given previous images from a patient, our method aims to predict whether the patient will progress onto the next stage of the disease. The proposed method uses InceptionV3 to produce feature vectors for each image. In order to account for uneven intervals, a novel interval scaling is proposed. Finally, a Recurrent Neural Network is used to prognosticate the disease. We demonstrate our method on a longitudinal dataset of color fundus images from 4903 eyes with age-related macular degeneration (AMD), taken from the Age-Related Eye Disease Study, to predict progression to late AMD. Our method attains a testing sensitivity of 0.878, a specificity of 0.887, and an area under the receiver operating characteristic of 0.950. We compare our method to previous methods, displaying superior performance in our model. Class activation maps display how the network reaches the final decision.