1
|
Holland R, Leingang O, Bogunović H, Riedl S, Fritsche L, Prevost T, Scholl HPN, Schmidt-Erfurth U, Sivaprasad S, Lotery AJ, Rueckert D, Menten MJ. Metadata-enhanced contrastive learning from retinal optical coherence tomography images. Med Image Anal 2024; 97:103296. [PMID: 39154616 DOI: 10.1016/j.media.2024.103296] [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: 08/03/2022] [Revised: 07/26/2024] [Accepted: 08/01/2024] [Indexed: 08/20/2024]
Abstract
Deep learning has potential to automate screening, monitoring and grading of disease in medical images. Pretraining with contrastive learning enables models to extract robust and generalisable features from natural image datasets, facilitating label-efficient downstream image analysis. However, the direct application of conventional contrastive methods to medical datasets introduces two domain-specific issues. Firstly, several image transformations which have been shown to be crucial for effective contrastive learning do not translate from the natural image to the medical image domain. Secondly, the assumption made by conventional methods, that any two images are dissimilar, is systematically misleading in medical datasets depicting the same anatomy and disease. This is exacerbated in longitudinal image datasets that repeatedly image the same patient cohort to monitor their disease progression over time. In this paper we tackle these issues by extending conventional contrastive frameworks with a novel metadata-enhanced strategy. Our approach employs widely available patient metadata to approximate the true set of inter-image contrastive relationships. To this end we employ records for patient identity, eye position (i.e. left or right) and time series information. In experiments using two large longitudinal datasets containing 170,427 retinal optical coherence tomography (OCT) images of 7912 patients with age-related macular degeneration (AMD), we evaluate the utility of using metadata to incorporate the temporal dynamics of disease progression into pretraining. Our metadata-enhanced approach outperforms both standard contrastive methods and a retinal image foundation model in five out of six image-level downstream tasks related to AMD. We find benefits in both a low-data and high-data regime across tasks ranging from AMD stage and type classification to prediction of visual acuity. Due to its modularity, our method can be quickly and cost-effectively tested to establish the potential benefits of including available metadata in contrastive pretraining.
Collapse
Affiliation(s)
- Robbie Holland
- BioMedIA, Imperial College London, London, United Kingdom.
| | - Oliver Leingang
- Laboratory for Ophthalmic Image Analysis, Medical University of Vienna, Vienna, Austria
| | - Hrvoje Bogunović
- Laboratory for Ophthalmic Image Analysis, Medical University of Vienna, Vienna, Austria; Christian Doppler Lab for Artificial Intelligence in Retina, Medical University of Vienna, Vienna, Austria
| | - Sophie Riedl
- Laboratory for Ophthalmic Image Analysis, Medical University of Vienna, Vienna, Austria
| | - Lars Fritsche
- Department of Biostatistics, University of Michigan, Ann Arbor, MI, United States
| | - Toby Prevost
- Nightingale-Saunders Clinical Trials & Epidemiology Unit, King's College London, London, United Kingdom
| | - Hendrik P N Scholl
- Institute of Molecular and Clinical Ophthalmology Basel, Basel, Basel-Stadt, Switzerland; Department of Ophthalmology, Universitat Basel, Basel, Basel-Stadt, Switzerland
| | | | - Sobha Sivaprasad
- Institute of Ophthalmology, University College London, London, United Kingdom; Moorfields National Institute for Health and Care Biomedical Research Centre, Moorfields Eye Hospital, London, United Kingdom
| | - Andrew J Lotery
- Clinical and Experimental Sciences, Faculty of Medicine, University of Southampton, Southampton, Hampshire, United Kingdom
| | | | - Martin J Menten
- BioMedIA, Imperial College London, London, United Kingdom; Institute for AI and Informatics in Medicine, Technical University of Munich, Munich, Bavaria, Germany
| |
Collapse
|
2
|
Sivaprasad S, Chandra S, Sadda S, Teo KYC, Thottarath S, de Cock E, Empeslidis T, Esmaeelpour M. Predict and Protect: Evaluating the Double-Layer Sign in Age-Related Macular Degeneration. Ophthalmol Ther 2024; 13:2511-2541. [PMID: 39150604 PMCID: PMC11408448 DOI: 10.1007/s40123-024-01012-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2024] [Accepted: 07/24/2024] [Indexed: 08/17/2024] Open
Abstract
INTRODUCTION Advanced age-related macular degeneration (AMD) is a major cause of vision loss. Therefore, there is interest in precursor lesions that may predict or prevent the onset of advanced AMD. One such lesion is a shallow separation of the retinal pigment epithelium (RPE) and Bruch's membrane (BM), which is described by various terms, including double-layer sign (DLS). METHODS In this article, we aim to examine and clarify the different terms referring to shallow separation of the RPE and BM. We also review current evidence on the outcomes associated with DLS: firstly, whether DLS is predictive of exudative neovascular AMD; and secondly, whether DLS has potential protective properties against geographic atrophy. RESULTS The range of terms used to describe a shallow separation of the RPE and BM reflects that DLS can present with different characteristics. While vascularised DLS appears to protect against atrophy but can progress to exudation, non-vascularised DLS is associated with an increased risk of atrophy. Optical coherence tomography (OCT) angiography (OCTA) is the principal method for identifying and differentiating various forms of DLS. If OCTA is unavailable or not practically possible, simplified classification of DLS as thick or thin, using OCT, enables the likelihood of vascularisation to be approximated. Research is ongoing to automate DLS detection by applying deep-learning algorithms to OCT scans. CONCLUSIONS The term DLS remains applicable for describing shallow separation of the RPE and BM. Detection and classification of this feature provides valuable information regarding the risk of progression to advanced AMD. However, the appearance of DLS and its value in predicting AMD progression can vary between patients. With further research, individualised risks can be confirmed to inform appropriate treatment.
Collapse
Affiliation(s)
- Sobha Sivaprasad
- National Institute of Health Research Biomedical Research Centre, Moorfields Eye Hospital NHS Foundation Trust, London, UK.
- University College London Institute of Ophthalmology, London, UK.
| | - Shruti Chandra
- National Institute of Health Research Biomedical Research Centre, Moorfields Eye Hospital NHS Foundation Trust, London, UK
- University College London Institute of Ophthalmology, London, UK
| | - SriniVas Sadda
- Doheny Imaging Reading Center, Doheny Eye Institute, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA
| | - Kelvin Y C Teo
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore
- Duke-NUS Medical School, Singapore, Singapore
| | - Sridevi Thottarath
- National Institute of Health Research Biomedical Research Centre, Moorfields Eye Hospital NHS Foundation Trust, London, UK
| | - Eduard de Cock
- Boehringer Ingelheim International GmbH, Ingelheim am Rhein, Germany
| | - Theo Empeslidis
- Boehringer Ingelheim International GmbH, Ingelheim am Rhein, Germany
| | | |
Collapse
|
3
|
Hu Y, Gao Y, Gao W, Luo W, Yang Z, Xiong F, Chen Z, Lin Y, Xia X, Yin X, Deng Y, Ma L, Li G. AMD-SD: An Optical Coherence Tomography Image Dataset for wet AMD Lesions Segmentation. Sci Data 2024; 11:1014. [PMID: 39294152 PMCID: PMC11410981 DOI: 10.1038/s41597-024-03844-6] [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: 04/03/2024] [Accepted: 09/02/2024] [Indexed: 09/20/2024] Open
Abstract
Wet Age-related Macular Degeneration (wet AMD) is a common ophthalmic disease that significantly impacts patients' vision. Optical coherence tomography (OCT) examination has been widely utilized for diagnosing, treating, and monitoring wet AMD due to its cost-effectiveness, non-invasiveness, and repeatability, positioning it as the most valuable tool for diagnosis and tracking. OCT can provide clear visualization of retinal layers and precise segmentation of lesion areas, facilitating the identification and quantitative analysis of abnormalities. However, the lack of high-quality datasets for assessing wet AMD has impeded the advancement of related algorithms. To address this issue, we have curated a comprehensive wet AMD OCT Segmentation Dataset (AMD-SD), comprising 3049 B-scan images from 138 patients, each annotated with five segmentation labels: subretinal fluid, intraretinal fluid, ellipsoid zone continuity, subretinal hyperreflective material, and pigment epithelial detachment. This dataset presents a valuable opportunity to investigate the accuracy and reliability of various segmentation algorithms for wet AMD, offering essential data support for developing AI-assisted clinical applications targeting wet AMD.
Collapse
Affiliation(s)
- Yunwei Hu
- Ophthalmic Center, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330000, P. R. China
| | - Yundi Gao
- Ophthalmic Center, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330000, P. R. China
| | - Weihao Gao
- Shenzhen International Graduate School, Tsinghua University, Lishui Rd, Shenzhen, 518055, Guangdong, P. R. China
| | - Wenbin Luo
- Ophthalmic Center, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330000, P. R. China
| | - Zhongyi Yang
- Ophthalmic Center, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330000, P. R. China
| | - Fen Xiong
- Ophthalmic Center, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330000, P. R. China
| | - Zidan Chen
- Ophthalmic Center, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330000, P. R. China
| | - Yucai Lin
- Ophthalmic Center, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330000, P. R. China
| | - Xinjing Xia
- Ophthalmic Center, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330000, P. R. China
| | - Xiaolong Yin
- Ophthalmic Center, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330000, P. R. China.
| | - Yan Deng
- Ophthalmic Center, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330000, P. R. China.
| | - Lan Ma
- Shenzhen International Graduate School, Tsinghua University, Lishui Rd, Shenzhen, 518055, Guangdong, P. R. China.
| | - Guodong Li
- Ophthalmic Center, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, 330000, P. R. China.
| |
Collapse
|
4
|
Balas M, Micieli JA, Wong JCY. Integrating AI with tele-ophthalmology in Canada: a review. CANADIAN JOURNAL OF OPHTHALMOLOGY 2024:S0008-4182(24)00259-X. [PMID: 39255951 DOI: 10.1016/j.jcjo.2024.08.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/29/2023] [Revised: 05/21/2024] [Accepted: 08/18/2024] [Indexed: 09/12/2024]
Abstract
The field of ophthalmology is rapidly advancing, with technological innovations enhancing the diagnosis and management of eye diseases. Tele-ophthalmology, or the use of telemedicine for ophthalmology, has emerged as a promising solution to improve access to eye care services, particularly for patients in remote or underserved areas. Despite its potential benefits, tele-ophthalmology faces significant challenges, including the need for high volumes of medical images to be analyzed and interpreted by trained clinicians. Artificial intelligence (AI) has emerged as a powerful tool in ophthalmology, capable of assisting clinicians in diagnosing and treating a variety of conditions. Integrating AI models into existing tele-ophthalmology infrastructure has the potential to revolutionize eye care services by reducing costs, improving efficiency, and increasing access to specialized care. By automating the analysis and interpretation of clinical data and medical images, AI models can reduce the burden on human clinicians, allowing them to focus on patient care and disease management. Available literature on the current status of tele-ophthalmology in Canada and successful AI models in ophthalmology was acquired and examined using the Arksey and O'Malley framework. This review covers literature up to 2022 and is split into 3 sections: 1) existing Canadian tele-ophthalmology infrastructure, with its benefits and drawbacks; 2) preeminent AI models in ophthalmology, across a variety of ocular conditions; and 3) bridging the gap between Canadian tele-ophthalmology and AI in a safe and effective manner.
Collapse
Affiliation(s)
- Michael Balas
- Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada
| | - Jonathan A Micieli
- Department of Ophthalmology and Vision Sciences, University of Toronto, ON, Canada; Division of Neurology, Department of Medicine, St. Michael's Hospital, University of Toronto, Toronto, ON, Canada; Department of Ophthalmology, St. Michael's Hospital, Toronto, ON, Canada
| | - Jovi C Y Wong
- Department of Ophthalmology and Vision Sciences, University of Toronto, ON, Canada.
| |
Collapse
|
5
|
Chakravarty A, Emre T, Leingang O, Riedl S, Mai J, Scholl HPN, Sivaprasad S, Rueckert D, Lotery A, Schmidt-Erfurth U, Bogunovic H. Morph-SSL: Self-Supervision With Longitudinal Morphing for Forecasting AMD Progression From OCT Volumes. IEEE TRANSACTIONS ON MEDICAL IMAGING 2024; 43:3224-3239. [PMID: 38635383 DOI: 10.1109/tmi.2024.3390940] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/20/2024]
Abstract
The lack of reliable biomarkers makes predicting the conversion from intermediate to neovascular age-related macular degeneration (iAMD, nAMD) a challenging task. We develop a Deep Learning (DL) model to predict the future risk of conversion of an eye from iAMD to nAMD from its current OCT scan. Although eye clinics generate vast amounts of longitudinal OCT scans to monitor AMD progression, only a small subset can be manually labeled for supervised DL. To address this issue, we propose Morph-SSL, a novel Self-supervised Learning (SSL) method for longitudinal data. It uses pairs of unlabelled OCT scans from different visits and involves morphing the scan from the previous visit to the next. The Decoder predicts the transformation for morphing and ensures a smooth feature manifold that can generate intermediate scans between visits through linear interpolation. Next, the Morph-SSL trained features are input to a Classifier which is trained in a supervised manner to model the cumulative probability distribution of the time to conversion with a sigmoidal function. Morph-SSL was trained on unlabelled scans of 399 eyes (3570 visits). The Classifier was evaluated with a five-fold cross-validation on 2418 scans from 343 eyes with clinical labels of the conversion date. The Morph-SSL features achieved an AUC of 0.779 in predicting the conversion to nAMD within the next 6 months, outperforming the same network when trained end-to-end from scratch or pre-trained with popular SSL methods. Automated prediction of the future risk of nAMD onset can enable timely treatment and individualized AMD management.
Collapse
|
6
|
Emre T, Chakravarty A, Rivail A, Lachinov D, Leingang O, Riedl S, Mai J, Scholl HPN, Sivaprasad S, Rueckert D, Lotery A, Schmidt-Erfurth U, Bogunovic H. 3DTINC: Time-Equivariant Non-Contrastive Learning for Predicting Disease Progression From Longitudinal OCTs. IEEE TRANSACTIONS ON MEDICAL IMAGING 2024; 43:3200-3210. [PMID: 38656867 DOI: 10.1109/tmi.2024.3391215] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/26/2024]
Abstract
Self-supervised learning (SSL) has emerged as a powerful technique for improving the efficiency and effectiveness of deep learning models. Contrastive methods are a prominent family of SSL that extract similar representations of two augmented views of an image while pushing away others in the representation space as negatives. However, the state-of-the-art contrastive methods require large batch sizes and augmentations designed for natural images that are impractical for 3D medical images. To address these limitations, we propose a new longitudinal SSL method, 3DTINC, based on non-contrastive learning. It is designed to learn perturbation-invariant features for 3D optical coherence tomography (OCT) volumes, using augmentations specifically designed for OCT. We introduce a new non-contrastive similarity loss term that learns temporal information implicitly from intra-patient scans acquired at different times. Our experiments show that this temporal information is crucial for predicting progression of retinal diseases, such as age-related macular degeneration (AMD). After pretraining with 3DTINC, we evaluated the learned representations and the prognostic models on two large-scale longitudinal datasets of retinal OCTs where we predict the conversion to wet-AMD within a six-month interval. Our results demonstrate that each component of our contributions is crucial for learning meaningful representations useful in predicting disease progression from longitudinal volumetric scans.
