2
|
Ehlers JP, McConville C, Yordi S, Cetin H, Cakir Y, Kalra G, Amine R, Whitney J, Whitmore V, Bonnay M, Reese J, Clark J, Zhu L, Luo D, Jaffe GJ, Srivastava SK. Correlation Between Blue Fundus Autofluorescence and SD-OCT Measurements of Geographic Atrophy in Dry Age-Related Macular Degeneration. Am J Ophthalmol 2024; 266:92-101. [PMID: 38719131 DOI: 10.1016/j.ajo.2024.04.031] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2023] [Revised: 04/27/2024] [Accepted: 04/30/2024] [Indexed: 06/13/2024]
Abstract
PURPOSE To compare fundus autofluorescence (FAF) and spectral domain optical coherence tomography (OCT) measurements of geographic atrophy (GA) area and to analyze lesion area changes measured by spectral domain OCT in GATHER1. DESIGN An assessment reliability analysis using prospective, randomized, double-masked phase 2/3 clinical trial data. METHODS GATHER1 examined the efficacy and safety of avacincaptad pegol (ACP) for GA treatment. A post hoc analysis was performed to identify correlations between FAF- and OCT-based measurements of GA. GA area was measured on blue-light FAF images using semiautomatic segmentation software with support from OCT and near-infrared imaging. Machine-learning enhanced, multilayer segmentation of OCT scans were reviewed by human readers, and segmentation errors were corrected as needed. GA area was defined as total RPE loss on cross-sectional B scans. Time points included Months 0, 6, 12, and 18. Additionally, OCT-based GA-area changes between ACP and sham were analyzed. RESULTS There was a strong correlation (r = 0.93) between FAF and OCT GA area measurements that persisted through 18 months. Mean (SD) differences between OCT and FAF GA measurements were negligible: 0.11 mm2 (1.42) at Month 0, 0.03 mm2 (1.62) at Month 6, -0.17 mm2 (1.81) at Month 12, and -0.07 mm2 (1.78) at Month 18. OCT assessments of GA growth revealed a 30% and 27% reduction at Months 12 and 18, respectively, between ACP and sham, replicating FAF measurements from GATHER1. CONCLUSIONS The strong correlation between blue FAF and OCT measurements of GA area supports OCT as a reliable method to measure GA lesion area in clinical trials.
Collapse
Affiliation(s)
- Justis P Ehlers
- From The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA; Cole Eye Institute, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA.
| | - Conor McConville
- From The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA; Cole Eye Institute, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA
| | - Sari Yordi
- From The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA; Cole Eye Institute, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA
| | - Hasan Cetin
- From The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA; Cole Eye Institute, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA
| | - Yavuz Cakir
- From The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA; Cole Eye Institute, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA
| | - Gagan Kalra
- From The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA; Cole Eye Institute, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA
| | - Reem Amine
- From The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA; Cole Eye Institute, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA
| | - Jon Whitney
- From The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA; Cole Eye Institute, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA
| | - Victoria Whitmore
- From The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA; Cole Eye Institute, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA
| | - Michelle Bonnay
- From The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA; Cole Eye Institute, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA
| | - Jamie Reese
- From The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA; Cole Eye Institute, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA
| | - Julie Clark
- Iveric Bio, An Astellas Company (J.C., L.Z., D.L.), Parsippany-Troy Hills, New Jersey, USA
| | - Liansheng Zhu
- Iveric Bio, An Astellas Company (J.C., L.Z., D.L.), Parsippany-Troy Hills, New Jersey, USA
| | - Don Luo
- Iveric Bio, An Astellas Company (J.C., L.Z., D.L.), Parsippany-Troy Hills, New Jersey, USA
| | - Glenn J Jaffe
- Department of Ophthalmology, Duke University (G.J.J.), Durham, North Carolina, USA
| | - Sunil K Srivastava
- From The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA; Cole Eye Institute, Cleveland Clinic (J.P.E., C.M., S.Y., H.C., Y.C., G.K., R.A., J.W., V.W., M.B., J.R., S.K.S.), Cleveland, Ohio, USA
| |
Collapse
|
6
|
Lu J, Cheng Y, Hiya FE, Shen M, Herrera G, Zhang Q, Gregori G, Rosenfeld PJ, Wang RK. Deep-learning-based automated measurement of outer retinal layer thickness for use in the assessment of age-related macular degeneration, applicable to both swept-source and spectral-domain OCT imaging. BIOMEDICAL OPTICS EXPRESS 2024; 15:413-427. [PMID: 38223170 PMCID: PMC10783897 DOI: 10.1364/boe.512359] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/16/2023] [Revised: 12/17/2023] [Accepted: 12/17/2023] [Indexed: 01/16/2024]
Abstract
Effective biomarkers are required for assessing the progression of age-related macular degeneration (AMD), a prevalent and progressive eye disease. This paper presents a deep learning-based automated algorithm, applicable to both swept-source OCT (SS-OCT) and spectral-domain OCT (SD-OCT) scans, for measuring outer retinal layer (ORL) thickness as a surrogate biomarker for outer retinal degeneration, e.g., photoreceptor disruption, to assess AMD progression. The algorithm was developed based on a modified TransUNet model with clinically annotated retinal features manifested in the progression of AMD. The algorithm demonstrates a high accuracy with an intersection of union (IoU) of 0.9698 in the testing dataset for segmenting ORL using both SS-OCT and SD-OCT datasets. The robustness and applicability of the algorithm are indicated by strong correlation (r = 0.9551, P < 0.0001 in the central-fovea 3 mm-circle, and r = 0.9442, P < 0.0001 in the 5 mm-circle) and agreement (the mean bias = 0.5440 um in the 3-mm circle, and 1.392 um in the 5-mm circle) of the ORL thickness measurements between SS-OCT and SD-OCT scans. Comparative analysis reveals significant differences (P < 0.0001) in ORL thickness among 80 normal eyes, 30 intermediate AMD eyes with reticular pseudodrusen, 49 intermediate AMD eyes with drusen, and 40 late AMD eyes with geographic atrophy, highlighting its potential as an independent biomarker for predicting AMD progression. The findings provide valuable insights into the ORL alterations associated with different stages of AMD and emphasize the potential of ORL thickness as a sensitive indicator of AMD severity and progression.
Collapse
Affiliation(s)
- Jie Lu
- Department of Bioengineering, University of Washington, Seattle, Washington, USA
| | - Yuxuan Cheng
- Department of Bioengineering, University of Washington, Seattle, Washington, USA
| | - Farhan E. Hiya
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Mengxi Shen
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Gissel Herrera
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Qinqin Zhang
- Research and Development, Carl Zeiss Meditec, Inc., Dublin, CA, USA
| | - Giovanni Gregori
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Philip J. Rosenfeld
- Department of Ophthalmology, Bascom Palmer Eye Institute, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Ruikang K. Wang
- Department of Bioengineering, University of Washington, Seattle, Washington, USA
- Department of Ophthalmology, University of Washington, Seattle, Washington, USA
| |
Collapse
|
8
|
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
|