Predicting geographic atrophy growth rate from fundus autofluorescence images using deep neural networks

Neha Anegondi; Qi Yang; Michael Kawczynski; Verena Steffen; Simon S. Gao

doi:10.1117/12.2575898

5 March 2021 Predicting geographic atrophy growth rate from fundus autofluorescence images using deep neural networks

Neha Anegondi, Qi Yang, Michael Kawczynski, Verena Steffen, Simon S. Gao

Proceedings Volume 11634, Multimodal Biomedical Imaging XVI; 116340E (2021) https://doi.org/10.1117/12.2575898
Event: SPIE BiOS, 2021, Online Only

Abstract

Geographic atrophy (GA) is late-stage dry age-related macular degeneration (AMD). Improved predictors of GA progression would be useful in clinical trial design and may be relevant for clinical practice. The purpose of this study was to accurately predict GA progression over time from baseline fundus autofluorescence (FAF) images (Heidelberg Engineering, Inc., Germany) using deep learning. Study eyes of patients (n = 1312) enrolled in the Lampalizumab trials^{1, 2} (NCT02479386, NCT02247479, NCT02247531) were included. The dataset was split by patient into training (n = 1047) and holdout sets (n = 265). GA progression, defined as GA lesion growth rate, was derived by a linear fit on all available measurements of GA lesion area (mm2 , measured from manually graded FAF images). The model performance was evaluated using 5-fold cross-validation (CV). Coefficient of determination (R2 ) computed as the square of Pearson correlation coefficient was used as the performance metric. Multiple modeling approaches were implemented, and the best performance was observed using cascade learning. In this approach, pre-trained weights on ImageNet were finetuned to predict GA lesion area followed by further fine-tuning to predict GA growth rate. The 5-folds had an average CV R² of 0.44, and the holdout showed R² of 0.50 (95% confidence interval: 0.41 - 0.61). In comparison, a linear model using only baseline GA lesion area in the same holdout showed an R² of 0.18. Further investigation with visualization techniques might help understand the pathophysiology behind the predictions. The predictions may be improved by combining with imaging modalities like near-infrared and/or optical coherence tomography.

Conference Presentation

Citation Download Citation

Neha Anegondi, Qi Yang, Michael Kawczynski, Verena Steffen, and Simon S. Gao "Predicting geographic atrophy growth rate from fundus autofluorescence images using deep neural networks", Proc. SPIE 11634, Multimodal Biomedical Imaging XVI, 116340E (5 March 2021); https://doi.org/10.1117/12.2575898

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available