Collapse
|
7
|
von der Emde L, Künzel SH, Pfau M, Morelle O, Liermann Y, Chang P, Pfau K, Thiele S, Holz FG. [Use of artificial intelligence for recognition of biomarkers in intermediate age-related macular degeneration]. DIE OPHTHALMOLOGIE 2024; 121:609-615. [PMID: 39083095 DOI: 10.1007/s00347-024-02078-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/26/2024] [Revised: 06/20/2024] [Accepted: 06/20/2024] [Indexed: 08/03/2024]
Abstract
Advances in imaging and artificial intelligence (AI) have revolutionized the detection, quantification and monitoring for the clinical assessment of intermediate age-related macular degeneration (iAMD). The iAMD incorporates a broad spectrum of manifestations, which range from individual small drusen, hyperpigmentation, hypopigmentation up to early stages of geographical atrophy. Current high-resolution imaging technologies enable an accurate detection and description of anatomical features, such as drusen volumes, hyperreflexive foci and photoreceptor degeneration, which are risk factors that are decisive for prediction of the course of the disease; however, the manual annotation of these features in complex optical coherence tomography (OCT) scans is impractical for the routine clinical practice and research. In this context AI provides a solution by fully automatic segmentation and therefore delivers exact, reproducible and quantitative analyses of AMD-related biomarkers. Furthermore, the application of AI in iAMD facilitates the risk assessment and the development of structural endpoints for new forms of treatment. For example, the quantitative analysis of drusen volume and hyperreflective foci with AI algorithms has shown a correlation with the progression of the disease. These technological advances therefore improve not only the diagnostic precision but also support future targeted treatment strategies and contribute to the prioritized target of personalized medicine in the diagnostics and treatment of AMD.
Collapse
Affiliation(s)
- Leon von der Emde
- Augenklinik, Universitätsklinikum Bonn, Venusberg-Campus 1, 53127, Bonn, Deutschland.
| | - Sandrine H Künzel
- Augenklinik, Universitätsklinikum Bonn, Venusberg-Campus 1, 53127, Bonn, Deutschland
| | - Maximilian Pfau
- Institut für Molekulare und Klinische Ophthalmologie Basel, Basel, Schweiz
| | - Olivier Morelle
- Institut für Informatik 2, visual computing, Universität Bonn, Bonn, Deutschland
| | - Yannick Liermann
- Augenklinik, Universitätsklinikum Bonn, Venusberg-Campus 1, 53127, Bonn, Deutschland
| | - Petrus Chang
- Augenklinik, Universitätsklinikum Bonn, Venusberg-Campus 1, 53127, Bonn, Deutschland
| | - Kristina Pfau
- Institut für Molekulare und Klinische Ophthalmologie Basel, Basel, Schweiz
| | - Sarah Thiele
- Augenklinik, Universitätsklinikum Bonn, Venusberg-Campus 1, 53127, Bonn, Deutschland
- Klinik für Augenheilkunde, Universitätsklinikum Hamburg-Eppendorf, Hamburg, Deutschland
| | - Frank G Holz
- Augenklinik, Universitätsklinikum Bonn, Venusberg-Campus 1, 53127, Bonn, Deutschland
| |
Collapse
|
8
|
Frank S, Reiter GS, Leingang O, Fuchs P, Coulibaly LM, Mares V, Bogunovic H, Schmidt-Erfurth U. ADVANCES IN PHOTORECEPTOR AND RETINAL PIGMENT EPITHELIUM QUANTIFICATIONS IN INTERMEDIATE AGE-RELATED MACULAR DEGENERATION: High-Res Versus Standard SPECTRALIS Optical Coherence Tomography. Retina 2024; 44:1351-1359. [PMID: 39047196 PMCID: PMC11280440 DOI: 10.1097/iae.0000000000004118] [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] [Indexed: 07/27/2024]
Abstract
PURPOSE In this study, differences in retinal feature visualization of high-resolution optical coherence tomography (OCT) devices were investigated with different axial resolutions in quantifications of retinal pigment epithelium and photoreceptors (PRs) in intermediate age-related macular degeneration. METHODS Patients were imaged with standard SPECTRALIS HRA + OCT and the investigational High-Res OCT device (both by Heidelberg Engineering, Heidelberg, Germany). Drusen, retinal pigment epithelium, and PR layers were segmented using validated artificial intelligence-based algorithms followed by manual corrections. Thickness and drusen maps were computed for all patients. Loss and thickness measurements were compared between devices, drusen versus nondrusen areas, and early treatment diabetic retinopathy study subfields using mixed-effects models. RESULTS Thirty-three eyes from 28 patients with intermediate age-related macular degeneration were included. Normalized PR integrity loss was significantly higher with 4.6% for standard OCT compared with 2.5% for High-Res OCT. The central and parafoveal PR integrity loss was larger than the perifoveal loss (P < 0.05). Photoreceptor thickness was increased on High-Res OCT and in nondrusen regions (P < 0.001). Retinal pigment epithelium appeared thicker on standard OCT and above drusen (P < 0.01). CONCLUSION Our study shows that High-Res OCT is able to identify the condition of investigated layers in intermediate age-related macular degeneration with higher precision. This improved in vivo imaging technology might promote our understanding of the pathophysiology and progression of age-related macular degeneration.
Collapse
Affiliation(s)
- Sophie Frank
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria;
| | - Gregor Sebastian Reiter
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria;
| | - Oliver Leingang
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria;
| | - Philipp Fuchs
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria;
| | - Leonard Mana Coulibaly
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria;
| | - Virginia Mares
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria;
- Department of Ophthalmology, Federal University of Minas Gerais, Belo Horizonte, Brazil; and
| | - Hrvoje Bogunovic
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria;
- Christian Doppler Lab for Artificial Intelligence in Retina, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria.
| | - Ursula Schmidt-Erfurth
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology, Medical University of Vienna, Vienna, Austria;
| |
Collapse
|
9
|
Asani B, Holmberg O, Schiefelbein JB, Hafner M, Herold T, Spitzer H, Siedlecki J, Kern C, Kortuem KU, Frishberg A, Theis FJ, Priglinger SG. Evaluation of OCT biomarker changes in treatment-naive neovascular AMD using a deep semantic segmentation algorithm. Eye (Lond) 2024:10.1038/s41433-024-03264-1. [PMID: 39068248 DOI: 10.1038/s41433-024-03264-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2023] [Revised: 06/28/2024] [Accepted: 07/16/2024] [Indexed: 07/30/2024] Open
Abstract
OBJECTIVES To determine real-life quantitative changes in OCT biomarkers in a large set of treatment naive patients in a real-life setting undergoing anti-VEGF therapy. For this purpose, we devised a novel deep learning based semantic segmentation algorithm providing the first benchmark results for automatic segmentation of 11 OCT features including biomarkers for neovascular age-related macular degeneration (nAMD). METHODS Training of a Deep U-net based semantic segmentation ensemble algorithm for state-of-the-art semantic segmentation performance which was used to analyze OCT features prior to, after 3 and 12 months of anti-VEGF therapy. RESULTS High F1 scores of almost 1.0 for neurosensory retina and subretinal fluid on a separate hold-out test set with unseen patients. The algorithm performed worse for subretinal hyperreflective material and fibrovascular PED, on par with drusenoid PED, and better in segmenting fibrosis. In the evaluation of treatment naive OCT scans, significant changes occurred for intraretinal fluid (mean: 0.03 µm3 to 0.01 µm3, p < 0.001), subretinal fluid (0.08 µm3 to 0.01 µm3, p < 0.001), subretinal hyperreflective material (0.02 µm3 to 0.01 µm3, p < 0.001), fibrovascular PED (0.12 µm3 to 0.09 µm3, p = 0.02) and central retinal thickness C0 (225.78 µm3 to 169.40 µm3). The amounts of intraretinal fluid, fibrovascular PED, and ERM were predictive of poor outcome. CONCLUSIONS The segmentation algorithm allows efficient volumetric analysis of OCT scans. Anti-VEGF provokes most potent changes in the first 3 months while a gradual loss of RPE hints at a progressing decline of visual acuity. Additional research is required to understand how these accurate OCT predictions can be leveraged for a personalized therapy regimen.
Collapse
Affiliation(s)
- Ben Asani
- Department of Ophthalmology, Ludwig-Maximilians-University, Munich, Germany.
| | - Olle Holmberg
- Institute of Computational Biology, Helmholtz Centre Munich, Munich, Germany
| | | | - Michael Hafner
- Department of Ophthalmology, Ludwig-Maximilians-University, Munich, Germany
| | - Tina Herold
- Department of Ophthalmology, Ludwig-Maximilians-University, Munich, Germany
| | - Hannah Spitzer
- Institute of Computational Biology, Helmholtz Centre Munich, Munich, Germany
| | - Jakob Siedlecki
- Department of Ophthalmology, Ludwig-Maximilians-University, Munich, Germany
| | - Christoph Kern
- Department of Ophthalmology, Ludwig-Maximilians-University, Munich, Germany
| | | | - Amit Frishberg
- Institute of Computational Biology, Helmholtz Centre Munich, Munich, Germany
| | - Fabian J Theis
- Institute of Computational Biology, Helmholtz Centre Munich, Munich, Germany
- Department of Mathematics, TU Munich, Munich, Germany
| | | |
Collapse
|
10
|
Talcott KE, Baxter SL, Chen DK, Korot E, Lee A, Kim JE, Modi Y, Moshfeghi DM, Singh RP. American Society of Retina Specialists Artificial Intelligence Task Force Report. JOURNAL OF VITREORETINAL DISEASES 2024; 8:373-380. [PMID: 39148579 PMCID: PMC11323512 DOI: 10.1177/24741264241247602] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/17/2024]
Abstract
Since the Artificial Intelligence Committee of the American Society of Retina Specialists developed the initial task force report in 2020, the artificial intelligence (AI) field has seen further adoption of US Food and Drug Administration-approved AI platforms and significant development of AI for various retinal conditions. With expansion of this technology comes further areas of challenges, including the data sources used in AI, the democracy of AI, commercialization, bias, and the need for provider education on the technology of AI. The overall focus of this committee report is to explore these recent issues as they relate to the continued development of AI and its integration into ophthalmology and retinal practice.
Collapse
Affiliation(s)
- Katherine E. Talcott
- Center for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic Foundation, Cleveland, OH, USA
- Cleveland Clinic Lerner College of Medicine, Cleveland, OH, USA
| | - Sally L. Baxter
- Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, La Jolla, CA, USA
- Division of Biomedical Informatics, Department of Medicine, University of California San Diego, La Jolla, CA, USA
| | - Dinah K. Chen
- Department of Ophthalmology, NYU Grossman School of Medicine, New York University, NY, USA
- Genentech/Roche, South San Francisco, CA, USA
| | - Edward Korot
- Retina Specialists of Michigan, Grand Rapids, MI, USA
- Horngren Family Vitreoretinal Center, Byers Eye Institute, Department of Ophthalmology, Stanford University School of Medicine, Palo Alto, CA, USA
| | - Aaron Lee
- Roger and Angie Karalis Johnson Retina Center, Department of Ophthalmology, School of Medicine, University of Washington, Seattle, WA, USA
| | - Judy E. Kim
- Department of Ophthalmology and Visual Sciences, Medical College of Wisconsin, Milwaukee, WI, USA
| | - Yasha Modi
- Department of Ophthalmology, NYU Grossman School of Medicine, New York University, NY, USA
| | - Darius M. Moshfeghi
- Horngren Family Vitreoretinal Center, Byers Eye Institute, Department of Ophthalmology, Stanford University School of Medicine, Palo Alto, CA, USA
| | - Rishi P. Singh
- Center for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic Foundation, Cleveland, OH, USA
- Cleveland Clinic Lerner College of Medicine, Cleveland, OH, USA
- Cleveland Clinic Martin Health, Stuart, FL, USA
| |
Collapse
|
11
|
Riedl S, Schmidt-Erfurth U, Rivail A, Birner K, Mai J, Vogl WD, Wu Z, Guymer RH, Bogunović H, Reiter GS. Sequence of Morphological Changes Preceding Atrophy in Intermediate AMD Using Deep Learning. Invest Ophthalmol Vis Sci 2024; 65:30. [PMID: 39028907 PMCID: PMC11262471 DOI: 10.1167/iovs.65.8.30] [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: 12/05/2023] [Accepted: 06/24/2024] [Indexed: 07/21/2024] Open
Abstract
Purpose Investigating the sequence of morphological changes preceding outer plexiform layer (OPL) subsidence, a marker preceding geographic atrophy, in intermediate AMD (iAMD) using high-precision artificial intelligence (AI) quantifications on optical coherence tomography imaging. Methods In this longitudinal observational study, individuals with bilateral iAMD participating in a multicenter clinical trial were screened for OPL subsidence and RPE and outer retinal atrophy. OPL subsidence was segmented on an A-scan basis in optical coherence tomography volumes, obtained 6-monthly with 36 months follow-up. AI-based quantification of photoreceptor (PR) and outer nuclear layer (ONL) thickness, drusen height and choroidal hypertransmission (HT) was performed. Changes were compared between topographic areas of OPL subsidence (AS), drusen (AD), and reference (AR). Results Of 280 eyes of 140 individuals, OPL subsidence occurred in 53 eyes from 43 individuals. Thirty-six eyes developed RPE and outer retinal atrophy subsequently. In the cohort of 53 eyes showing OPL subsidence, PR and ONL thicknesses were significantly decreased in AS compared with AD and AR 12 and 18 months before OPL subsidence occurred, respectively (PR: 20 µm vs. 23 µm and 27 µm [P < 0.009]; ONL, 84 µm vs. 94 µm and 98 µm [P < 0.008]). Accelerated thinning of PR (0.6 µm/month; P < 0.001) and ONL (0.8 µm/month; P < 0.001) was observed in AS compared with AD and AR. Concomitant drusen regression and hypertransmission increase at the occurrence of OPL subsidence underline the atrophic progress in areas affected by OPL subsidence. Conclusions PR and ONL thinning are early subclinical features associated with subsequent OPL subsidence, an indicator of progression toward geographic atrophy. AI algorithms are able to predict and quantify morphological precursors of iAMD conversion and allow personalized risk stratification.
