Deep Learning to Predict the Future Growth of Geographic Atrophy from Fundus Autofluorescence

Purpose: The region of growth (ROG) of geographic atrophy (GA) throughout the macular area has an impact on visual outcomes. Here, we developed multiple deep learning models to predict the 1-year ROG of GA lesions using fundus autofluorescence (FAF) images. Design: In this retrospective analysis, 3...

Full description

Saved in:
Bibliographic Details
Main Authors: Anish Salvi, MS, Julia Cluceru, PhD, Simon S. Gao, PhD, Christina Rabe, PhD, Courtney Schiffman, PhD, Qi Yang, PhD, Aaron Y. Lee, MD, MSCI, Pearse A. Keane, MD, FRCOphth, Srinivas R. Sadda, MD, Frank G. Holz, MD, Daniela Ferrara, MD, PhD, Neha Anegondi, MTech
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Ophthalmology Science
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666914524001714
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850108522220486656
author Anish Salvi, MS
Julia Cluceru, PhD
Simon S. Gao, PhD
Christina Rabe, PhD
Courtney Schiffman, PhD
Qi Yang, PhD
Aaron Y. Lee, MD, MSCI
Pearse A. Keane, MD, FRCOphth
Srinivas R. Sadda, MD
Frank G. Holz, MD
Daniela Ferrara, MD, PhD
Neha Anegondi, MTech
author_facet Anish Salvi, MS
Julia Cluceru, PhD
Simon S. Gao, PhD
Christina Rabe, PhD
Courtney Schiffman, PhD
Qi Yang, PhD
Aaron Y. Lee, MD, MSCI
Pearse A. Keane, MD, FRCOphth
Srinivas R. Sadda, MD
Frank G. Holz, MD
Daniela Ferrara, MD, PhD
Neha Anegondi, MTech
author_sort Anish Salvi, MS
collection DOAJ
description Purpose: The region of growth (ROG) of geographic atrophy (GA) throughout the macular area has an impact on visual outcomes. Here, we developed multiple deep learning models to predict the 1-year ROG of GA lesions using fundus autofluorescence (FAF) images. Design: In this retrospective analysis, 3 types of models were developed using FAF images collected 6 months after baseline to predict the GA lesion area (segmented lesion mask) at 1.5 years, FAF images collected at baseline and 6 months to predict the GA lesion at 1.5 years, and FAF images collected 6 months after baseline to predict the GA lesion at 1 and 1.5 years. The 1-year ROG from the 6-month visit was derived by taking the difference between the GA lesion area (segmented lesion mask) at the 1.5-year and 6-month visits. Participants: Patients enrolled in the following lampalizumab clinical trials and prospective observational studies: NCT02247479, NCT02247531, NCT02479386, and NCT02399072. Methods: Datasets of study eyes from 597 patients were split into model training (310), validation (78), and test sets (209), stratified by baseline or initial lesion area, lesion growth rate, foveal involvement, and focality. Deep learning experiments were performed using the 2-dimensional U-Net; whole-lesion and multiclass models were developed. Main Outcome Measures: The performance of the models was evaluated by calculating the Dice score, coefficient of determination (R2), and the squared Pearson correlation coefficient (r2) between the true and derived GA lesion 1-year ROG. Results: The model using baseline and 6-month FAF images to predict GA lesion enlargement at 1.5 years had the best performance for the derived 1-year ROG. Mean Dice scores were 0.73, 0.68, and 0.70 in the training, validation, and test sets, respectively. The R2 (0.77, 0.53, and 0.79) and r2 (0.83, 0.61, and 0.79) showed similar trends across the 3 sets. Conclusions: These findings show the potential of using baseline and/or 6-month visit FAF images to predict 1-year GA ROG using a deep learning approach. This work could potentially help support decision-making in clinical trials and more informed treatment decisions in clinical practice. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
format Article
id doaj-art-073278975fa14f85a96add2f9ca2a345
institution OA Journals
issn 2666-9145
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Ophthalmology Science
spelling doaj-art-073278975fa14f85a96add2f9ca2a3452025-08-20T02:38:21ZengElsevierOphthalmology Science2666-91452025-03-015210063510.1016/j.xops.2024.100635Deep Learning to Predict the Future Growth of Geographic Atrophy from Fundus AutofluorescenceAnish Salvi, MS0Julia Cluceru, PhD1Simon S. Gao, PhD2Christina Rabe, PhD3Courtney Schiffman, PhD4Qi Yang, PhD5Aaron Y. Lee, MD, MSCI6Pearse A. Keane, MD, FRCOphth7Srinivas R. Sadda, MD8Frank G. Holz, MD9Daniela Ferrara, MD, PhD10Neha Anegondi, MTech11Genentech, Inc., South San Francisco, CaliforniaGenentech, Inc., South San Francisco, CaliforniaGenentech, Inc., South San Francisco, CaliforniaGenentech, Inc., South San Francisco, CaliforniaGenentech, Inc., South San Francisco, CaliforniaGenentech, Inc., South San Francisco, CaliforniaDepartment of Ophthalmology, University of Washington, Seattle, WashingtonNational Institute for Health Research, Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS Foundation Trust, UCL Institute of Ophthalmology, London, UKDoheny Image Reading Center, Doheny Eye Institute, Los Angeles, CaliforniaDepartment of Ophthalmology, University of Bonn, Bonn, GermanyGenentech, Inc., South San Francisco, CaliforniaGenentech, Inc., South