1
|
Braun M, Saini C, Sun JA, Shen LQ. The Role of Optical Coherence Tomography Angiography in Glaucoma. Semin Ophthalmol 2024; 39:412-423. [PMID: 38643350 DOI: 10.1080/08820538.2024.2343049] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/08/2024] [Revised: 04/08/2024] [Accepted: 04/09/2024] [Indexed: 04/22/2024]
Abstract
Glaucoma is the leading cause of irreversible vision loss and comprises a group of chronic optic neuropathies characterized by progressive retinal ganglion cell (RGC) loss. Various etiologies, including impaired blood supply to the optic nerve, have been implicated for glaucoma pathogenesis. Optical coherence tomography angiography (OCTA) is a non-invasive imaging modality for visualizing the ophthalmic microvasculature. Using blood flow as an intrinsic contrast agent, it distinguishes blood vessels from the surrounding tissue. Vessel density (VD) is mainly used as a metric for quantifying the ophthalmic microvasculature. The key anatomic regions for OCTA in glaucoma are the optic nerve head area including the peripapillary region, and the macular region. Specifically, VD of the superficial peripapillary and superficial macular microvasculature is reduced in glaucoma patients compared to unaffected subjects, and VD correlates with functional deficits measured by visual field (VF). This renders OCTA similar in diagnostic capabilities compared to structural retinal nerve fiber layer (RNFL) thickness measurements, especially in early glaucoma. Furthermore, in cases where RNFL thickness measurements are limited due to artifact or floor effect, OCTA technology can be used to evaluate and monitor glaucoma, such as in eyes with high myopia and eyes with advanced glaucoma. However, the clinical utility of OCTA in glaucoma management is limited due to the prevalence of imaging artifacts. Overall, OCTA can play a complementary role in structural OCT imaging and VF testing to aid in the diagnosis and monitoring of glaucoma.
Collapse
Affiliation(s)
- Maximilian Braun
- Department of Ophthalmology, Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, USA
- Department of Ophthalmology, University Medical Center of the Johannes Gutenberg-University Mainz, Mainz, Germany
| | - Chhavi Saini
- Department of Ophthalmology, Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, USA
| | - Jessica A Sun
- Department of Ophthalmology, Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, USA
| | - Lucy Q Shen
- Department of Ophthalmology, Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, USA
| |
Collapse
|
2
|
Bellemo V, Kumar Das A, Sreng S, Chua J, Wong D, Shah J, Jonas R, Tan B, Liu X, Xu X, Tan GSW, Agrawal R, Ting DSW, Yong L, Schmetterer L. Optical coherence tomography choroidal enhancement using generative deep learning. NPJ Digit Med 2024; 7:115. [PMID: 38704440 PMCID: PMC11069520 DOI: 10.1038/s41746-024-01119-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2023] [Accepted: 04/23/2024] [Indexed: 05/06/2024] Open
Abstract
Spectral-domain optical coherence tomography (SDOCT) is the gold standard of imaging the eye in clinics. Penetration depth with such devices is, however, limited and visualization of the choroid, which is essential for diagnosing chorioretinal disease, remains limited. Whereas swept-source OCT (SSOCT) devices allow for visualization of the choroid these instruments are expensive and availability in praxis is limited. We present an artificial intelligence (AI)-based solution to enhance the visualization of the choroid in OCT scans and allow for quantitative measurements of choroidal metrics using generative deep learning (DL). Synthetically enhanced SDOCT B-scans with improved choroidal visibility were generated, leveraging matching images to learn deep anatomical features during the training. Using a single-center tertiary eye care institution cohort comprising a total of 362 SDOCT-SSOCT paired subjects, we trained our model with 150,784 images from 410 healthy, 192 glaucoma, and 133 diabetic retinopathy eyes. An independent external test dataset of 37,376 images from 146 eyes was deployed to assess the authenticity and quality of the synthetically enhanced SDOCT images. Experts' ability to differentiate real versus synthetic images was poor (47.5% accuracy). Measurements of choroidal thickness, area, volume, and vascularity index, from the reference SSOCT and synthetically enhanced SDOCT, showed high Pearson's correlations of 0.97 [95% CI: 0.96-0.98], 0.97 [0.95-0.98], 0.95 [0.92-0.98], and 0.87 [0.83-0.91], with intra-class correlation values of 0.99 [0.98-0.99], 0.98 [0.98-0.99], and 0.95 [0.96-0.98], 0.93 [0.91-0.95], respectively. Thus, our DL generative model successfully generated realistic enhanced SDOCT data that is indistinguishable from SSOCT images providing improved visualization of the choroid. This technology enabled accurate measurements of choroidal metrics previously limited by the imaging depth constraints of SDOCT. The findings open new possibilities for utilizing affordable SDOCT devices in studying the choroid in both healthy and pathological conditions.