Collapse
Affiliation(s)
- Sophie Riedl
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Ursula Schmidt-Erfurth
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Antoine Rivail
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Klaudia Birner
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Julia Mai
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Wolf-Dieter Vogl
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
- RetInSight, Vienna, Austria
| | - Zhichao Wu
- Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Australia
- Department of Surgery (Ophthalmology), The University of Melbourne, Melbourne, Australia
| | - Robyn H. Guymer
- Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Australia
- Department of Surgery (Ophthalmology), The University of Melbourne, Melbourne, Australia
| | - Hrvoje Bogunović
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Gregor S. Reiter
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| |
Collapse
|
12
|
Fragiotta S, Dysli C, Parravano M, Sacconi R, Fantaguzzi F, Servillo A, Severo AA, Tombolini B, Costanzo E, De Geronimo D, Capuano V, Souied E, Bandello F, Querques G. PHENOTYPIC CHARACTERIZATION OF PREDICTORS FOR DEVELOPMENT AND PROGRESSION OF GEOGRAPHIC ATROPHY USING OPTICAL COHERENCE TOMOGRAPHY. Retina 2024; 44:1232-1241. [PMID: 38471039 DOI: 10.1097/iae.0000000000004090] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/14/2024]
Abstract
PURPOSE To evaluate the impact of optical coherence tomography phenotypes preceding atrophy related to age-related macular degeneration on the progression of atrophic lesions. METHODS In this observational retrospective cohort study, a total of 70 eyes of 60 consecutive patients with intermediate age-related macular degeneration with a minimum follow-up of 24 months were included. The atrophy was quantified using fundus autofluorescence, also considering the directionality of atrophy as centrifugal and centripetal progression rates. The main outcome measures were geographic atrophy (GA) progression rate (mm 2 /year) and square root transformation of GA (mm 2 /year). RESULTS The best-fit model for GA (odds ratio: 1.81, P < 0.001) and square root transformation of GA (odds ratio: 1.36, P < 0.001) areas revealed that the main baseline predictor was the presence of a retinal pigment epithelium-basal lamina-Bruch membrane splitting. Large drusen at baseline appeared protective for the GA area lesion expansion over time (odds ratio: 0.52, P < 0.001) when considered with other confounders. CONCLUSION A thin retinal pigment epithelium-basal lamina-Bruch membrane splitting without evidence of neovascularization on optical coherence tomography angiography likely represents an optical coherence tomography signature for late basal laminar deposits. Identifying this phenotype can help identify individuals with a higher risk of rapid progression and atrophy expansion.
Collapse
Affiliation(s)
- Serena Fragiotta
- Ophthalmology Unit, "Sapienza" University of Rome, NESMOS Department, St. Andrea Hospital, Rome, Italy
| | - Chantal Dysli
- Department of Ophthalmology, Inselspital, Bern University Hospital and Department of BioMedical Research, University of Bern, Bern, Switzerland
| | | | - Riccardo Sacconi
- Department of Ophthalmology, IRCCS Ospedale San Raffaele, University Vita-Salute, Milan, Italy; and
| | - Federico Fantaguzzi
- Department of Ophthalmology, IRCCS Ospedale San Raffaele, University Vita-Salute, Milan, Italy; and
| | - Andrea Servillo
- Department of Ophthalmology, IRCCS Ospedale San Raffaele, University Vita-Salute, Milan, Italy; and
| | - Alice Antonella Severo
- Department of Ophthalmology, IRCCS Ospedale San Raffaele, University Vita-Salute, Milan, Italy; and
| | - Beatrice Tombolini
- Department of Ophthalmology, IRCCS Ospedale San Raffaele, University Vita-Salute, Milan, Italy; and
| | | | - Daniele De Geronimo
- Department of Ophthalmology, IRCCS Ospedale San Raffaele, University Vita-Salute, Milan, Italy; and
| | - Vittorio Capuano
- Ophthalmology, Centre Hospitalier Intercommunal De Creteil, Creteil, France
| | - Eric Souied
- Ophthalmology, Centre Hospitalier Intercommunal De Creteil, Creteil, France
| | - Francesco Bandello
- Department of Ophthalmology, IRCCS Ospedale San Raffaele, University Vita-Salute, Milan, Italy; and
| | - Giuseppe Querques
- Department of Ophthalmology, IRCCS Ospedale San Raffaele, University Vita-Salute, Milan, Italy; and
| |
Collapse
|
13
|
Sorrentino FS, Gardini L, Fontana L, Musa M, Gabai A, Maniaci A, Lavalle S, D’Esposito F, Russo A, Longo A, Surico PL, Gagliano C, Zeppieri M. Novel Approaches for Early Detection of Retinal Diseases Using Artificial Intelligence. J Pers Med 2024; 14:690. [PMID: 39063944 PMCID: PMC11278069 DOI: 10.3390/jpm14070690] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2024] [Revised: 06/24/2024] [Accepted: 06/25/2024] [Indexed: 07/28/2024] Open
Abstract
BACKGROUND An increasing amount of people are globally affected by retinal diseases, such as diabetes, vascular occlusions, maculopathy, alterations of systemic circulation, and metabolic syndrome. AIM This review will discuss novel technologies in and potential approaches to the detection and diagnosis of retinal diseases with the support of cutting-edge machines and artificial intelligence (AI). METHODS The demand for retinal diagnostic imaging exams has increased, but the number of eye physicians or technicians is too little to meet the request. Thus, algorithms based on AI have been used, representing valid support for early detection and helping doctors to give diagnoses and make differential diagnosis. AI helps patients living far from hub centers to have tests and quick initial diagnosis, allowing them not to waste time in movements and waiting time for medical reply. RESULTS Highly automated systems for screening, early diagnosis, grading and tailored therapy will facilitate the care of people, even in remote lands or countries. CONCLUSION A potential massive and extensive use of AI might optimize the automated detection of tiny retinal alterations, allowing eye doctors to perform their best clinical assistance and to set the best options for the treatment of retinal diseases.
Collapse
Affiliation(s)
| | - Lorenzo Gardini
- Unit of Ophthalmology, Department of Surgical Sciences, Ospedale Maggiore, 40100 Bologna, Italy; (F.S.S.)
| | - Luigi Fontana
- Ophthalmology Unit, Department of Surgical Sciences, Alma Mater Studiorum University of Bologna, IRCCS Azienda Ospedaliero-Universitaria Bologna, 40100 Bologna, Italy
| | - Mutali Musa
- Department of Optometry, University of Benin, Benin City 300238, Edo State, Nigeria
| | - Andrea Gabai
- Department of Ophthalmology, Humanitas-San Pio X, 20159 Milan, Italy
| | - Antonino Maniaci
- Department of Medicine and Surgery, University of Enna “Kore”, Piazza dell’Università, 94100 Enna, Italy
| | - Salvatore Lavalle
- Department of Medicine and Surgery, University of Enna “Kore”, Piazza dell’Università, 94100 Enna, Italy
| | - Fabiana D’Esposito
- Imperial College Ophthalmic Research Group (ICORG) Unit, Imperial College, 153-173 Marylebone Rd, London NW15QH, UK
- Department of Neurosciences, Reproductive Sciences and Dentistry, University of Naples Federico II, Via Pansini 5, 80131 Napoli, Italy
| | - Andrea Russo
- Department of Ophthalmology, University of Catania, 95123 Catania, Italy
| | - Antonio Longo
- Department of Ophthalmology, University of Catania, 95123 Catania, Italy
| | - Pier Luigi Surico
- Schepens Eye Research Institute of Mass Eye and Ear, Harvard Medical School, Boston, MA 02114, USA
- Department of Ophthalmology, Campus Bio-Medico University, 00128 Rome, Italy
| | - Caterina Gagliano
- Department of Medicine and Surgery, University of Enna “Kore”, Piazza dell’Università, 94100 Enna, Italy
- Eye Clinic, Catania University, San Marco Hospital, Viale Carlo Azeglio Ciampi, 95121 Catania, Italy
| | - Marco Zeppieri
- Department of Ophthalmology, University Hospital of Udine, 33100 Udine, Italy
| |
Collapse
|
14
|
Borrelli E, Serafino S, Ricardi F, Coletto A, Neri G, Olivieri C, Ulla L, Foti C, Marolo P, Toro MD, Bandello F, Reibaldi M. Deep Learning in Neovascular Age-Related Macular Degeneration. MEDICINA (KAUNAS, LITHUANIA) 2024; 60:990. [PMID: 38929607 PMCID: PMC11205843 DOI: 10.3390/medicina60060990] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/17/2024] [Revised: 05/29/2024] [Accepted: 06/13/2024] [Indexed: 06/28/2024]
Abstract
Background and objectives: Age-related macular degeneration (AMD) is a complex and multifactorial condition that can lead to permanent vision loss once it progresses to the neovascular exudative stage. This review aims to summarize the use of deep learning in neovascular AMD. Materials and Methods: Pubmed search. Results: Deep learning has demonstrated effectiveness in analyzing structural OCT images in patients with neovascular AMD. This review outlines the role of deep learning in identifying and measuring biomarkers linked to an elevated risk of transitioning to the neovascular form of AMD. Additionally, deep learning techniques can quantify critical OCT features associated with neovascular AMD, which have prognostic implications for these patients. Incorporating deep learning into the assessment of neovascular AMD eyes holds promise for enhancing clinical management strategies for affected individuals. Conclusion: Several studies have demonstrated effectiveness of deep learning in assessing neovascular AMD patients and this has a promising role in the assessment of these patients.
Collapse
Affiliation(s)
- Enrico Borrelli
- Division of Ophthalmology, Department of Surgical Sciences, University of Turin, Via Verdi, 8, 10124 Turin, Italy; (S.S.); (F.R.); (A.C.); (G.N.); (C.O.); (L.U.); (C.F.); (M.R.)
- Department of Ophthalmology, “City of Health and Science” Hospital, 10126 Turin, Italy
| | - Sonia Serafino
- Division of Ophthalmology, Department of Surgical Sciences, University of Turin, Via Verdi, 8, 10124 Turin, Italy; (S.S.); (F.R.); (A.C.); (G.N.); (C.O.); (L.U.); (C.F.); (M.R.)
- Department of Ophthalmology, “City of Health and Science” Hospital, 10126 Turin, Italy
| | - Federico Ricardi
- Division of Ophthalmology, Department of Surgical Sciences, University of Turin, Via Verdi, 8, 10124 Turin, Italy; (S.S.); (F.R.); (A.C.); (G.N.); (C.O.); (L.U.); (C.F.); (M.R.)
- Department of Ophthalmology, “City of Health and Science” Hospital, 10126 Turin, Italy
| | - Andrea Coletto
- Division of Ophthalmology, Department of Surgical Sciences, University of Turin, Via Verdi, 8, 10124 Turin, Italy; (S.S.); (F.R.); (A.C.); (G.N.); (C.O.); (L.U.); (C.F.); (M.R.)
- Department of Ophthalmology, “City of Health and Science” Hospital, 10126 Turin, Italy
| | - Giovanni Neri
- Division of Ophthalmology, Department of Surgical Sciences, University of Turin, Via Verdi, 8, 10124 Turin, Italy; (S.S.); (F.R.); (A.C.); (G.N.); (C.O.); (L.U.); (C.F.); (M.R.)
- Department of Ophthalmology, “City of Health and Science” Hospital, 10126 Turin, Italy
| | - Chiara Olivieri
- Division of Ophthalmology, Department of Surgical Sciences, University of Turin, Via Verdi, 8, 10124 Turin, Italy; (S.S.); (F.R.); (A.C.); (G.N.); (C.O.); (L.U.); (C.F.); (M.R.)
- Department of Ophthalmology, “City of Health and Science” Hospital, 10126 Turin, Italy
| | - Lorena Ulla
- Division of Ophthalmology, Department of Surgical Sciences, University of Turin, Via Verdi, 8, 10124 Turin, Italy; (S.S.); (F.R.); (A.C.); (G.N.); (C.O.); (L.U.); (C.F.); (M.R.)
- Department of Ophthalmology, “City of Health and Science” Hospital, 10126 Turin, Italy
| | - Claudio Foti
- Division of Ophthalmology, Department of Surgical Sciences, University of Turin, Via Verdi, 8, 10124 Turin, Italy; (S.S.); (F.R.); (A.C.); (G.N.); (C.O.); (L.U.); (C.F.); (M.R.)
- Department of Ophthalmology, “City of Health and Science” Hospital, 10126 Turin, Italy
| | - Paola Marolo
- Division of Ophthalmology, Department of Surgical Sciences, University of Turin, Via Verdi, 8, 10124 Turin, Italy; (S.S.); (F.R.); (A.C.); (G.N.); (C.O.); (L.U.); (C.F.); (M.R.)
- Department of Ophthalmology, “City of Health and Science” Hospital, 10126 Turin, Italy
| | - Mario Damiano Toro
- Eye Clinic, Public Health Department, University of Naples Federico II, 80138 Naples, Italy;
| | - Francesco Bandello
- Department of Ophthalmology, Vita-Salute San Raffaele University, 20132 Milan, Italy;
- IRCCS San Raffaele Scientific Institute, 20132 Milan, Italy
| | - Michele Reibaldi
- Division of Ophthalmology, Department of Surgical Sciences, University of Turin, Via Verdi, 8, 10124 Turin, Italy; (S.S.); (F.R.); (A.C.); (G.N.); (C.O.); (L.U.); (C.F.); (M.R.)
- Department of Ophthalmology, “City of Health and Science” Hospital, 10126 Turin, Italy
| |
Collapse
|
15
|
Kurzawa-Akanbi M, Tzoumas N, Corral-Serrano JC, Guarascio R, Steel DH, Cheetham ME, Armstrong L, Lako M. Pluripotent stem cell-derived models of retinal disease: Elucidating pathogenesis, evaluating novel treatments, and estimating toxicity. Prog Retin Eye Res 2024; 100:101248. [PMID: 38369182 DOI: 10.1016/j.preteyeres.2024.101248] [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: 12/07/2023] [Revised: 02/13/2024] [Accepted: 02/14/2024] [Indexed: 02/20/2024]
Abstract
Blindness poses a growing global challenge, with approximately 26% of cases attributed to degenerative retinal diseases. While gene therapy, optogenetic tools, photosensitive switches, and retinal prostheses offer hope for vision restoration, these high-cost therapies will benefit few patients. Understanding retinal diseases is therefore key to advance effective treatments, requiring in vitro models replicating pathology and allowing quantitative assessments for drug discovery. Pluripotent stem cells (PSCs) provide a unique solution given their limitless supply and ability to differentiate into light-responsive retinal tissues encompassing all cell types. This review focuses on the history and current state of photoreceptor and retinal pigment epithelium (RPE) cell generation from PSCs. We explore the applications of this technology in disease modelling, experimental therapy testing, biomarker identification, and toxicity studies. We consider challenges in scalability, standardisation, and reproducibility, and stress the importance of incorporating vasculature and immune cells into retinal organoids. We advocate for high-throughput automation in data acquisition and analyses and underscore the value of advanced micro-physiological systems that fully capture the interactions between the neural retina, RPE, and choriocapillaris.