San Francisco, California; Correspondence: Neha Anegondi, MTech, Genentech, Inc., 1 DNA Way, MS-44 #3B, South San Francisco, CA 94080.Purpose: The region of growth (ROG) of geographic atrophy (GA) throughout the macular area has an impact on visual outcomes. Here, we developed multiple deep learning models to predict the 1-year ROG of GA lesions using fundus autofluorescence (FAF) images. Design: In this retrospective analysis, 3 types of models were developed using FAF images collected 6 months after baseline to predict the GA lesion area (segmented lesion mask) at 1.5 years, FAF images collected at baseline and 6 months to predict the GA lesion at 1.5 years, and FAF images collected 6 months after baseline to predict the GA lesion at 1 and 1.5 years. The 1-year ROG from the 6-month visit was derived by taking the difference between the GA lesion area (segmented lesion mask) at the 1.5-year and 6-month visits. Participants: Patients enrolled in the following lampalizumab clinical trials and prospective observational studies: NCT02247479, NCT02247531, NCT02479386, and NCT02399072. Methods: Datasets of study eyes from 597 patients were split into model training (310), validation (78), and test sets (209), stratified by baseline or initial lesion area, lesion growth rate, foveal involvement, and focality. Deep learning experiments were performed using the 2-dimensional U-Net; whole-lesion and multiclass models were developed. Main Outcome Measures: The performance of the models was evaluated by calculating the Dice score, coefficient of determination (R2), and the squared Pearson correlation coefficient (r2) between the true and derived GA lesion 1-year ROG. Results: The model using baseline and 6-month FAF images to predict GA lesion enlargement at 1.5 years had the best performance for the derived 1-year ROG. Mean Dice scores were 0.73, 0.68, and 0.70 in the training, validation, and test sets, respectively. The R2 (0.77, 0.53, and 0.79) and r2 (0.83, 0.61, and 0.79) showed similar trends across the 3 sets. Conclusions: These findings show the potential of using baseline and/or 6-month visit FAF images to predict 1-year GA ROG using a deep learning approach. This work could potentially help support decision-making in clinical trials and more informed treatment decisions in clinical practice. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.http://www.sciencedirect.com/science/article/pii/S2666914524001714Age-related macular degenerationArtificial intelligenceDeep learningFundus autofluorescence imagingGeographic atrophy
spellingShingle Anish Salvi, MS
Julia Cluceru, PhD
Simon S. Gao, PhD
Christina Rabe, PhD
Courtney Schiffman, PhD
Qi Yang, PhD
Aaron Y. Lee, MD, MSCI
Pearse A. Keane, MD, FRCOphth
Srinivas R. Sadda, MD
Frank G. Holz, MD
Daniela Ferrara, MD, PhD
Neha Anegondi, MTech
Deep Learning to Predict the Future Growth of Geographic Atrophy from Fundus Autofluorescence
Ophthalmology Science
Age-related macular degeneration
Artificial intelligence
Deep learning
Fundus autofluorescence imaging
Geographic atrophy
title Deep Learning to Predict the Future Growth of Geographic Atrophy from Fundus Autofluorescence
title_full Deep Learning to Predict the Future Growth of Geographic Atrophy from Fundus Autofluorescence
title_fullStr Deep Learning to Predict the Future Growth of Geographic Atrophy from Fundus Autofluorescence
title_full_unstemmed Deep Learning to Predict the Future Growth of Geographic Atrophy from Fundus Autofluorescence
title_short Deep Learning to Predict the Future Growth of Geographic Atrophy from Fundus Autofluorescence
title_sort deep learning to predict the future growth of geographic atrophy from fundus autofluorescence
topic Age-related macular degeneration
Artificial intelligence
Deep learning
Fundus autofluorescence imaging
Geographic atrophy
url http://www.sciencedirect.com/science/article/pii/S2666914524001714
work_keys_str_mv AT anishsalvims deeplearningtopredictthefuturegrowthofgeographicatrophyfromfundusautofluorescence
AT juliacluceruphd deeplearningtopredictthefuturegrowthofgeographicatrophyfromfundusautofluorescence
AT simonsgaophd deeplearningtopredictthefuturegrowthofgeographicatrophyfromfundusautofluorescence
AT christinarabephd deeplearningtopredictthefuturegrowthofgeographicatrophyfromfundusautofluorescence
AT courtneyschiffmanphd deeplearningtopredictthefuturegrowthofgeographicatrophyfromfundusautofluorescence
AT qiyangphd deeplearningtopredictthefuturegrowthofgeographicatrophyfromfundusautofluorescence
AT aaronyleemdmsci deeplearningtopredictthefuturegrowthofgeographicatrophyfromfundusautofluorescence
AT pearseakeanemdfrcophth deeplearningtopredictthefuturegrowthofgeographicatrophyfromfundusautofluorescence
AT srinivasrsaddamd deeplearningtopredictthefuturegrowthofgeographicatrophyfromfundusautofluorescence
AT frankgholzmd deeplearningtopredictthefuturegrowthofgeographicatrophyfromfundusautofluorescence
AT danielaferraramdphd deeplearningtopredictthefuturegrowthofgeographicatrophyfromfundusautofluorescence
AT nehaanegondimtech deeplearningtopredictthefuturegrowthofgeographicatrophyfromfundusautofluorescence