Collapse
Affiliation(s)
- Valentina Bellemo
- Singapore Eye Research Institute, National Eye Centre, Singapore, Singapore
- Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore
- SERI-NTU Advanced Ocular Engineering (STANCE) Program, Singapore, Singapore
| | - Ankit Kumar Das
- Institute of High Performance Computing, Agency for Science, Technology and Research (A∗STAR), Singapore, Singapore
| | - Syna Sreng
- Singapore Eye Research Institute, National Eye Centre, Singapore, Singapore
- SERI-NTU Advanced Ocular Engineering (STANCE) Program, Singapore, Singapore
| | - Jacqueline Chua
- Singapore Eye Research Institute, National Eye Centre, Singapore, Singapore
- SERI-NTU Advanced Ocular Engineering (STANCE) Program, Singapore, Singapore
- Ophthalmology & Visual Sciences Academic Clinical Program (Eye ACP), Duke-NUS Medical School, Singapore, Singapore
| | - Damon Wong
- Singapore Eye Research Institute, National Eye Centre, Singapore, Singapore
- SERI-NTU Advanced Ocular Engineering (STANCE) Program, Singapore, Singapore
- Ophthalmology & Visual Sciences Academic Clinical Program (Eye ACP), Duke-NUS Medical School, Singapore, Singapore
- Centre for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria
| | - Janika Shah
- Singapore Eye Research Institute, National Eye Centre, Singapore, Singapore
- Ophthalmology & Visual Sciences Academic Clinical Program (Eye ACP), Duke-NUS Medical School, Singapore, Singapore
| | - Rahul Jonas
- University of Cologne, Faculty of Medicine and University Hospital Cologne, Department Ophthalmology, Cologne, Germany
| | - Bingyao Tan
- Singapore Eye Research Institute, National Eye Centre, Singapore, Singapore
- SERI-NTU Advanced Ocular Engineering (STANCE) Program, Singapore, Singapore
- University of Cologne, Faculty of Medicine and University Hospital Cologne, Department Ophthalmology, Cologne, Germany
| | - Xinyu Liu
- Singapore Eye Research Institute, National Eye Centre, Singapore, Singapore
- SERI-NTU Advanced Ocular Engineering (STANCE) Program, Singapore, Singapore
- Ophthalmology & Visual Sciences Academic Clinical Program (Eye ACP), Duke-NUS Medical School, Singapore, Singapore
| | - Xinxing Xu
- Institute of High Performance Computing, Agency for Science, Technology and Research (A∗STAR), Singapore, Singapore
| | - Gavin Siew Wei Tan
- Singapore Eye Research Institute, National Eye Centre, Singapore, Singapore
- Ophthalmology & Visual Sciences Academic Clinical Program (Eye ACP), Duke-NUS Medical School, Singapore, Singapore
| | - Rupesh Agrawal
- Singapore Eye Research Institute, National Eye Centre, Singapore, Singapore
- Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore
- National Healthcare Group Eye Institute, Tan Tock Seng Hospital, Singapore School of Chemical and Biomedical Engineering, Nanyang Technological University (NTU), Singapore, Singapore
| | - Daniel Shu Wei Ting
- Singapore Eye Research Institute, National Eye Centre, Singapore, Singapore
- Ophthalmology & Visual Sciences Academic Clinical Program (Eye ACP), Duke-NUS Medical School, Singapore, Singapore
| | - Liu Yong
- Singapore Eye Research Institute, National Eye Centre, Singapore, Singapore.
- Institute of High Performance Computing, Agency for Science, Technology and Research (A∗STAR), Singapore, Singapore.
| | - Leopold Schmetterer
- Singapore Eye Research Institute, National Eye Centre, Singapore, Singapore.
- Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore.
- SERI-NTU Advanced Ocular Engineering (STANCE) Program, Singapore, Singapore.
- Ophthalmology & Visual Sciences Academic Clinical Program (Eye ACP), Duke-NUS Medical School, Singapore, Singapore.
- Centre for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria.
- School of Chemistry, Chemical Engineering and Biotechnology, Nanyang Technological University, Singapore, Singapore.
- Department of Clinical Pharmacology, Medical University of Vienna, Vienna, Austria.
- Institute of Molecular and Clinical Ophthalmology, Basel, Switzerland.
| |
Collapse
|
3
|
Hong J, Tan SS, Chua J. Optical coherence tomography angiography in glaucoma. Clin Exp Optom 2024; 107:110-121. [PMID: 38266148 DOI: 10.1080/08164622.2024.2306963] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2023] [Accepted: 01/11/2024] [Indexed: 01/26/2024] Open
Abstract
The use of optical coherence tomography angiography (OCTA) holds significant promise for optometrists in the diagnosis and management of glaucoma. It offers reliable differentiation of glaucomatous eyes from healthy ones and extends monitoring capabilities for advanced cases. OCTA represents a valuable addition to traditional assessment methods, particularly in complex cases. Glaucoma, a major cause of irreversible blindness, is traditionally diagnosed using structural and functional metrics. With growing interest, OCTA is being explored to diagnose, monitor, and manage glaucoma. This review focuses on the application of OCTA in glaucoma patients. A database search was carried out using Embase Elsevier (n = 664), PubMed (n = 574), and Cochrane Central Register of Controlled Trials (n = 19) on 15 August 2023. After deduplication and screening, 272 original papers were included in the narrative review. Inclusion criteria comprised English-language original studies on OCTA use in human glaucoma patients, with or without healthy controls. Exclusion criteria encompassed animal studies, in-vivo/in-vitro research, reviews, and congress abstracts. OCTA has good repeatability and reproducibility. OCTA metrics have good discriminatory power to differentiate glaucomatous eyes from healthy eyes and show strong associations with structural changes and visual field defects. OCTA can extend the monitoring of advanced glaucoma, addressing the 'floor effect' of traditional structural measurements. OCTA metrics can be affected by the choice of OCTA machine, post-image processing algorithms, systemic diseases, and ocular factors. Image artefacts can affect the accuracy of OCTA measurements, and proper scan quality evaluation is crucial to ensure reliable results. Additionally, artificial intelligence techniques offer promise for enhancing the diagnostic accuracy of OCTA by combining data from various retinal layers and regions. OCTA complements traditional methods in assessing glaucoma, especially in challenging cases, providing valuable insights for detection and management. Further research and clinical validation are needed to integrate OCTA into routine practice.
