Detection of Nonexudative Macular Neovascularization on Structural OCT Images Using Vision Transformers

Yuka Kihara, MS; Mengxi Shen, MD; Yingying Shi, MD; Xiaoshuang Jiang, MD, PhD; Liang Wang, BS; Rita Laiginhas, MD, PhD; Cancan Lyu, MD, PhD; Jin Yang, MD, PhD; Jeremy Liu, BS; Rosalyn Morin; Randy Lu, BS; Hironobu Fujiyoshi, PhD; William J. Feuer, MS; Giovanni Gregori, PhD; Philip J. Rosenfeld, MD, PhD; Aaron Y. Lee, MD, MSCI

Ophthalmology Science (Dec 2022)

Detection of Nonexudative Macular Neovascularization on Structural OCT Images Using Vision Transformers

Yuka Kihara, MS,
Mengxi Shen, MD,
Yingying Shi, MD,
Xiaoshuang Jiang, MD, PhD,
Liang Wang, BS,
Rita Laiginhas, MD, PhD,
Cancan Lyu, MD, PhD,
Jin Yang, MD, PhD,
Jeremy Liu, BS,
Rosalyn Morin,
Randy Lu, BS,
Hironobu Fujiyoshi, PhD,
William J. Feuer, MS,
Giovanni Gregori, PhD,
Philip J. Rosenfeld, MD, PhD,
Aaron Y. Lee, MD, MSCI

Affiliations

Yuka Kihara, MS: University of Washington, Department of Ophthalmology, Seattle, Washington
Mengxi Shen, MD: Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
Yingying Shi, MD: Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
Xiaoshuang Jiang, MD, PhD: Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
Liang Wang, BS: Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
Rita Laiginhas, MD, PhD: Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
Cancan Lyu, MD, PhD: Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
Jin Yang, MD, PhD: Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
Jeremy Liu, BS: Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
Rosalyn Morin: Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
Randy Lu, BS: University of Washington, Department of Ophthalmology, Seattle, Washington
Hironobu Fujiyoshi, PhD: Department of Robotic Science and Technology, Chubu University, Aichi, Japan
William J. Feuer, MS: Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
Giovanni Gregori, PhD: Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
Philip J. Rosenfeld, MD, PhD: Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
Aaron Y. Lee, MD, MSCI: University of Washington, Department of Ophthalmology, Seattle, Washington; Correspondence: Aaron Y. Lee, MD, MSCI, Department of Ophthalmology, University of Washington, 325 Ninth Avenue, Box 359608, Seattle, WA 98104.

Journal volume & issue: Vol. 2, no. 4
p. 100197

Abstract

Read online

Purpose: A deep learning model was developed to detect nonexudative macular neovascularization (neMNV) using OCT B-scans. Design: Retrospective review of a prospective, observational study. Participants: Normal control eyes and patients with age-related macular degeneration (AMD) with and without neMNV. Methods: Swept-source OCT angiography (SS-OCTA) imaging (PLEX Elite 9000, Carl Zeiss Meditec, Inc) was performed using the 6 × 6-mm scan pattern. Individual B-scans were annotated to distinguish between drusen and the double-layer sign (DLS) associated with the neMNV. The machine learning model was tested on a dataset graded by humans, and model performance was compared with the human graders. Main Outcome Measures: Intersection over Union (IoU) score was measured to evaluate segmentation network performance. Area under the receiver operating characteristic curve values, sensitivity, specificity, and positive predictive value (PPV) and negative predictive value (NPV) were measured to assess the performance of the final classification performance. Chance-corrected agreement between the algorithm and the human grader determinations was measured with Cohen’s kappa. Results: A total of 251 eyes from 210 patients, including 182 eyes with DLS and 115 eyes with drusen, were used for model training. Of 125 500 B-scans, 6879 B-scans were manually annotated. A vision transformer segmentation model was built to extract DLS and drusen from B-scans. The extracted prediction masks from all B-scans in a volume were projected to an en face image, and an eye-level projection map was obtained for each eye. A binary classification algorithm was established to identify eyes with neMNV from the projection map. The algorithm achieved 82%, 90%, 79%, and 91% sensitivity, specificity, PPV, and NPV, respectively, on a separate test set of 100 eyes that were evaluated by human graders in a previous study. The area under the curve value was calculated as 0.91 (95% confidence interval, 0.85–0.98). The results of the algorithm showed excellent agreement with the senior human grader (kappa = 0.83, P < 0.001) and moderate agreement with the junior grader consensus (kappa = 0.54, P < 0.001). Conclusions: Our network (code is available at https://github.com/uw-biomedical-ml/double_layer_vit) was able to detect the presence of neMNV from structural B-scans alone by applying a purely transformer-based model.

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