Collapse
|
16
|
Verma A, Nittala MG, Corradetti G, Nassisi M, Velaga SB, He Y, Haines JL, Pericak-Vance MA, Stambolian D, Sadda SR. Longitudinal Evaluation of the Distribution of Intraretinal Hyper-Reflective Foci in Eyes with Intermediate Age-Related Macular Degeneration. Curr Eye Res 2024:1-7. [PMID: 38639042 DOI: 10.1080/02713683.2024.2343334] [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: 11/20/2023] [Accepted: 04/09/2024] [Indexed: 04/20/2024]
Abstract
PURPOSE Intraretinal hyper-reflective foci (IHRF) are optical coherence tomography (OCT) risk factors for progression of age-related macular degeneration (AMD). In this study we assess the change in the number and distribution of IHRF over two years. METHODS The axial distribution of IHRF were quantified in eyes with intermediate AMD (iAMD) at baseline and 24 months, using a series of 5 sequential equidistant en face OCT retinal slabs generated between the outer border of the internal limiting membrane (ILM) and the inner border of the retinal pigment epithelium (RPE). Following thresholding and binarization, IHRF were quantified in each retinal slab using ImageJ. The change in IHRF number in each slab between baseline and month 24 was calculated. RESULTS Fifty-two eyes showed evidence of IHRF at baseline, and all continued to show evidence of IHRF at 24 months (M24). The total average IHRF count/eye increased significantly from 4.67 ± 0.63 at baseline to 11.62 ± 13.86 at M24 (p < 0.001) with a mean increase of 6.94 ± 11.12 (range: - 9 to + 60). Overall, at M24, 76.9% eyes showed an increase in IHRF whereas 15.4% of eyes showed a decrease (3 eyes [5.7%] showed no change). There was a greater number of IHRF and a greater increase in IHRF over M24 in the outer slabs. CONCLUSIONS IHRF are most common in the outer retinal layers and tend to increase in number over time. The impact of the distribution and frequency of these IHRF on the overall progression of AMD requires further study.
Collapse
Affiliation(s)
- Aditya Verma
- Doheny Eye Institute, Pasadena, CA, USA
- Department of Ophthalmology and Visual Sciences, University of Louisville, Louisville, KY, USA
| | | | - Giulia Corradetti
- Doheny Eye Institute, Pasadena, CA, USA
- Department of Ophthalmology, David Geffen School of Medicine at the University of California, Los Angeles, CA, USA
| | - Marco Nassisi
- Department of Clinical Sciences and Community Health, University of Milan, Milan, Italy
- Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico, Milan, Italy
| | | | - Ye He
- Doheny Eye Institute, Pasadena, CA, USA
- Department of Ophthalmology, David Geffen School of Medicine at the University of California, Los Angeles, CA, USA
- Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin Branch of National Clinical Research Center for Ocular Disease, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital, Tianjin, China
| | - Jonathan L Haines
- Department of Population & Quantitative Health Sciences and Cleveland Institute for Computational Biology, Case Western Reserve University, Cleveland, OH, USA
| | - Margaret A Pericak-Vance
- John P. Hussman Institute for Human Genomics, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Dwight Stambolian
- Department of Ophthalmology, University of Pennsylvania, Perelman School of Medicine, Philadelphia, PA, USA
| | - SriniVas R Sadda
- Doheny Eye Institute, Pasadena, CA, USA
- Department of Ophthalmology, David Geffen School of Medicine at the University of California, Los Angeles, CA, USA
| |
Collapse
|
17
|
Mares V, Nehemy MB, Bogunovic H, Frank S, Reiter GS, Schmidt-Erfurth U. AI-based support for optical coherence tomography in age-related macular degeneration. Int J Retina Vitreous 2024; 10:31. [PMID: 38589936 PMCID: PMC11000391 DOI: 10.1186/s40942-024-00549-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2024] [Accepted: 03/16/2024] [Indexed: 04/10/2024] Open
Abstract
Artificial intelligence (AI) has emerged as a transformative technology across various fields, and its applications in the medical domain, particularly in ophthalmology, has gained significant attention. The vast amount of high-resolution image data, such as optical coherence tomography (OCT) images, has been a driving force behind AI growth in this field. Age-related macular degeneration (AMD) is one of the leading causes for blindness in the world, affecting approximately 196 million people worldwide in 2020. Multimodal imaging has been for a long time the gold standard for diagnosing patients with AMD, however, currently treatment and follow-up in routine disease management are mainly driven by OCT imaging. AI-based algorithms have by their precision, reproducibility and speed, the potential to reliably quantify biomarkers, predict disease progression and assist treatment decisions in clinical routine as well as academic studies. This review paper aims to provide a summary of the current state of AI in AMD, focusing on its applications, challenges, and prospects.
Collapse
Affiliation(s)
- Virginia Mares
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
- Department of Ophthalmology, Federal University of Minas Gerais, Belo Horizonte, Brazil
| | - Marcio B Nehemy
- Department of Ophthalmology, Federal University of Minas Gerais, Belo Horizonte, Brazil
| | - Hrvoje Bogunovic
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - Sophie Frank
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - Gregor S Reiter
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - Ursula Schmidt-Erfurth
- Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria.
| |
Collapse
|
18
|
Liu D, Liu Z, Liao H, Chen ZS, Qin B. Ferroptosis as a potential therapeutic target for age-related macular degeneration. Drug Discov Today 2024; 29:103920. [PMID: 38369100 DOI: 10.1016/j.drudis.2024.103920] [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: 12/11/2023] [Revised: 02/11/2024] [Accepted: 02/14/2024] [Indexed: 02/20/2024]
Abstract
Cell death plays a crucial part in the process of age-related macular degeneration (AMD), but its mechanisms remain elusive. Accumulating evidence suggests that ferroptosis, a novel form of regulatory cell death characterized by iron-dependent accumulation of lipid hydroperoxides, has a crucial role in the pathogenesis of AMD. Numerous studies have suggested that ferroptosis participates in the degradation of retinal cells and accelerates the progression of AMD. Furthermore, inhibitors of ferroptosis exhibit notable protective effects in AMD, underscoring the significance of ferroptosis as a pivotal mechanism in the death of retinal cells during the process of AMD. This review aims to summarize the molecular mechanisms of ferroptosis in AMD, enumerate potential inhibitors and discuss the challenges and future opportunities associated with targeting ferroptosis as a therapeutic strategy, providing important information references and insights for the prevention and treatment of AMD.
Collapse
Affiliation(s)
- Dongcheng Liu
- Shenzhen Aier Eye Hospital, Aier Eye Hospital, Jinan University, Shenzhen, China; Shenzhen Aier Ophthalmic Technology Institute, Shenzhen, China
| | - Ziling Liu
- Shenzhen Aier Eye Hospital, Aier Eye Hospital, Jinan University, Shenzhen, China; Shenzhen Aier Ophthalmic Technology Institute, Shenzhen, China
| | - Hongxia Liao
- Shenzhen Aier Eye Hospital, Aier Eye Hospital, Jinan University, Shenzhen, China; Shenzhen Aier Ophthalmic Technology Institute, Shenzhen, China
| | - Zhe-Sheng Chen
- College of Pharmacy and Health Sciences, St. John's University, Queens, New York, USA.
| | - Bo Qin
- Shenzhen Aier Eye Hospital, Aier Eye Hospital, Jinan University, Shenzhen, China; Shenzhen Aier Ophthalmic Technology Institute, Shenzhen, China; Aier Eye Hospital, Tianjin University, Tianjin, China.
| |
Collapse
|
19
|
Parmar UPS, Surico PL, Singh RB, Romano F, Salati C, Spadea L, Musa M, Gagliano C, Mori T, Zeppieri M. Artificial Intelligence (AI) for Early Diagnosis of Retinal Diseases. MEDICINA (KAUNAS, LITHUANIA) 2024; 60:527. [PMID: 38674173 PMCID: PMC11052176 DOI: 10.3390/medicina60040527] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/27/2024] [Revised: 03/12/2024] [Accepted: 03/21/2024] [Indexed: 04/28/2024]
Abstract
Artificial intelligence (AI) has emerged as a transformative tool in the field of ophthalmology, revolutionizing disease diagnosis and management. This paper provides a comprehensive overview of AI applications in various retinal diseases, highlighting its potential to enhance screening efficiency, facilitate early diagnosis, and improve patient outcomes. Herein, we elucidate the fundamental concepts of AI, including machine learning (ML) and deep learning (DL), and their application in ophthalmology, underscoring the significance of AI-driven solutions in addressing the complexity and variability of retinal diseases. Furthermore, we delve into the specific applications of AI in retinal diseases such as diabetic retinopathy (DR), age-related macular degeneration (AMD), Macular Neovascularization, retinopathy of prematurity (ROP), retinal vein occlusion (RVO), hypertensive retinopathy (HR), Retinitis Pigmentosa, Stargardt disease, best vitelliform macular dystrophy, and sickle cell retinopathy. We focus on the current landscape of AI technologies, including various AI models, their performance metrics, and clinical implications. Furthermore, we aim to address challenges and pitfalls associated with the integration of AI in clinical practice, including the "black box phenomenon", biases in data representation, and limitations in comprehensive patient assessment. In conclusion, this review emphasizes the collaborative role of AI alongside healthcare professionals, advocating for a synergistic approach to healthcare delivery. It highlights the importance of leveraging AI to augment, rather than replace, human expertise, thereby maximizing its potential to revolutionize healthcare delivery, mitigate healthcare disparities, and improve patient outcomes in the evolving landscape of medicine.
Collapse
Affiliation(s)
| | - Pier Luigi Surico
- Massachusetts Eye and Ear, Department of Ophthalmology, Harvard Medical School, Boston, MA 02114, USA
- Department of Ophthalmology, Campus Bio-Medico University, 00128 Rome, Italy
- Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, Italy
| | - Rohan Bir Singh
- Massachusetts Eye and Ear, Department of Ophthalmology, Harvard Medical School, Boston, MA 02114, USA
| | - Francesco Romano
- Massachusetts Eye and Ear, Department of Ophthalmology, Harvard Medical School, Boston, MA 02114, USA
| | - Carlo Salati
- Department of Ophthalmology, University Hospital of Udine, p.le S. Maria della Misericordia 15, 33100 Udine, Italy
| | - Leopoldo Spadea
- Eye Clinic, Policlinico Umberto I, “Sapienza” University of Rome, 00142 Rome, Italy
| | - Mutali Musa
- Department of Optometry, University of Benin, Benin City 300238, Edo State, Nigeria
| | - Caterina Gagliano
- Faculty of Medicine and Surgery, University of Enna “Kore”, Piazza dell’Università, 94100 Enna, Italy
- Eye Clinic, Catania University, San Marco Hospital, Viale Carlo Azeglio Ciampi, 95121 Catania, Italy
| | - Tommaso Mori
- Department of Ophthalmology, Campus Bio-Medico University, 00128 Rome, Italy
- Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, Italy
- Department of Ophthalmology, University of California San Diego, La Jolla, CA 92122, USA
| | - Marco Zeppieri
- Department of Ophthalmology, University Hospital of Udine, p.le S. Maria della Misericordia 15, 33100 Udine, Italy
| |
Collapse
|
20
|
Sekimitsu S, Shweikh Y, Shareef S, Zhao Y, Elze T, Segrè A, Wiggs J, Zebardast N. Association of retinal optical coherence tomography metrics and polygenic risk scores with cognitive function and future cognitive decline. Br J Ophthalmol 2024; 108:599-606. [PMID: 36990674 DOI: 10.1136/bjo-2022-322762] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2022] [Accepted: 03/15/2023] [Indexed: 03/31/2023]
Abstract
PURPOSE To evaluate the potential of retinal optical coherence tomography (OCT) measurements and polygenic risk scores (PRS) to identify people at risk of cognitive impairment. METHODS Using OCT images from 50 342 UK Biobank participants, we examined associations between retinal layer thickness and genetic risk for neurodegenerative disease and combined these metrics with PRS to predict baseline cognitive function and future cognitive deterioration. Multivariate Cox proportional hazard models were used to predict cognitive performance. P values for retinal thickness analyses are false-discovery-rate-adjusted. RESULTS Higher Alzheimer's disease PRS was associated with a thicker inner nuclear layer (INL), chorio-scleral interface (CSI) and inner plexiform layer (IPL) (all p<0.05). Higher Parkinson's disease PRS was associated with thinner outer plexiform layer (p<0.001). Worse baseline cognitive performance was associated with thinner retinal nerve fibre layer (RNFL) (aOR=1.038, 95% CI (1.029 to 1.047), p<0.001) and photoreceptor (PR) segment (aOR=1.035, 95% CI (1.019 to 1.051), p<0.001), ganglion cell complex (aOR=1.007, 95% CI (1.002 to 1.013), p=0.004) and thicker ganglion cell layer (aOR=0.981, 95% CI (0.967 to 0.995), p=0.009), IPL (aOR=0.976, 95% CI (0.961 to 0.992), p=0.003), INL (aOR=0.923, 95% CI (0.905 to 0.941), p<0.001) and CSI (aOR=0.998, 95% CI (0.997 to 0.999), p<0.001). Worse future cognitive performance was associated with thicker IPL (aOR=0.945, 95% CI (0.915 to 0.999), p=0.045) and CSI (aOR=0.996, 95% CI (0.993 to 0.999) 95% CI, p=0.014). Prediction of cognitive decline was significantly improved with the addition of PRS and retinal measurements. CONCLUSIONS AND RELEVANCE Retinal OCT measurements are significantly associated with genetic risk of neurodegenerative disease and may serve as biomarkers predictive of future cognitive impairment.
Collapse
Affiliation(s)
| | - Yusrah Shweikh
- Department of Ophthalmology, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
- Sussex Eye Hospital, University Hospitals Sussex NHS Foundation Trust, Sussex, UK
| | - Sarah Shareef
- Department of Ophthalmology, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
| | - Yan Zhao
- Department of Ophthalmology, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
- Broad Institute of Harvard and MIT, Cambridge, Massachusetts, USA
| | - Tobias Elze
- Schepens Eye Research Institute, Harvard Medical School, Boston, Massachusetts, USA
| | - Ayellet Segrè
- Department of Ophthalmology, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
- Broad Institute of Harvard and MIT, Cambridge, Massachusetts, USA
| | - Janey Wiggs
- Department of Ophthalmology, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
- Broad Institute of Harvard and MIT, Cambridge, Massachusetts, USA
| | - Nazlee Zebardast
- Department of Ophthalmology, Massachusetts Eye and Ear Infirmary, Boston, Massachusetts, USA
| |
Collapse
|
21
|
Crincoli E, Sacconi R, Querques L, Querques G. Artificial intelligence in age-related macular degeneration: state of the art and recent updates. BMC Ophthalmol 2024; 24:121. [PMID: 38491380 PMCID: PMC10943791 DOI: 10.1186/s12886-024-03381-1] [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: 12/05/2023] [Accepted: 03/06/2024] [Indexed: 03/18/2024] Open
Abstract
Age related macular degeneration (AMD) represents a leading cause of vision loss and it is expected to affect 288 million people by 2040. During the last decade, machine learning technologies have shown great potential to revolutionize clinical management of AMD and support research for a better understanding of the disease. The aim of this review is to provide a panoramic description of all the applications of AI to AMD management and screening that have been analyzed in recent past literature. Deep learning (DL) can be effectively used to diagnose AMD, to predict short term risk of exudation and need for injections within the next 2 years. Moreover, DL technology has the potential to customize anti-VEGF treatment choice with a higher accuracy than expert human experts. In addition, accurate prediction of VA response to treatment can be provided to the patients with the use of ML models, which could considerably increase patients' compliance to treatment in favorable cases. Lastly, AI, especially in the form of DL, can effectively predict conversion to GA in 12 months and also suggest new biomarkers of conversion with an innovative reverse engineering approach.
