1
|
Kihara Y, Shen M, Shi Y, Jiang X, Wang L, Laiginhas R, Lyu C, Yang J, Liu J, Morin R, Lu R, Fujiyoshi H, Feuer WJ, Gregori G, Rosenfeld PJ, Lee AY. Detection of Nonexudative Macular Neovascularization on Structural OCT Images Using Vision Transformers. Ophthalmol Sci 2022; 2:100197. [PMID: 36531577 PMCID: PMC9754966 DOI: 10.1016/j.xops.2022.100197] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/31/2022] [Revised: 06/09/2022] [Accepted: 07/01/2022] [Indexed: 06/17/2023]
Abstract
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.
Collapse
Key Words
- AI, artificial intelligence
- AMD, age-related macular degeneration
- Age-related macular degeneration
- CNN, convolutional neural network
- DLS, double-layer sign
- Deep learning
- GA, geographic atrophy
- IoU, Intersection over Union
- MNV, macular neovascularization
- Macular neovascularization
- NPV, negative predictive value
- OCT
- OCTA, OCT angiography
- PPV, positive predictive value
- ROC, receiver operating characteristic
- RPE, retinal pigment epithelium
- SS-OCT, swept-source OCT
- SS-OCTA, swept-source OCT angiography
- ViT, Vision Transformer
- iAMD, intermediate age-related macular degeneration
- neMNV, nonexudative macular neovascularization
Collapse
Affiliation(s)
- Yuka Kihara
- University of Washington, Department of Ophthalmology, Seattle, Washington
| | - Mengxi Shen
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
| | - Yingying Shi
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
| | - Xiaoshuang Jiang
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
| | - Liang Wang
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
| | - Rita Laiginhas
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
| | - Cancan Lyu
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
| | - Jin Yang
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
| | - Jeremy Liu
- 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
- University of Washington, Department of Ophthalmology, Seattle, Washington
| | - Hironobu Fujiyoshi
- Department of Robotic Science and Technology, Chubu University, Aichi, Japan
| | - William J. Feuer
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
| | - Giovanni Gregori
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
| | - Philip J. Rosenfeld
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida
| | - Aaron Y. Lee
- University of Washington, Department of Ophthalmology, Seattle, Washington
| |
Collapse
|