1
|
Teo KYC, Zhao J, Ibrahim FI, Fenner B, Chakravarthy U, Cheung CMG. Features Associated With Vision in Eyes With Subfoveal Fibrosis From Neovascular Age-Related Macular Degeneration. Am J Ophthalmol 2024; 261:121-131. [PMID: 38135238 DOI: 10.1016/j.ajo.2023.12.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2023] [Revised: 12/12/2023] [Accepted: 12/14/2023] [Indexed: 12/24/2023]
Abstract
PURPOSE To report the characteristics and correlation of visual acuity in eyes treated for neovascular age-related macular degeneration (nAMD) and developed fibrosis. DESIGN Case-control study. METHODS Three hundred fifty-six treatment-naive nAMD eyes that were treated for 12 months were included. Fibrosis was defined as present if well-defined hyperreflective material (HRM) were present between the neurosensory retina and the Bruch membrane on optical coherence tomography (OCT) that correlated with well-defined regions of yellowish pallor on fundus photography and/or staining on fluorescence angiography. OCT features of subfoveal fibrosis and the overlying retina were correlated with visual acuity at month 12. RESULTS Sixty-three eyes (20.3%) developed incident fibrosis at month 12. Compared with eyes that did not develop fibrosis, these eyes had lower baseline vision (49 vs 54 letters, P = .02) and more of them had type 2 macular neovascularization (15.0 vs 8.8%, P = .03), larger lesion area (29.6 vs 15.1 mm2, P = .02), and subretinal hemorrhage ≥4 disc diameters (44.4% vs 19.8%, P < .01). Visual acuity was worse in the incident fibrosis compared with the group that never developed fibrosis by month 12. (-1.4±17.1 versus +6.0±17.4 letters, P < .01). In 83 eyes that had subfoveal fibrosis, better vision was associated with intact ellipsoid zone-external limiting membrane complex (β coefficient 29.4, 95% CI 14.2-44.6, P < .01), whereas worse vision was associated with retinal pigment epithelium (RPE)-involving HRM, HRM above the RPE, and width of HRM (β coefficients -25.4 [95% CI -36.3 to -14.6], P < .01; -23.5 [95% CI -39.0 to -7.9], P < .01; and -3.8 [95% CI -7.2 to -0.4], P = .03, respectively). CONCLUSION Although fibrosis is associated with poorer visual outcome, preservation of external limiting membrane and level of fibrosis relative to the RPE are associated with visual outcomes.
Collapse
Affiliation(s)
- Kelvin Y C Teo
- From the Singapore Eye Research Institute, Singapore National Eye Centre (K.Y.C.T., J.Z., F.I.I., B.F., C.M.G.C.), Singapore; Duke-NUS Medical School, National University of Singapore (K.Y.C.T., F.I.I., B.F., C.M.G.C.), Singapore
| | - Jinzhi Zhao
- From the Singapore Eye Research Institute, Singapore National Eye Centre (K.Y.C.T., J.Z., F.I.I., B.F., C.M.G.C.), Singapore
| | - Farah Ilyana Ibrahim
- From the Singapore Eye Research Institute, Singapore National Eye Centre (K.Y.C.T., J.Z., F.I.I., B.F., C.M.G.C.), Singapore; Duke-NUS Medical School, National University of Singapore (K.Y.C.T., F.I.I., B.F., C.M.G.C.), Singapore
| | - Beau Fenner
- From the Singapore Eye Research Institute, Singapore National Eye Centre (K.Y.C.T., J.Z., F.I.I., B.F., C.M.G.C.), Singapore; Duke-NUS Medical School, National University of Singapore (K.Y.C.T., F.I.I., B.F., C.M.G.C.), Singapore
| | | | - Chui Ming Gemmy Cheung
- From the Singapore Eye Research Institute, Singapore National Eye Centre (K.Y.C.T., J.Z., F.I.I., B.F., C.M.G.C.), Singapore; Duke-NUS Medical School, National University of Singapore (K.Y.C.T., F.I.I., B.F., C.M.G.C.), Singapore.
| |
Collapse
|
2
|
Leingang O, Riedl S, Mai J, Reiter GS, Faustmann G, Fuchs P, Scholl HPN, Sivaprasad S, Rueckert D, Lotery A, Schmidt-Erfurth U, Bogunović H. Automated deep learning-based AMD detection and staging in real-world OCT datasets (PINNACLE study report 5). Sci Rep 2023; 13:19545. [PMID: 37945665 PMCID: PMC10636170 DOI: 10.1038/s41598-023-46626-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/08/2023] [Accepted: 11/03/2023] [Indexed: 11/12/2023] Open
Abstract
Real-world retinal optical coherence tomography (OCT) scans are available in abundance in primary and secondary eye care centres. They contain a wealth of information to be analyzed in retrospective studies. The associated electronic health records alone are often not enough to generate a high-quality dataset for clinical, statistical, and machine learning analysis. We have developed a deep learning-based age-related macular degeneration (AMD) stage classifier, to efficiently identify the first onset of early/intermediate (iAMD), atrophic (GA), and neovascular (nAMD) stage of AMD in retrospective data. We trained a two-stage convolutional neural network to classify macula-centered 3D volumes from Topcon OCT images into 4 classes: Normal, iAMD, GA and nAMD. In the first stage, a 2D ResNet50 is trained to identify the disease categories on the individual OCT B-scans while in the second stage, four smaller models (ResNets) use the concatenated B-scan-wise output from the first stage to classify the entire OCT volume. Classification uncertainty estimates are generated with Monte-Carlo dropout at inference time. The model was trained on a real-world OCT dataset, 3765 scans of 1849 eyes, and extensively evaluated, where it reached an average ROC-AUC of 0.94 in a real-world test set.