Collapse
Affiliation(s)
- Emanuele Crincoli
- Ophthalmology Unit, "Fondazione Policlinico Universitario A. Gemelli IRCCS", Rome, Italy
| | - Riccardo Sacconi
- Department of Ophthalmology, University Vita-Salute IRCCS San Raffaele Scientific Institute, Via Olgettina, 60, 20132, Milan, Italy
| | - Lea Querques
- Department of Ophthalmology, University Vita-Salute IRCCS San Raffaele Scientific Institute, Via Olgettina, 60, 20132, Milan, Italy
| | - Giuseppe Querques
- Department of Ophthalmology, University Vita-Salute IRCCS San Raffaele Scientific Institute, Via Olgettina, 60, 20132, Milan, Italy.
| |
Collapse
|
22
|
Hagag AM, Kaye R, Hoang V, Riedl S, Anders P, Stuart B, Traber G, Appenzeller-Herzog C, Schmidt-Erfurth U, Bogunovic H, Scholl HP, Prevost T, Fritsche L, Rueckert D, Sivaprasad S, Lotery AJ. Systematic review of prognostic factors associated with progression to late age-related macular degeneration: Pinnacle study report 2. Surv Ophthalmol 2024; 69:165-172. [PMID: 37890677 DOI: 10.1016/j.survophthal.2023.10.010] [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: 04/05/2023] [Revised: 10/18/2023] [Accepted: 10/23/2023] [Indexed: 10/29/2023]
Abstract
There is a need to identify accurately prognostic factors that determine the progression of intermediate to late-stage age-related macular degeneration (AMD). Currently, clinicians cannot provide individualised prognoses of disease progression. Moreover, enriching clinical trials with rapid progressors may facilitate delivery of shorter intervention trials aimed at delaying or preventing progression to late AMD. Thus, we performed a systematic review to outline and assess the accuracy of reporting prognostic factors for the progression of intermediate to late AMD. A meta-analysis was originally planned. Synonyms of AMD and disease progression were used to search Medline and EMBASE for articles investigating AMD progression published between 1991 and 2021. Initial search results included 3229 articles. Predetermined eligibility criteria were employed to systematically screen papers by two reviewers working independently and in duplicate. Quality appraisal and data extraction were performed by a team of reviewers. Only 6 studies met the eligibility criteria. Based on these articles, exploratory prognostic factors for progression of intermediate to late AMD included phenotypic features (e.g. location and size of drusen), age, smoking status, ocular and systemic co-morbidities, race, and genotype. Overall, study heterogeneity precluded reporting by forest plots and meta-analysis. The most commonly reported prognostic factors were baseline drusen volume/size, which was associated with progression to neovascular AMD, and outer retinal thinning linked to progression to geographic atrophy. In conclusion, poor methodological quality of included studies warrants cautious interpretation of our findings. Rigorous studies are warranted to provide robust evidence in the future.
Collapse
Affiliation(s)
- Ahmed M Hagag
- University College London Institute of Ophthalmology, London, United Kingdom; Moorfields Eye Hospital NHS Foundation Trust, London, United Kingdom; Boehringer Ingelheim Limited, Bracknell, United Kingdom
| | - Rebecca Kaye
- University of Southampton, Faculty of Medicine, Southampton, United Kingdom
| | - Vy Hoang
- University of Southampton, Faculty of Medicine, Southampton, United Kingdom
| | - Sophie Riedl
- Laboratory for Ophthalmic Image Analysis, Medical University of Vienna, Vienna, Austria
| | - Philipp Anders
- Institute of Molecular and Clinical Ophthalmology Basel, Basel, Switzerland; Department of Ophthalmology, University of Basel, Basel, Switzerland; Ophthalmology Unit, Centro Hospitalar e Universitário de Coimbra (CHUC), Coimbra, Portugal; AIBILI, Association for Innovation and Biomedical Research on Light and Image, Coimbra, Portugal
| | - Beth Stuart
- University of Southampton, Faculty of Medicine, Southampton, United Kingdom
| | - Ghislaine Traber
- Institute of Molecular and Clinical Ophthalmology Basel, Basel, Switzerland; Department of Ophthalmology, University of Basel, Basel, Switzerland
| | | | | | - Hrvoje Bogunovic
- Laboratory for Ophthalmic Image Analysis, Medical University of Vienna, Vienna, Austria
| | - Hendrik P Scholl
- Institute of Molecular and Clinical Ophthalmology Basel, Basel, Switzerland; Department of Ophthalmology, University of Basel, Basel, Switzerland
| | | | | | - Daniel Rueckert
- Imperial College London, London, United Kingdom; Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Sobha Sivaprasad
- University College London Institute of Ophthalmology, London, United Kingdom; Moorfields Eye Hospital NHS Foundation Trust, London, United Kingdom.
| | - Andrew J Lotery
- University of Southampton, Faculty of Medicine, Southampton, United Kingdom.
| |
Collapse
|
23
|
Navneet S, Wilson K, Rohrer B. Müller Glial Cells in the Macula: Their Activation and Cell-Cell Interactions in Age-Related Macular Degeneration. Invest Ophthalmol Vis Sci 2024; 65:42. [PMID: 38416457 PMCID: PMC10910558 DOI: 10.1167/iovs.65.2.42] [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: 12/14/2023] [Accepted: 02/10/2024] [Indexed: 02/29/2024] Open
Abstract
Müller glia, the main glial cell of the retina, are critical for neuronal and vascular homeostasis in the retina. During age-related macular degeneration (AMD) pathogenesis, Müller glial activation, remodeling, and migrations are reported in the areas of retinal pigment epithelial (RPE) degeneration, photoreceptor loss, and choroidal neovascularization (CNV) lesions. Despite this evidence indicating glial activation localized to the regions of AMD pathogenesis, it is unclear whether these glial responses contribute to AMD pathology or occur merely as a bystander effect. In this review, we summarize how Müller glia are affected in AMD retinas and share a prospect on how Müller glial stress might directly contribute to the pathogenesis of AMD. The goal of this review is to highlight the need for future studies investigating the Müller cell's role in AMD. This may lead to a better understanding of AMD pathology, including the conversion from dry to wet AMD, which has no effective therapy currently and may shed light on drug intolerance and resistance to current treatments.
Collapse
Affiliation(s)
- Soumya Navneet
- Department of Ophthalmology, Medical University of South Carolina, Charleston, South Carolina, United States
| | - Kyrie Wilson
- Department of Ophthalmology, Medical University of South Carolina, Charleston, South Carolina, United States
| | - Bärbel Rohrer
- Department of Ophthalmology, Medical University of South Carolina, Charleston, South Carolina, United States
- Department of Neuroscience, Medical University of South Carolina, Charleston, South Carolina, United States
- Ralph H. Johnson VA Medical Center, Division of Research, Charleston, South Carolina, United States
| |
Collapse
|
24
|
Zou J, Shen YK, Wu SN, Wei H, Li QJ, Xu SH, Ling Q, Kang M, Liu ZL, Huang H, Chen X, Wang YX, Liao XL, Tan G, Shao Y. Prediction Model of Ocular Metastases in Gastric Adenocarcinoma: Machine Learning-Based Development and Interpretation Study. Technol Cancer Res Treat 2024; 23:15330338231219352. [PMID: 38233736 PMCID: PMC10865948 DOI: 10.1177/15330338231219352] [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: 11/30/2022] [Revised: 10/10/2023] [Accepted: 11/08/2023] [Indexed: 01/19/2024] Open
Abstract
Background: Although gastric adenocarcinoma (GA) related ocular metastasis (OM) is rare, its occurrence indicates a more severe disease. We aimed to utilize machine learning (ML) to analyze the risk factors of GA-related OM and predict its risks. Methods: This is a retrospective cohort study. The clinical data of 3532 GA patients were collected and randomly classified into training and validation sets in a ratio of 7:3. Those with or without OM were classified into OM and non-OM (NOM) groups. Univariate and multivariate logistic regression analyses and least absolute shrinkage and selection operator were conducted. We integrated the variables identified through feature importance ranking and further refined the selection process using forward sequential feature selection based on random forest (RF) algorithm before incorporating them into the ML model. We applied six ML algorithms to construct the predictive GA model. The area under the receiver operating characteristic (ROC) curve indicated the model's predictive ability. Also, we established a network risk calculator based on the best performance model. We used Shapley additive interpretation (SHAP) to identify risk factors and to confirm the interpretability of the black box model. We have de-identified all patient details. Results: The ML model, consisting of 13 variables, achieved an optimal predictive performance using the gradient boosting machine (GBM) model, with an impressive area under the curve (AUC) of 0.997 in the test set. Utilizing the SHAP method, we identified crucial factors for OM in GA patients, including LDL, CA724, CEA, AFP, CA125, Hb, CA153, and Ca2+. Additionally, we validated the model's reliability through an analysis of two patient cases and developed a functional online web prediction calculator based on the GBM model. Conclusion: We used the ML method to establish a risk prediction model for GA-related OM and showed that GBM performed best among the six ML models. The model may identify patients with GA-related OM to provide early and timely treatment.
Collapse
Affiliation(s)
- Jie Zou
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Jiangxi Branch of National Clinical Research Center for Ocular Disease, Nanchang, Jiangxi, People's Republic of China
| | - Yan-Kun Shen
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Jiangxi Branch of National Clinical Research Center for Ocular Disease, Nanchang, Jiangxi, People's Republic of China
| | - Shi-Nan Wu
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Jiangxi Branch of National Clinical Research Center for Ocular Disease, Nanchang, Jiangxi, People's Republic of China
- Fujian Provincial Key Laboratory of Ophthalmology and Visual Science, Eye Institute of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, People's Republic of China
| | - Hong Wei
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Jiangxi Branch of National Clinical Research Center for Ocular Disease, Nanchang, Jiangxi, People's Republic of China
| | - Qing-Jian Li
- Fujian Provincial Key Laboratory of Ophthalmology and Visual Science, Eye Institute of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, People's Republic of China
| | - San Hua Xu
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Jiangxi Branch of National Clinical Research Center for Ocular Disease, Nanchang, Jiangxi, People's Republic of China
| | - Qian Ling
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Jiangxi Branch of National Clinical Research Center for Ocular Disease, Nanchang, Jiangxi, People's Republic of China
| | - Min Kang
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Jiangxi Branch of National Clinical Research Center for Ocular Disease, Nanchang, Jiangxi, People's Republic of China
| | - Zhao-Lin Liu
- Department of Ophthalmology, the First Affiliated Hospital of University of South China, Hunan Branch of National Clinical Research Center for Ocular Disease, Hengyan, Hunan Province, People's Republic of China
| | - Hui Huang
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Jiangxi Branch of National Clinical Research Center for Ocular Disease, Nanchang, Jiangxi, People's Republic of China
| | - Xu Chen
- Department of Ophthalmology and Visual Sciences, Maastricht University, Maastricht, Limburg Province, Netherlands
| | - Yi-Xin Wang
- School of Optometry and Vision Sciences, Cardiff University, Cardiff, UK
| | - Xu-Lin Liao
- Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Shatin, Hong Kong SAR, People's Republic of China
| | - Gang Tan
- Department of Ophthalmology, the First Affiliated Hospital of University of South China, Hunan Branch of National Clinical Research Center for Ocular Disease, Hengyan, Hunan Province, People's Republic of China
| | - Yi Shao
- Department of Ophthalmology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Jiangxi Branch of National Clinical Research Center for Ocular Disease, Nanchang, Jiangxi, People's Republic of China
- Current affiliation: Department of Ophthalmology, Eye & ENT Hospital of Fudan University, Shanghai, China
| |
Collapse
|
25
|
Heger KA, Waldstein SM. Artificial intelligence in retinal imaging: current status and future prospects. Expert Rev Med Devices 2024; 21:73-89. [PMID: 38088362 DOI: 10.1080/17434440.2023.2294364] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2023] [Accepted: 12/09/2023] [Indexed: 12/19/2023]
Abstract
INTRODUCTION The steadily growing and aging world population, in conjunction with continuously increasing prevalences of vision-threatening retinal diseases, is placing an increasing burden on the global healthcare system. The main challenges within retinology involve identifying the comparatively few patients requiring therapy within the large mass, the assurance of comprehensive screening for retinal disease and individualized therapy planning. In order to sustain high-quality ophthalmic care in the future, the incorporation of artificial intelligence (AI) technologies into our clinical practice represents a potential solution. AREAS COVERED This review sheds light onto already realized and promising future applications of AI techniques in retinal imaging. The main attention is directed at the application in diabetic retinopathy and age-related macular degeneration. The principles of use in disease screening, grading, therapeutic planning and prediction of future developments are explained based on the currently available literature. EXPERT OPINION The recent accomplishments of AI in retinal imaging indicate that its implementation into our daily practice is likely to fundamentally change the ophthalmic healthcare system and bring us one step closer to the goal of individualized treatment. However, it must be emphasized that the aim is to optimally support clinicians by gradually incorporating AI approaches, rather than replacing ophthalmologists.
Collapse
Affiliation(s)
- Katharina A Heger
- Department of Ophthalmology, Landesklinikum Mistelbach-Gaenserndorf, Mistelbach, Austria
| | - Sebastian M Waldstein
- Department of Ophthalmology, Landesklinikum Mistelbach-Gaenserndorf, Mistelbach, Austria
| |
Collapse
|
26
|
Talcott KE, Valentim CCS, Perkins SW, Ren H, Manivannan N, Zhang Q, Bagherinia H, Lee G, Yu S, D'Souza N, Jarugula H, Patel K, Singh RP. Automated Detection of Abnormal Optical Coherence Tomography B-scans Using a Deep Learning Artificial Intelligence Neural Network Platform. Int Ophthalmol Clin 2024; 64:115-127. [PMID: 38146885 DOI: 10.1097/iio.0000000000000519] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2023]
|
27
|
Jang B, Lee SY, Kim C, Park UC, Kim YG, Lee EK. Preliminary analysis of predicting the first recurrence in patients with neovascular age-related macular degeneration using deep learning. BMC Ophthalmol 2023; 23:499. [PMID: 38062449 PMCID: PMC10702052 DOI: 10.1186/s12886-023-03229-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Accepted: 11/17/2023] [Indexed: 12/18/2023] Open
Abstract
BACKGROUND To predict, using deep learning, the first recurrence in patients with neovascular age-related macular degeneration (nAMD) after three monthly loading injections of intravitreal anti-vascular endothelial growth factor (anti-VEGF). METHODS Optical coherence tomography (OCT) images were obtained at baseline and after the loading phase. The first recurrence was defined as the initial appearance of a new retinal hemorrhage or intra/subretinal fluid accumulation after the initial resolution of exudative changes after three loading injections. Standard U-Net architecture was used to identify the three retinal fluid compartments, which include pigment epithelial detachment, subretinal fluid, and intraretinal fluid. To predict the first recurrence of nAMD, classification learning was conducted to determine whether the first recurrence occurred within three months after the loading phase. The recurrence classification architecture was built using ResNet50. The model with retinal regions of interest of the entire region and fluid region on OCT at baseline and after the loading phase is presented. RESULTS A total of 1,444 eyes of 1,302 patients were included. The mean duration until the first recurrence after the loading phase was 8.20 ± 15.56 months. The recurrence classification system revealed that the model with the fluid region of OCT after the loading phase provided the highest classification performance, with an area under the receiver operating characteristic curve (AUC) of 0.725 ± 0.012. Heatmap analysis revealed that three pathological fluids, subsided choroidal neovascularization lesions, and hyperreflective foci were important areas for the first recurrence. CONCLUSIONS The deep learning algorithm allowed for the prediction of the first recurrence for three months after the loading phase with adequate feasibility. An automated prediction system may assist in establishing patient-specific treatment plans and the provision of individualized medical care for patients with nAMD.
