Estimating Uncertainty of Geographic Atrophy Segmentations with Bayesian Deep Learning

Theodore Spaide, PhD; Anand E. Rajesh, MD; Nayoon Gim; Marian Blazes, MD; Cecilia S. Lee, MD, MS; Niranchana Macivannan, PhD; Gary Lee, PhD, MEng; Warren Lewis, MS; Ali Salehi, PhD; Luis de Sisternes, PhD; Gissel Herrera, MD; Mengxi Shen, MD, PhD; Giovanni Gregori, PhD; Philip J. Rosenfeld, MD, PhD; Varsha Pramil, MD, MS; Nadia Waheed, MD, MPH; Yue Wu, PhD; Qinqin Zhang, PhD; Aaron Y. Lee, MD, MSCI

Ophthalmology Science (Jan 2025)

Estimating Uncertainty of Geographic Atrophy Segmentations with Bayesian Deep Learning

Theodore Spaide, PhD,
Anand E. Rajesh, MD,
Nayoon Gim,
Marian Blazes, MD,
Cecilia S. Lee, MD, MS,
Niranchana Macivannan, PhD,
Gary Lee, PhD, MEng,
Warren Lewis, MS,
Ali Salehi, PhD,
Luis de Sisternes, PhD,
Gissel Herrera, MD,
Mengxi Shen, MD, PhD,
Giovanni Gregori, PhD,
Philip J. Rosenfeld, MD, PhD,
Varsha Pramil, MD, MS,
Nadia Waheed, MD, MPH,
Yue Wu, PhD,
Qinqin Zhang, PhD,
Aaron Y. Lee, MD, MSCI

Affiliations

Theodore Spaide, PhD: Department of Ophthalmology, University of Washington, Seattle, Washington; The Roger and Angie Karalis Retina Center, Seattle, Washington; Topcon Healthcare, Oakland, New Jersey
Anand E. Rajesh, MD: Department of Ophthalmology, University of Washington, Seattle, Washington; The Roger and Angie Karalis Retina Center, Seattle, Washington
Nayoon Gim: Department of Ophthalmology, University of Washington, Seattle, Washington; The Roger and Angie Karalis Retina Center, Seattle, Washington; Department of Bioengineering, University of Washington, Seattle, Washington
Marian Blazes, MD: Department of Ophthalmology, University of Washington, Seattle, Washington; The Roger and Angie Karalis Retina Center, Seattle, Washington
Cecilia S. Lee, MD, MS: Department of Ophthalmology, University of Washington, Seattle, Washington; The Roger and Angie Karalis Retina Center, Seattle, Washington
Niranchana Macivannan, PhD: Carl Zeiss Meditec, Inc., Dublin, California
Gary Lee, PhD, MEng: Carl Zeiss Meditec, Inc., Dublin, California
Warren Lewis, MS: Carl Zeiss Meditec, Inc., Dublin, California
Ali Salehi, PhD: Carl Zeiss Meditec, Inc., Dublin, California
Luis de Sisternes, PhD: Twenty Twenty Therapeutics, LLC, San Francisco, California
Gissel Herrera, MD: Department of Ophthalmology, Bascom Palmer Eye Institute (BPEI), University of Miami Miller School of Medicine, Miami, Florida
Mengxi Shen, MD, PhD: Department of Ophthalmology, Bascom Palmer Eye Institute (BPEI), University of Miami Miller School of Medicine, Miami, Florida
Giovanni Gregori, PhD: Department of Ophthalmology, Bascom Palmer Eye Institute (BPEI), University of Miami Miller School of Medicine, Miami, Florida
Philip J. Rosenfeld, MD, PhD: Department of Ophthalmology, Bascom Palmer Eye Institute (BPEI), University of Miami Miller School of Medicine, Miami, Florida
Varsha Pramil, MD, MS: Tufts University School of Medicine, Boston, Massachusetts; New England Eye Center, Tufts New England Medical Center, Boston, Massachusetts
Nadia Waheed, MD, MPH: Tufts University School of Medicine, Boston, Massachusetts; New England Eye Center, Tufts New England Medical Center, Boston, Massachusetts
Yue Wu, PhD: Department of Ophthalmology, University of Washington, Seattle, Washington; The Roger and Angie Karalis Retina Center, Seattle, Washington
Qinqin Zhang, PhD: Carl Zeiss Meditec, Inc., Dublin, California
Aaron Y. Lee, MD, MSCI: Department of Ophthalmology, University of Washington, Seattle, Washington; The Roger and Angie Karalis Retina Center, Seattle, Washington; Correspondence: Aaron Y. Lee, MD, MSCI, Associate Professor, C. Dan and Irene Hunter Endowed Professorship, Department of Ophthalmology, University of Washington, 325 Ninth Avenue, Box 359608, Seattle, WA 98104.

Journal volume & issue: Vol. 5, no. 1
p. 100587

Abstract

Read online

Purpose: To apply methods for quantifying uncertainty of deep learning segmentation of geographic atrophy (GA). Design: Retrospective analysis of OCT images and model comparison. Participants: One hundred twenty-six eyes from 87 participants with GA in the SWAGGER cohort of the Nonexudative Age-Related Macular Degeneration Imaged with Swept-Source OCT (SS-OCT) study. Methods: The manual segmentations of GA lesions were conducted on structural subretinal pigment epithelium en face images from the SS-OCT images. Models were developed for 2 approximate Bayesian deep learning techniques, Monte Carlo dropout and ensemble, to assess the uncertainty of GA semantic segmentation and compared to a traditional deep learning model. Main Outcome Measures: Model performance (Dice score) was compared. Uncertainty was calculated using the formula for Shannon Entropy. Results: The output of both Bayesian technique models showed a greater number of pixels with high entropy than the standard model. Dice scores for the Monte Carlo dropout method (0.90, 95% confidence interval 0.87–0.93) and the ensemble method (0.88, 95% confidence interval 0.85–0.91) were significantly higher (P < 0.001) than for the traditional model (0.82, 95% confidence interval 0.78–0.86). Conclusions: Quantifying the uncertainty in a prediction of GA may improve trustworthiness of the models and aid clinicians in decision-making. The Bayesian deep learning techniques generated pixel-wise estimates of model uncertainty for segmentation, while also improving model performance compared with traditionally trained deep learning models. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Published in Ophthalmology Science

ISSN: 2666-9145 (Online)
Publisher: Elsevier
Country of publisher: United States
LCC subjects: Medicine: Ophthalmology
Website: https://www.journals.elsevier.com/ophthalmology-science/

About the journal

Abstract

Keywords