Collapse
Affiliation(s)
- Oliver Leingang
- Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Sophie Riedl
- Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Julia Mai
- Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Gregor S Reiter
- Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Georg Faustmann
- Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
- Christian Doppler Lab for Artificial Intelligence in Retina, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Philipp Fuchs
- Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Hendrik P N Scholl
- Institute of Molecular and Clinical Ophthalmology Basel, Basel, Switzerland
- Department of Ophthalmology, University of Basel, Basel, Switzerland
| | - Sobha Sivaprasad
- NIHR Moorfields Biomedical Research Centre, Moorfields Eye Hospital NHS Foundation Trust, London, UK
| | - Daniel Rueckert
- BioMedIA, Imperial College London, London, UK
- Institute for AI and Informatics in Medicine, Klinikum rechts der Isar, Technical University Munich, Munich, Germany
| | - Andrew Lotery
- Clinical and Experimental Sciences, Faculty of Medicine, University of Southampton, Southampton, UK
| | - Ursula Schmidt-Erfurth
- Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Hrvoje Bogunović
- Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria.
- Christian Doppler Lab for Artificial Intelligence in Retina, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria.
| |
Collapse
|
3
|
Tan TE, Fenner BJ, Barathi VA, Tun SBB, Wey YS, Tsai ASH, Su X, Lee SY, Cheung CMG, Wong TY, Mehta JS, Teo KYC. Gene-Based Therapeutics for Acquired Retinal Disease: Opportunities and Progress. Front Genet 2021; 12:795010. [PMID: 34950193 PMCID: PMC8688942 DOI: 10.3389/fgene.2021.795010] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2021] [Accepted: 11/16/2021] [Indexed: 12/22/2022] Open
Abstract
Acquired retinal diseases such as age-related macular degeneration and diabetic retinopathy rank among the leading causes of blindness and visual loss worldwide. Effective treatments for these conditions are available, but often have a high treatment burden, and poor compliance can lead to disappointing real-world outcomes. Development of new treatment strategies that provide more durable treatment effects could help to address some of these unmet needs. Gene-based therapeutics, pioneered for the treatment of monogenic inherited retinal disease, are being actively investigated as new treatments for acquired retinal disease. There are significant advantages to the application of gene-based therapeutics in acquired retinal disease, including the presence of established therapeutic targets and common pathophysiologic pathways between diseases, the lack of genotype-specificity required, and the larger potential treatment population per therapy. Different gene-based therapeutic strategies have been attempted, including gene augmentation therapy to induce in vivo expression of therapeutic molecules, and gene editing to knock down genes encoding specific mediators in disease pathways. We highlight the opportunities and unmet clinical needs in acquired retinal disease, review the progress made thus far with current therapeutic strategies and surgical delivery techniques, and discuss limitations and future directions in the field.
Collapse
Affiliation(s)
- Tien-En Tan
- Singapore National Eye Centre, Singapore, Singapore.,Singapore Eye Research Institute, Singapore, Singapore.,Duke-National University of Singapore Medical School, Singapore, Singapore
| | - Beau James Fenner
- Singapore National Eye Centre, Singapore, Singapore.,Singapore Eye Research Institute, Singapore, Singapore.,Duke-National University of Singapore Medical School, Singapore, Singapore
| | - Veluchamy Amutha Barathi
- Singapore Eye Research Institute, Singapore, Singapore.,Duke-National University of Singapore Medical School, Singapore, Singapore.,Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
| | - Sai Bo Bo Tun
- Singapore Eye Research Institute, Singapore, Singapore
| | - Yeo Sia Wey
- Singapore Eye Research Institute, Singapore, Singapore
| | - Andrew Shih Hsiang Tsai
- Singapore National Eye Centre, Singapore, Singapore.,Singapore Eye Research Institute, Singapore, Singapore.,Duke-National University of Singapore Medical School, Singapore, Singapore
| | - Xinyi Su
- Singapore Eye Research Institute, Singapore, Singapore.,Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.,Institute of Molecular and Cell Biology (IMCB), Agency for Science, Technology and Research (ASTAR), Singapore, Singapore.,Department of Ophthalmology, National University Hospital, Singapore, Singapore
| | - Shu Yen Lee
- Singapore National Eye Centre, Singapore, Singapore.,Singapore Eye Research Institute, Singapore, Singapore.,Duke-National University of Singapore Medical School, Singapore, Singapore
| | - Chui Ming Gemmy Cheung
- Singapore National Eye Centre, Singapore, Singapore.,Singapore Eye Research Institute, Singapore, Singapore.,Duke-National University of Singapore Medical School, Singapore, Singapore
| | - Tien Yin Wong
- Singapore National Eye Centre, Singapore, Singapore.,Singapore Eye Research Institute, Singapore, Singapore.,Duke-National University of Singapore Medical School, Singapore, Singapore
| | - Jodhbir Singh Mehta
- Singapore National Eye Centre, Singapore, Singapore.,Singapore Eye Research Institute, Singapore, Singapore.,Duke-National University of Singapore Medical School, Singapore, Singapore
| | - Kelvin Yi Chong Teo
- Singapore National Eye Centre, Singapore, Singapore.,Singapore Eye Research Institute, Singapore, Singapore.,Duke-National University of Singapore Medical School, Singapore, Singapore
| |
Collapse
|