Collapse
Affiliation(s)
- Boa Jang
- Department of Transdisciplinary Medicine, Seoul National University Hospital, #101, Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea
- Interdisciplinary Program in Bioengineering, College of Engineering, Seoul National University, Seoul, Republic of Korea
| | - Sang-Yoon Lee
- Seoul Shinsegae Eye Clinic, Seoul, Republic of Korea
| | - Chaea Kim
- Department of Transdisciplinary Medicine, Seoul National University Hospital, #101, Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea
| | - Un Chul Park
- Department of Ophthalmology, Seoul National University College of Medicine, Seoul National University Hospital, #101, Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea
| | - Young-Gon Kim
- Department of Transdisciplinary Medicine, Seoul National University Hospital, #101, Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea.
- Department of Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea.
| | - Eun Kyoung Lee
- Department of Ophthalmology, Seoul National University College of Medicine, Seoul National University Hospital, #101, Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea.
| |
Collapse
|
28
|
Verma A, Corradetti G, He Y, Nittala MG, Nassisi M, Velaga SB, Haines JL, Pericak-Vance MA, Stambolian D, Sadda SR. Relationship between the distribution of intra-retinal hyper-reflective foci and the progression of intermediate age-related macular degeneration. Graefes Arch Clin Exp Ophthalmol 2023; 261:3437-3447. [PMID: 37566303 PMCID: PMC10667133 DOI: 10.1007/s00417-023-06180-4] [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: 05/10/2023] [Revised: 07/08/2023] [Accepted: 07/17/2023] [Indexed: 08/12/2023] Open
Abstract
PURPOSE To assess the relationship between the distribution of intra-retinal hyper-reflective foci (IHRF) on optical coherence tomography (OCT) and progression of intermediate age-related macular degeneration (iAMD) over 2 years. METHODS Cirrus OCT volumes of the macula of subjects enrolled in the Amish Eye Study with 2 years of follow-up were evaluated for the presence of iAMD and IHRF at baseline. The IHRF were counted in a series of 5 sequential en face slabs from outer to inner retina. The number of IHRF in each slab at baseline and the change in IHRF from baseline to year 2 were correlated with progression to late AMD at 2 years. RESULTS Among 120 eyes from 71 patients with iAMD, 52 eyes (43.3%) of 42 patients had evidence of both iAMD and IHRF at baseline. Twenty-three eyes (19.0%) showed progression to late AMD after 2 years. The total IHRF count increased from 243 at baseline to 604 at 2 years, with a significant increase in the IHRF number in each slab, except for the innermost slab 5 which had no IHRF at baseline or follow-up. The IHRF count increased from 121 to 340 in eyes that showed progression to late AMD. The presence of IHRF in the outermost retinal slabs 1 and 2 was independently associated with a significant risk of progression to late AMD. A greater increase in IHRF count over 2 years in these same slabs 1 and 2 was also associated with a higher risk of conversion to late AMD. CONCLUSIONS The risk of progression to late AMD appears to be significantly associated with the distribution and extent of IHRF in the outermost retinal layers. This observation may point to significant pathophysiologic differences of IHRF in inner versus outer layers of the retina.
Collapse
Affiliation(s)
- Aditya Verma
- Doheny Eye Institute, Pasadena, CA, USA
- Department of Ophthalmology and Visual Sciences, University of Louisville Health Eye Specialists, Louisville, KY, USA
| | - Giulia Corradetti
- Doheny Eye Institute, Pasadena, CA, USA
- Department of Ophthalmology, David Geffen School of Medicine at the University of California, Los Angeles, Los Angeles, CA, USA
| | - Ye He
- Doheny Eye Institute, Pasadena, CA, USA
- Department of Ophthalmology, David Geffen School of Medicine at the University of California, Los Angeles, Los Angeles, CA, USA
- Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin Branch of National Clinical Research Center for Ocular Disease, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital, Tianjin, China
| | | | - Marco Nassisi
- Department of Clinical Sciences and Community Health, University of Milan, Milan, Italy
- Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico, Milan, Italy
| | | | - Jonathan L Haines
- Department of Population & Quantitative Health Sciences and Cleveland Institute for Computational Biology, Case Western Reserve University, Cleveland, OH, USA
| | - Margaret A Pericak-Vance
- John P. Hussman Institute for Human Genomics, University of Miami Miller School of Medicine, Miami, FL, 33136, USA
| | - Dwight Stambolian
- Department of Ophthalmology, University of Pennsylvania, Perelman School of Medicine, Philadelphia, PA, 19104, USA
| | - SriniVas R Sadda
- Doheny Eye Institute, Pasadena, CA, USA.
- Department of Ophthalmology, David Geffen School of Medicine at the University of California, Los Angeles, Los Angeles, CA, USA.
| |
Collapse
|
29
|
Lad EM, Finger RP, Guymer R. Biomarkers for the Progression of Intermediate Age-Related Macular Degeneration. Ophthalmol Ther 2023; 12:2917-2941. [PMID: 37773477 PMCID: PMC10640447 DOI: 10.1007/s40123-023-00807-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2023] [Accepted: 08/30/2023] [Indexed: 10/01/2023] Open
Abstract
Age-related macular degeneration (AMD) is a leading cause of severe vision loss worldwide, with a global prevalence that is predicted to substantially increase. Identifying early biomarkers indicative of progression risk will improve our ability to assess which patients are at greatest risk of progressing from intermediate AMD (iAMD) to vision-threatening late-stage AMD. This is key to ensuring individualized management and timely intervention before substantial structural damage. Some structural biomarkers suggestive of AMD progression risk are well established, such as changes seen on color fundus photography and more recently optical coherence tomography (drusen volume, pigmentary abnormalities). Emerging biomarkers identified through multimodal imaging, including reticular pseudodrusen, hyperreflective foci, and drusen sub-phenotypes, are being intensively explored as risk factors for progression towards late-stage disease. Other structural biomarkers merit further research, such as ellipsoid zone reflectivity and choriocapillaris flow features. The measures of visual function that best detect change in iAMD and correlate with risk of progression remain under intense investigation, with tests such as dark adaptometry and cone-specific contrast tests being explored. Evidence on blood and plasma markers is preliminary, but there are indications that changes in levels of C-reactive protein and high-density lipoprotein cholesterol may be used to stratify patients and predict risk. With further research, some of these biomarkers may be used to monitor progression. Emerging artificial intelligence methods may help evaluate and validate these biomarkers; however, until we have large and well-curated longitudinal data sets, using artificial intelligence effectively to inform clinical trial design and detect outcomes will remain challenging. This is an exciting area of intense research, and further work is needed to establish the most promising biomarkers for disease progression and their use in clinical care and future trials. Ultimately, a multimodal approach may yield the most accurate means of monitoring and predicting future progression towards vision-threatening, late-stage AMD.
Collapse
Affiliation(s)
- Eleonora M Lad
- Department of Ophthalmology, Duke University Medical Center, Durham, NC, USA.
| | - Robert P Finger
- Department of Ophthalmology, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
| | - Robyn Guymer
- Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, University of Melbourne, Melbourne, Australia
| |
Collapse
|
30
|
Dow ER, Jeong HK, Katz EA, Toth CA, Wang D, Lee T, Kuo D, Allingham MJ, Hadziahmetovic M, Mettu PS, Schuman S, Carin L, Keane PA, Henao R, Lad EM. A Deep-Learning Algorithm to Predict Short-Term Progression to Geographic Atrophy on Spectral-Domain Optical Coherence Tomography. JAMA Ophthalmol 2023; 141:1052-1061. [PMID: 37856139 PMCID: PMC10587827 DOI: 10.1001/jamaophthalmol.2023.4659] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Accepted: 08/27/2023] [Indexed: 10/20/2023]
Abstract
Importance The identification of patients at risk of progressing from intermediate age-related macular degeneration (iAMD) to geographic atrophy (GA) is essential for clinical trials aimed at preventing disease progression. DeepGAze is a fully automated and accurate convolutional neural network-based deep learning algorithm for predicting progression from iAMD to GA within 1 year from spectral-domain optical coherence tomography (SD-OCT) scans. Objective To develop a deep-learning algorithm based on volumetric SD-OCT scans to predict the progression from iAMD to GA during the year following the scan. Design, Setting, and Participants This retrospective cohort study included participants with iAMD at baseline and who either progressed or did not progress to GA within the subsequent 13 months. Participants were included from centers in 4 US states. Data set 1 included patients from the Age-Related Eye Disease Study 2 AREDS2 (Ancillary Spectral-Domain Optical Coherence Tomography) A2A study (July 2008 to August 2015). Data sets 2 and 3 included patients with imaging taken in routine clinical care at a tertiary referral center and associated satellites between January 2013 and January 2023. The stored imaging data were retrieved for the purpose of this study from July 1, 2022, to February 1, 2023. Data were analyzed from May 2021 to July 2023. Exposure A position-aware convolutional neural network with proactive pseudointervention was trained and cross-validated on Bioptigen SD-OCT volumes (data set 1) and validated on 2 external data sets comprising Heidelberg Spectralis SD-OCT scans (data sets 2 and 3). Main Outcomes and Measures Prediction of progression to GA within 13 months was evaluated with area under the receiver-operator characteristic curves (AUROC) as well as area under the precision-recall curve (AUPRC), sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. Results The study included a total of 417 patients: 316 in data set 1 (mean [SD] age, 74 [8]; 185 [59%] female), 53 in data set 2, (mean [SD] age, 83 [8]; 32 [60%] female), and 48 in data set 3 (mean [SD] age, 81 [8]; 32 [67%] female). The AUROC for prediction of progression from iAMD to GA within 1 year was 0.94 (95% CI, 0.92-0.95; AUPRC, 0.90 [95% CI, 0.85-0.95]; sensitivity, 0.88 [95% CI, 0.84-0.92]; specificity, 0.90 [95% CI, 0.87-0.92]) for data set 1. The addition of expert-annotated SD-OCT features to the model resulted in no improvement compared to the fully autonomous model (AUROC, 0.95; 95% CI, 0.92-0.95; P = .19). On an independent validation data set (data set 2), the model predicted progression to GA with an AUROC of 0.94 (95% CI, 0.91-0.96; AUPRC, 0.92 [0.89-0.94]; sensitivity, 0.91 [95% CI, 0.74-0.98]; specificity, 0.80 [95% CI, 0.63-0.91]). At a high-specificity operating point, simulated clinical trial recruitment was enriched for patients progressing to GA within 1 year by 8.3- to 20.7-fold (data sets 2 and 3). Conclusions and Relevance The fully automated, position-aware deep-learning algorithm assessed in this study successfully predicted progression from iAMD to GA over a clinically meaningful time frame. The ability to predict imminent GA progression could facilitate clinical trials aimed at preventing the condition and could guide clinical decision-making regarding screening frequency or treatment initiation.
Collapse
Affiliation(s)
- Eliot R. Dow
- Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina
| | - Hyeon Ki Jeong
- Department of Biostatistics and Bioinformatics, Duke University Medical Center, Durham, North Carolina
| | - Ella Arnon Katz
- Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina
| | - Cynthia A. Toth
- Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina
| | - Dong Wang
- Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina
| | - Terry Lee
- Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina
| | - David Kuo
- Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina
| | - Michael J. Allingham
- Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina
| | - Majda Hadziahmetovic
- Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina
| | - Priyatham S. Mettu
- Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina
| | - Stefanie Schuman
- Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina
| | - Lawrence Carin
- Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina
- King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
| | - Pearse A. Keane
- University College London Institute of Ophthalmology, National Institute for Health and Care Research, Biomedical Research Centre, Moorfields Eye Hospital National Health Services Foundation Trust, London, United Kingdom
| | - Ricardo Henao
- Department of Biostatistics and Bioinformatics, Duke University Medical Center, Durham, North Carolina
- Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina
- King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
| | - Eleonora M. Lad
- Department of Ophthalmology, Duke University Medical Center, Durham, North Carolina
| |
Collapse
|
31
|
Daich Varela M, Sen S, De Guimaraes TAC, Kabiri N, Pontikos N, Balaskas K, Michaelides M. Artificial intelligence in retinal disease: clinical application, challenges, and future directions. Graefes Arch Clin Exp Ophthalmol 2023; 261:3283-3297. [PMID: 37160501 PMCID: PMC10169139 DOI: 10.1007/s00417-023-06052-x] [Citation(s) in RCA: 15] [Impact Index Per Article: 15.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2023] [Revised: 03/20/2023] [Accepted: 03/24/2023] [Indexed: 05/11/2023] Open
Abstract
Retinal diseases are a leading cause of blindness in developed countries, accounting for the largest share of visually impaired children, working-age adults (inherited retinal disease), and elderly individuals (age-related macular degeneration). These conditions need specialised clinicians to interpret multimodal retinal imaging, with diagnosis and intervention potentially delayed. With an increasing and ageing population, this is becoming a global health priority. One solution is the development of artificial intelligence (AI) software to facilitate rapid data processing. Herein, we review research offering decision support for the diagnosis, classification, monitoring, and treatment of retinal disease using AI. We have prioritised diabetic retinopathy, age-related macular degeneration, inherited retinal disease, and retinopathy of prematurity. There is cautious optimism that these algorithms will be integrated into routine clinical practice to facilitate access to vision-saving treatments, improve efficiency of healthcare systems, and assist clinicians in processing the ever-increasing volume of multimodal data, thereby also liberating time for doctor-patient interaction and co-development of personalised management plans.
Collapse
Affiliation(s)
- Malena Daich Varela
- UCL Institute of Ophthalmology, London, UK
- Moorfields Eye Hospital, London, UK
| | | | | | | | - Nikolas Pontikos
- UCL Institute of Ophthalmology, London, UK
- Moorfields Eye Hospital, London, UK
| | | | - Michel Michaelides
- UCL Institute of Ophthalmology, London, UK.