Collapse
Affiliation(s)
- Jimmy Hong
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
| | - Shayne S Tan
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
| | - Jacqueline Chua
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
| |
Collapse
|
4
|
Chiang CYN, Braeu FA, Chuangsuwanich T, Tan RKY, Chua J, Schmetterer L, Thiery AH, Buist ML, Girard MJA. Are Macula or Optic Nerve Head Structures Better at Diagnosing Glaucoma? An Answer Using Artificial Intelligence and Wide-Field Optical Coherence Tomography. Transl Vis Sci Technol 2024; 13:5. [PMID: 38197730 PMCID: PMC10787590 DOI: 10.1167/tvst.13.1.5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2023] [Accepted: 11/06/2023] [Indexed: 01/11/2024] Open
Abstract
Purpose We wanted to develop a deep-learning algorithm to automatically segment optic nerve head (ONH) and macula structures in three-dimensional (3D) wide-field optical coherence tomography (OCT) scans and to assess whether 3D ONH or macula structures (or a combination of both) provide the best diagnostic power for glaucoma. Methods A cross-sectional comparative study was performed using 319 OCT scans of glaucoma eyes and 298 scans of nonglaucoma eyes. Scans were compensated to improve deep-tissue visibility. We developed a deep-learning algorithm to automatically label major tissue structures, trained with 270 manually annotated B-scans. The performance was assessed using the Dice coefficient (DC). A glaucoma classification algorithm (3D-CNN) was then designed using 500 OCT volumes and corresponding automatically segmented labels. This algorithm was trained and tested on three datasets: cropped scans of macular tissues, those of ONH tissues, and wide-field scans. The classification performance for each dataset was reported using the area under the curve (AUC). Results Our segmentation algorithm achieved a DC of 0.94 ± 0.003. The classification algorithm was best able to diagnose glaucoma using wide-field scans, followed by ONH scans, and finally macula scans, with AUCs of 0.99 ± 0.01, 0.93 ± 0.06 and 0.91 ± 0.11, respectively. Conclusions This study showed that wide-field OCT may allow for significantly improved glaucoma diagnosis over typical OCTs of the ONH or macula. Translational Relevance This could lead to mainstream clinical adoption of 3D wide-field OCT scan technology.
Collapse
Affiliation(s)
- Charis Y. N. Chiang
- Department of Biomedical Engineering, National University of Singapore, Singapore
- Ophthalmic Engineering & Innovation Laboratory, Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
| | - Fabian A. Braeu
- Ophthalmic Engineering & Innovation Laboratory, Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
- Singapore-MIT Alliance for Research and Technology, Singapore
- Yong Loo Lin School of Medicine, National University of Singapore, Singapore
| | - Thanadet Chuangsuwanich
- Department of Biomedical Engineering, National University of Singapore, Singapore
- Ophthalmic Engineering & Innovation Laboratory, Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
| | - Royston K. Y. Tan
- Department of Biomedical Engineering, National University of Singapore, Singapore
- Ophthalmic Engineering & Innovation Laboratory, Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
| | - Jacqueline Chua
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
- SERI-NTU Advanced Ocular Engineering (STANCE), Singapore, Singapore
- Duke-NUS Graduate Medical School, Singapore
| | - Leopold Schmetterer
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
- SERI-NTU Advanced Ocular Engineering (STANCE), Singapore, Singapore
- Duke-NUS Graduate Medical School, Singapore
- School of Chemical and Biological Engineering, Nanyang Technological University, Singapore
- Department of Clinical Pharmacology, Medical University of Vienna, Austria
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Austria
- Institute of Molecular and Clinical Ophthalmology, Basel, Switzerland
| | - Alexandre H. Thiery
- Department of Statistics and Data Sciences, National University of Singapore, Singapore
| | - Martin L. Buist
- Department of Biomedical Engineering, National University of Singapore, Singapore
| | - Michaël J. A. Girard
- Ophthalmic Engineering & Innovation Laboratory, Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
- Duke-NUS Graduate Medical School, Singapore
- Institute of Molecular and Clinical Ophthalmology, Basel, Switzerland
| |
Collapse
|