- Moorfields Eye Hospital, London, UK.
| |
Collapse
|
32
|
Schmetterer L, Scholl H, Garhöfer G, Janeschitz-Kriegl L, Corvi F, Sadda SR, Medeiros FA. Endpoints for clinical trials in ophthalmology. Prog Retin Eye Res 2023; 97:101160. [PMID: 36599784 DOI: 10.1016/j.preteyeres.2022.101160] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2022] [Revised: 12/22/2022] [Accepted: 12/28/2022] [Indexed: 01/03/2023]
Abstract
With the identification of novel targets, the number of interventional clinical trials in ophthalmology has increased. Visual acuity has for a long time been considered the gold standard endpoint for clinical trials, but in the recent years it became evident that other endpoints are required for many indications including geographic atrophy and inherited retinal disease. In glaucoma the currently available drugs were approved based on their IOP lowering capacity. Some recent findings do, however, indicate that at the same level of IOP reduction, not all drugs have the same effect on visual field progression. For neuroprotection trials in glaucoma, novel surrogate endpoints are required, which may either include functional or structural parameters or a combination of both. A number of potential surrogate endpoints for ophthalmology clinical trials have been identified, but their validation is complicated and requires solid scientific evidence. In this article we summarize candidates for clinical endpoints in ophthalmology with a focus on retinal disease and glaucoma. Functional and structural biomarkers, as well as quality of life measures are discussed, and their potential to serve as endpoints in pivotal trials is critically evaluated.
Collapse
Affiliation(s)
- Leopold Schmetterer
- Singapore Eye Research Institute, Singapore; SERI-NTU Advanced Ocular Engineering (STANCE), Singapore; Academic Clinical Program, Duke-NUS Medical School, Singapore; School of Chemistry, Chemical Engineering and Biotechnology, Nanyang Technological University, Singapore; Department of Clinical Pharmacology, Medical University Vienna, Vienna, Austria; Center for Medical Physics and Biomedical Engineering, Medical University Vienna, Vienna, Austria; Institute of Molecular and Clinical Ophthalmology, Basel, Switzerland.
| | - Hendrik Scholl
- Institute of Molecular and Clinical Ophthalmology, Basel, Switzerland; Department of Ophthalmology, University of Basel, Basel, Switzerland
| | - Gerhard Garhöfer
- Department of Clinical Pharmacology, Medical University Vienna, Vienna, Austria
| | - Lucas Janeschitz-Kriegl
- Institute of Molecular and Clinical Ophthalmology, Basel, Switzerland; Department of Ophthalmology, University of Basel, Basel, Switzerland
| | - Federico Corvi
- Eye Clinic, Department of Biomedical and Clinical Sciences "Luigi Sacco", University of Milan, Italy
| | - SriniVas R Sadda
- Doheny Eye Institute, Los Angeles, CA, USA; Department of Ophthalmology, David Geffen School of Medicine at University of California, Los Angeles, CA, USA
| | - Felipe A Medeiros
- Vision, Imaging and Performance Laboratory, Department of Ophthalmology, Duke Eye Center, Duke University, Durham, NC, USA
| |
Collapse
|
33
|
Sadda S, Verma A, Corradetti G, Nittala M, He Y, Nassisi M, Velaga SB, Haines J, Pericak-Vance M, Stambolian D. Longitudinal evaluation of the distribution of intraretinal hyper-reflective foci in eyes with intermediate age-related macular degeneration. RESEARCH SQUARE 2023:rs.3.rs-3273570. [PMID: 37790320 PMCID: PMC10543506 DOI: 10.21203/rs.3.rs-3273570/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/05/2023]
Abstract
Purpose Intraretinal hyper-reflective foci (IHRF) are optical coherence tomography (OCT) risk factors for progression of age-related macular degeneration (AMD). In this study we assess the change in the number and distribution of IHRF over two years. Methods The axial distribution of IHRF were quantified in eyes with intermediate AMD (iAMD) at baseline and 24 months, using a series of 5 sequential equidistant en face OCT retinal slabs generated between the outer border of the internal limiting membrane (ILM) and the inner border of the retinal pigment epithelium (RPE). Following thresholding and binarization, IHRF were quantified in each retinal slab using ImageJ. The change in IHRF number in each slab between baseline and month 24 was calculated. Results Fifty-two eyes showed evidence of IHRF at baseline, and all continued to show evidence of IHRF at 24 months (M24). The total average IHRF count/eye increased significantly from 4.67 ± 0.63 at baseline to 11.62 ± 13.86 at M24 (p<0.001) with a mean increase of 6.94 ± 11.12 (range: - 9 to + 60). Overall, at M24, 76.9% eyes showed an increase in IHRF whereas 15.4% of eyes showed a decrease (4 eyes [7.6%] showed no change). There was a greater number of IHRF and a greater increase in IHRF over M24 in the outer slabs. Conclusions IHRF are most common in the outer retinal layers and tend to increase in number over time. The impact of the distribution and frequency of these IHRF on the overall progression of AMD requires further study.
Collapse
|
34
|
Danese C, Kale AU, Aslam T, Lanzetta P, Barratt J, Chou YB, Eldem B, Eter N, Gale R, Korobelnik JF, Kozak I, Li X, Li X, Loewenstein A, Ruamviboonsuk P, Sakamoto T, Ting DS, van Wijngaarden P, Waldstein SM, Wong D, Wu L, Zapata MA, Zarranz-Ventura J. The impact of artificial intelligence on retinal disease management: Vision Academy retinal expert consensus. Curr Opin Ophthalmol 2023; 34:396-402. [PMID: 37326216 PMCID: PMC10399953 DOI: 10.1097/icu.0000000000000980] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/17/2023]
Abstract
PURPOSE OF REVIEW The aim of this review is to define the "state-of-the-art" in artificial intelligence (AI)-enabled devices that support the management of retinal conditions and to provide Vision Academy recommendations on the topic. RECENT FINDINGS Most of the AI models described in the literature have not been approved for disease management purposes by regulatory authorities. These new technologies are promising as they may be able to provide personalized treatments as well as a personalized risk score for various retinal diseases. However, several issues still need to be addressed, such as the lack of a common regulatory pathway and a lack of clarity regarding the applicability of AI-enabled medical devices in different populations. SUMMARY It is likely that current clinical practice will need to change following the application of AI-enabled medical devices. These devices are likely to have an impact on the management of retinal disease. However, a consensus needs to be reached to ensure they are safe and effective for the overall population.
Collapse
Affiliation(s)
- Carla Danese
- Department of Medicine – Ophthalmology, University of Udine, Udine, Italy
- Department of Ophthalmology, AP-HP Hôpital Lariboisière, Université Paris Cité, Paris, France
| | - Aditya U. Kale
- Academic Unit of Ophthalmology, Institute of Inflammation & Ageing, College of Medical and Dental Sciences, University of Birmingham, Birmingham
| | - Tariq Aslam
- Division of Pharmacy and Optometry, Faculty of Biology, Medicine and Health, University of Manchester School of Health Sciences, Manchester, UK
| | - Paolo Lanzetta
- Department of Medicine – Ophthalmology, University of Udine, Udine, Italy
- Istituto Europeo di Microchirurgia Oculare, Udine, Italy
| | - Jane Barratt
- International Federation on Ageing, Toronto, Canada
| | - Yu-Bai Chou
- Department of Ophthalmology, Taipei Veterans General Hospital
- School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Bora Eldem
- Department of Ophthalmology, Hacettepe University, Ankara, Turkey
| | - Nicole Eter
- Department of Ophthalmology, University of Münster Medical Center, Münster, Germany
| | - Richard Gale
- Department of Ophthalmology, York Teaching Hospital NHS Foundation Trust, York, UK
| | - Jean-François Korobelnik
- Service d’ophtalmologie, CHU Bordeaux
- University of Bordeaux, INSERM, BPH, UMR1219, F-33000 Bordeaux, France
| | - Igor Kozak
- Moorfields Eye Hospital Centre, Abu Dhabi, UAE
| | - Xiaorong Li
- Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin Branch of National Clinical Research Center for Ocular Disease, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital, Tianjin
| | - Xiaoxin Li
- Xiamen Eye Center, Xiamen University, Xiamen, China
| | - Anat Loewenstein
- Division of Ophthalmology, Tel Aviv Sourasky Medical Center, Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Paisan Ruamviboonsuk
- Department of Ophthalmology, College of Medicine, Rangsit University, Rajavithi Hospital, Bangkok, Thailand
| | - Taiji Sakamoto
- Department of Ophthalmology, Kagoshima University, Kagoshima, Japan
| | - Daniel S.W. Ting
- Singapore National Eye Center, Duke-NUS Medical School, Singapore
| | - Peter van Wijngaarden
- Ophthalmology, Department of Surgery, University of Melbourne, Melbourne, Australia
- Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Victoria, Australia
| | | | - David Wong
- Unity Health Toronto – St. Michael's Hospital, University of Toronto, Toronto, Canada
| | - Lihteh Wu
- Macula, Vitreous and Retina Associates of Costa Rica, San José, Costa Rica
| | | | | |
Collapse
|
35
|
Baumgartner M, Veeranki SPK, Hayn D, Schreier G. Introduction and Comparison of Novel Decentral Learning Schemes with Multiple Data Pools for Privacy-Preserving ECG Classification. JOURNAL OF HEALTHCARE INFORMATICS RESEARCH 2023; 7:291-312. [PMID: 37637722 PMCID: PMC10449753 DOI: 10.1007/s41666-023-00142-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2022] [Revised: 04/11/2023] [Accepted: 07/28/2023] [Indexed: 08/29/2023]
Abstract
Artificial intelligence and machine learning have led to prominent and spectacular innovations in various scenarios. Application in medicine, however, can be challenging due to privacy concerns and strict legal regulations. Methods that centralize knowledge instead of data could address this issue. In this work, 6 different decentralized machine learning algorithms are applied to 12-lead ECG classification and compared to conventional, centralized machine learning. The results show that state-of-the-art federated learning leads to reasonable losses of classification performance compared to a standard, central model (-0.054 AUROC) while providing a significantly higher level of privacy. A proposed weighted variant of federated learning (-0.049 AUROC) and an ensemble (-0.035 AUROC) outperformed the standard federated learning algorithm. Overall, considering multiple metrics, the novel batch-wise sequential learning scheme performed best (-0.036 AUROC to baseline). Although, the technical aspects of implementing them in a real-world application are to be carefully considered, the described algorithms constitute a way forward towards preserving-preserving AI in medicine.
Collapse
Affiliation(s)
- Martin Baumgartner
- Center for Health & Bioresources, AIT Austrian Institute of Technology, Giefinggasse 4, 1210 Vienna, Austria
- Institute of Neural Engineering, Technical University of Graz, Graz, Austria
| | | | - Dieter Hayn
- Center for Health & Bioresources, AIT Austrian Institute of Technology, Giefinggasse 4, 1210 Vienna, Austria
- Ludwig Boltzmann Institute for Digital Health and Prevention, Salzburg, Austria
| | - Günter Schreier
- Center for Health & Bioresources, AIT Austrian Institute of Technology, Giefinggasse 4, 1210 Vienna, Austria
- Institute of Neural Engineering, Technical University of Graz, Graz, Austria
| |
Collapse
|
36
|
Hanson RLW, Airody A, Sivaprasad S, Gale RP. Optical coherence tomography imaging biomarkers associated with neovascular age-related macular degeneration: a systematic review. Eye (Lond) 2023; 37:2438-2453. [PMID: 36526863 PMCID: PMC9871156 DOI: 10.1038/s41433-022-02360-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2022] [Revised: 10/13/2022] [Accepted: 12/06/2022] [Indexed: 12/23/2022] Open
Abstract
The aim of this systematic literature review is twofold, (1) detail the impact of retinal biomarkers identifiable via optical coherence tomography (OCT) on disease progression and response to treatment in neovascular age-related macular degeneration (nAMD) and (2) establish which biomarkers are currently identifiable by artificial intelligence (AI) models and the utilisation of this technology. Following the PRISMA guidelines, PubMed was searched for peer-reviewed publications dated between January 2016 and January 2022. POPULATION Patients diagnosed with nAMD with OCT imaging. SETTINGS Comparable settings to NHS hospitals. STUDY DESIGNS Randomised controlled trials, prospective/retrospective cohort studies and review articles. From 228 articles, 130 were full-text reviewed, 50 were removed for falling outside the scope of this review with 10 added from the author's inventory, resulting in the inclusion of 90 articles. From 9 biomarkers identified; intraretinal fluid (IRF), subretinal fluid, pigment epithelial detachment, subretinal hyperreflective material (SHRM), retinal pigmental epithelial (RPE) atrophy, drusen, outer retinal tabulation (ORT), hyperreflective foci (HF) and retinal thickness, 5 are considered pertinent to nAMD disease progression; IRF, SHRM, drusen, ORT and HF. A number of these biomarkers can be classified using current AI models. Significant retinal biomarkers pertinent to disease activity and progression in nAMD are identifiable via OCT; IRF being the most important in terms of the significant impact on visual outcome. Incorporating AI into ophthalmology practice is a promising advancement towards automated and reproducible analyses of OCT data with the ability to diagnose disease and predict future disease conversion. SYSTEMATIC REVIEW REGISTRATION This review has been registered with PROSPERO (registration ID: CRD42021233200).
Collapse
Affiliation(s)
- Rachel L W Hanson
- Academic Unit of Ophthalmology, York and Scarborough Teaching Hospitals NHS Foundation Trust, York, UK
| | - Archana Airody
- Academic Unit of Ophthalmology, York and Scarborough Teaching Hospitals NHS Foundation Trust, York, UK
| | - Sobha Sivaprasad
- Moorfields National Institute of Health Research, Biomedical Research Centre, London, UK
| | - Richard P Gale
- Academic Unit of Ophthalmology, York and Scarborough Teaching Hospitals NHS Foundation Trust, York, UK.
- Hull York Medical School, University of York, York, UK.
- York Biomedical Research Institute, University of York, York, UK.
| |
Collapse
|
37
|
Muntean GA, Marginean A, Groza A, Damian I, Roman SA, Hapca MC, Muntean MV, Nicoară SD. The Predictive Capabilities of Artificial Intelligence-Based OCT Analysis for Age-Related Macular Degeneration Progression-A Systematic Review. Diagnostics (Basel) 2023; 13:2464. [PMID: 37510207 PMCID: PMC10378064 DOI: 10.3390/diagnostics13142464] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2023] [Revised: 06/16/2023] [Accepted: 07/13/2023] [Indexed: 07/30/2023] Open
Abstract
The era of artificial intelligence (AI) has revolutionized our daily lives and AI has become a powerful force that is gradually transforming the field of medicine. Ophthalmology sits at the forefront of this transformation thanks to the effortless acquisition of an abundance of imaging modalities. There has been tremendous work in the field of AI for retinal diseases, with age-related macular degeneration being at the top of the most studied conditions. The purpose of the current systematic review was to identify and evaluate, in terms of strengths and limitations, the articles that apply AI to optical coherence tomography (OCT) images in order to predict the future evolution of age-related macular degeneration (AMD) during its natural history and after treatment in terms of OCT morphological structure and visual function. After a thorough search through seven databases up to 1 January 2022 using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, 1800 records were identified. After screening, 48 articles were selected for full-text retrieval and 19 articles were finally included. From these 19 articles, 4 articles concentrated on predicting the anti-VEGF requirement in neovascular AMD (nAMD), 4 articles focused on predicting anti-VEGF efficacy in nAMD patients, 3 articles predicted the conversion from early or intermediate AMD (iAMD) to nAMD, 1 article predicted the conversion from iAMD to geographic atrophy (GA), 1 article predicted the conversion from iAMD to both nAMD and GA, 3 articles predicted the future growth of GA and 3 articles predicted the future outcome for visual acuity (VA) after anti-VEGF treatment in nAMD patients. Since using AI methods to predict future changes in AMD is only in its initial phase, a systematic review provides the opportunity of setting the context of previous work in this area and can present a starting point for future research.
Collapse
Affiliation(s)
- George Adrian Muntean
- Department of Ophthalmology, "Iuliu Hatieganu" University of Medicine and Pharmacy, Emergency County Hospital, 400347 Cluj-Napoca, Romania
| | - Anca Marginean
- Department of Computer Science, Technical University of Cluj-Napoca, 400114 Cluj-Napoca, Romania
| | - Adrian Groza
- Department of Computer Science, Technical University of Cluj-Napoca, 400114 Cluj-Napoca, Romania
| | - Ioana Damian
- Department of Ophthalmology, "Iuliu Hatieganu" University of Medicine and Pharmacy, Emergency County Hospital, 400347 Cluj-Napoca, Romania
| | - Sara Alexia Roman
- Faculty of Medicine, "Iuliu Hatieganu" University of Medicine and Pharmacy, 400347 Cluj-Napoca, Romania
| | - Mădălina Claudia Hapca
- Department of Ophthalmology, "Iuliu Hatieganu" University of Medicine and Pharmacy, Emergency County Hospital, 400347 Cluj-Napoca, Romania
| | - Maximilian Vlad Muntean
- Plastic Surgery Department, "Prof. Dr. I. Chiricuta" Institute of Oncology, 400015 Cluj-Napoca, Romania
| | - Simona Delia Nicoară
- Department of Ophthalmology, "Iuliu Hatieganu" University of Medicine and Pharmacy, Emergency County Hospital, 400347 Cluj-Napoca, Romania
| |
Collapse
|
38
|
Goździewska E, Wichrowska M, Kocięcki J. Early Optical Coherence Tomography Biomarkers for Selected Retinal Diseases-A Review. Diagnostics (Basel) 2023; 13:2444. [PMID: 37510188 PMCID: PMC10378475 DOI: 10.3390/diagnostics13142444] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2023] [Revised: 07/14/2023] [Accepted: 07/19/2023] [Indexed: 07/30/2023] Open
Abstract
Optical coherence tomography (OCT) is a non-invasive, easily accessible imaging technique that enables diagnosing several retinal diseases at various stages of development. This review discusses early OCT findings as non-invasive imaging biomarkers for predicting the future development of selected retinal diseases, with emphasis on age-related macular degeneration, macular telangiectasia, and drug-induced maculopathies. Practitioners, by being able to predict the development of many conditions and start treatment at the earliest stage, may thus achieve better treatment outcomes.
Collapse
Affiliation(s)
- Ewa Goździewska
- Department of Ophthalmology, Poznan University of Medical Sciences, 60-569 Poznań, Poland
| | - Małgorzata Wichrowska
- Department of Ophthalmology, Poznan University of Medical Sciences, 60-569 Poznań, Poland
- Doctoral School, Poznan University of Medical Sciences, 61-701 Poznań, Poland
| | - Jarosław Kocięcki
- Department of Ophthalmology, Poznan University of Medical Sciences, 60-569 Poznań, Poland
| |
Collapse
|
39
|
Rivail A, Vogl WD, Riedl S, Grechenig C, Coulibaly LM, Reiter GS, Guymer RH, Wu Z, Schmidt-Erfurth U, Bogunović H. Deep survival modeling of longitudinal retinal OCT volumes for predicting the onset of atrophy in patients with intermediate AMD. BIOMEDICAL OPTICS EXPRESS 2023; 14:2449-2464. [PMID: 37342683 PMCID: PMC10278641 DOI: 10.1364/boe.487206] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Revised: 03/30/2023] [Accepted: 04/10/2023] [Indexed: 06/23/2023]
Abstract
In patients with age-related macular degeneration (AMD), the risk of progression to late stages is highly heterogeneous, and the prognostic imaging biomarkers remain unclear. We propose a deep survival model to predict the progression towards the late atrophic stage of AMD. The model combines the advantages of survival modelling, accounting for time-to-event and censoring, and the advantages of deep learning, generating prediction from raw 3D OCT scans, without the need for extracting a predefined set of quantitative biomarkers. We demonstrate, in an extensive set of evaluations, based on two large longitudinal datasets with 231 eyes from 121 patients for internal evaluation, and 280 eyes from 140 patients for the external evaluation, that this model improves the risk estimation performance over standard deep learning classification models.
Collapse
Affiliation(s)
- Antoine Rivail
- Christian Doppler Lab for Artificial Intelligence in Retina, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Wolf-Dieter Vogl
- Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Sophie Riedl
- Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Christoph Grechenig
- Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Leonard M. Coulibaly
- 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
| | - Robyn H. Guymer
- Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Australia
- Department of Surgery (Ophthalmology), The University of Melbourne, Melbourne, Australia
| | - Zhichao Wu
- Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, Australia
- Department of Surgery (Ophthalmology), The University of Melbourne, Melbourne, Australia
| | - Ursula Schmidt-Erfurth
- Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Hrvoje Bogunović
- Christian Doppler Lab for Artificial Intelligence in Retina, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| |
Collapse
|
40
|
Brizzi F, Steiert B, Pang H, Diack C, Lomax M, Peck R, Morgan Z, Soubret A. A model-based approach for historical borrowing, with an application to neovascular age-related macular degeneration. Stat Methods Med Res 2023; 32:1064-1081. [PMID: 37082812 DOI: 10.1177/09622802231155597] [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] [Indexed: 04/22/2023]
Abstract
Bayesian historical borrowing has recently attracted growing interest due to the increasing availability of historical control data, as well as improved computational methodology and software. In this article, we argue that the statistical models used for borrowing may be suboptimal when they do not adjust for differing factors across historical studies such as covariates, dosing regimen, etc. We propose an alternative approach to address these shortcomings. We start by constructing a historical model based on subject-level historical data to accurately characterize the control treatment by adjusting for known between trials differences. This model is subsequently used to predict the control arm response in the current trial, enabling the derivation of a model-informed prior for the treatment effect parameter of another (potentially simpler) model used to analyze the trial efficacy (i.e. the trial model). Our approach is applied to neovascular age-related macular degeneration trials, employing a cross-sectional regression trial model, and a longitudinal non-linear mixed-effects drug-disease-trial historical model. The latter model characterizes the relationship between clinical response, drug exposure and baseline covariates so that the derived model-informed prior seamlessly adapts to the trial population and can be extrapolated to a different dosing regimen. This approach can yield a more accurate prior for borrowing, thus optimizing gains in efficiency (e.g. increasing power or reducing the sample size) in future trials.
Collapse
Affiliation(s)
- Francesco Brizzi
- Predictive Modelling and Data Analytics, Roche Pharma Research & Early Development, Roche Innovation Center Basel, Switzerland
| | - Bernhard Steiert
- Predictive Modelling and Data Analytics, Roche Pharma Research & Early Development, Roche Innovation Center Basel, Switzerland
| | - Herbert Pang
- Methods Collaboration & Outreach (MCO) Enabling Platform, Genentech Inc., South San Francisco, USA
| | - Cheikh Diack
- Predictive Modelling and Data Analytics, Roche Pharma Research & Early Development, Roche Innovation Center Basel, Switzerland
| | - Mark Lomax
- Data & Statistical Sciences, F. Hoffman-La Roche Ltd, Welwyn Garden City, UK
| | - Robbie Peck
- Data & Statistical Sciences, Hoffmann-La Roche AG, Basel, Switzerland
| | - Zoe Morgan
- Data & Statistical Sciences, Hoffmann-La Roche AG, Basel, Switzerland
| | - Antoine Soubret
- Predictive Modelling and Data Analytics, Roche Pharma Research & Early Development, Roche Innovation Center Basel, Switzerland
| |
Collapse
|
41
|
Mai J, Lachinov D, Riedl S, Reiter GS, Vogl WD, Bogunovic H, Schmidt-Erfurth U. Clinical validation for automated geographic atrophy monitoring on OCT under complement inhibitory treatment. Sci Rep 2023; 13:7028. [PMID: 37120456 PMCID: PMC10148818 DOI: 10.1038/s41598-023-34139-2] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2023] [Accepted: 04/25/2023] [Indexed: 05/01/2023] Open
Abstract
Geographic atrophy (GA) represents a late stage of age-related macular degeneration, which leads to irreversible vision loss. With the first successful therapeutic approach, namely complement inhibition, huge numbers of patients will have to be monitored regularly. Given these perspectives, a strong need for automated GA segmentation has evolved. The main purpose of this study was the clinical validation of an artificial intelligence (AI)-based algorithm to segment a topographic 2D GA area on a 3D optical coherence tomography (OCT) volume, and to evaluate its potential for AI-based monitoring of GA progression under complement-targeted treatment. 100 GA patients from routine clinical care at the Medical University of Vienna for internal validation and 113 patients from the FILLY phase 2 clinical trial for external validation were included. Mean Dice Similarity Coefficient (DSC) was 0.86 ± 0.12 and 0.91 ± 0.05 for total GA area on the internal and external validation, respectively. Mean DSC for the GA growth area at month 12 on the external test set was 0.46 ± 0.16. Importantly, the automated segmentation by the algorithm corresponded to the outcome of the original FILLY trial measured manually on fundus autofluorescence. The proposed AI approach can reliably segment GA area on OCT with high accuracy. The availability of such tools represents an important step towards AI-based monitoring of GA progression under treatment on OCT for clinical management as well as regulatory trials.
Collapse
Affiliation(s)
- Julia Mai
- Laboratory for Ophthalmic Image Analysis (OPTIMA), Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - Dmitrii Lachinov
- Laboratory for Ophthalmic Image Analysis (OPTIMA), Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
- Christian Doppler Laboratory for Artificial Intelligence in Retina, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Sophie Riedl
- Laboratory for Ophthalmic Image Analysis (OPTIMA), Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - Gregor S Reiter
- Laboratory for Ophthalmic Image Analysis (OPTIMA), Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - Wolf-Dieter Vogl
- Laboratory for Ophthalmic Image Analysis (OPTIMA), Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
| | - Hrvoje Bogunovic
- Laboratory for Ophthalmic Image Analysis (OPTIMA), Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria
- Christian Doppler Laboratory for Artificial Intelligence in Retina, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Ursula Schmidt-Erfurth
- Laboratory for Ophthalmic Image Analysis (OPTIMA), Department of Ophthalmology and Optometry, Medical University of Vienna, Währinger Gürtel 18-20, 1090, Vienna, Austria.
| |
Collapse
|
42
|
Wawer Matos PA, Reimer RP, Rokohl AC, Caldeira L, Heindl LM, Große Hokamp N. Artificial Intelligence in Ophthalmology - Status Quo and Future Perspectives. Semin Ophthalmol 2023; 38:226-237. [PMID: 36356300 DOI: 10.1080/08820538.2022.2139625] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Abstract
Artificial intelligence (AI) is an emerging technology in healthcare and holds the potential to disrupt many arms in medical care. In particular, disciplines using medical imaging modalities, including e.g. radiology but ophthalmology as well, are already confronted with a wide variety of AI implications. In ophthalmologic research, AI has demonstrated promising results limited to specific diseases and imaging tools, respectively. Yet, implementation of AI in clinical routine is not widely spread due to availability, heterogeneity in imaging techniques and AI methods. In order to describe the status quo, this narrational review provides a brief introduction to AI ("what the ophthalmologist needs to know"), followed by an overview of different AI-based applications in ophthalmology and a discussion on future challenges.Abbreviations: Age-related macular degeneration, AMD; Artificial intelligence, AI; Anterior segment OCT, AS-OCT; Coronary artery calcium score, CACS; Convolutional neural network, CNN; Deep convolutional neural network, DCNN; Diabetic retinopathy, DR; Machine learning, ML; Optical coherence tomography, OCT; Retinopathy of prematurity, ROP; Support vector machine, SVM; Thyroid-associated ophthalmopathy, TAO.
Collapse
Affiliation(s)
| | - Robert P Reimer
- Department of Diagnostic and Interventional Radiology, University Hospital of Cologne, Köln, Germany
| | - Alexander C Rokohl
- Department of Ophthalmology, University Hospital of Cologne, Köln, Germany
| | - Liliana Caldeira
- Department of Diagnostic and Interventional Radiology, University Hospital of Cologne, Köln, Germany
| | - Ludwig M Heindl
- Department of Ophthalmology, University Hospital of Cologne, Köln, Germany
| | - Nils Große Hokamp
- Department of Diagnostic and Interventional Radiology, University Hospital of Cologne, Köln, Germany
| |
Collapse
|
43
|
Kalra G, Cetin H, Whitney J, Yordi S, Cakir Y, McConville C, Whitmore V, Bonnay M, Reese JL, Srivastava SK, Ehlers JP. Automated Identification and Segmentation of Ellipsoid Zone At-Risk Using Deep Learning on SD-OCT for Predicting Progression in Dry AMD. Diagnostics (Basel) 2023; 13:1178. [PMID: 36980486 PMCID: PMC10047385 DOI: 10.3390/diagnostics13061178] [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: 01/27/2023] [Revised: 03/14/2023] [Accepted: 03/17/2023] [Indexed: 03/30/2023] Open
Abstract
BACKGROUND The development and testing of a deep learning (DL)-based approach for detection and measurement of regions of Ellipsoid Zone (EZ) At-Risk to study progression in nonexudative age-related macular degeneration (AMD). METHODS Used in DL model training and testing were 341 subjects with nonexudative AMD with or without geographic atrophy (GA). An independent dataset of 120 subjects were used for testing model performance for prediction of GA progression. Accuracy, specificity, sensitivity, and intraclass correlation coefficient (ICC) for DL-based EZ At-Risk percentage area measurement was calculated. Random forest-based feature ranking of EZ At-Risk was compared to previously validated quantitative OCT-based biomarkers. RESULTS The model achieved a detection accuracy of 99% (sensitivity = 99%; specificity = 100%) for EZ At-Risk. Automatic EZ At-Risk measurement achieved an accuracy of 90% (sensitivity = 90%; specificity = 84%) and the ICC compared to ground truth was high (0.83). In the independent dataset, higher baseline mean EZ At-Risk correlated with higher progression to GA at year 5 (p < 0.001). EZ At-Risk was a top ranked feature in the random forest assessment for GA prediction. CONCLUSIONS This report describes a novel high performance DL-based model for the detection and measurement of EZ At-Risk. This biomarker showed promising results in predicting progression in nonexudative AMD patients.
Collapse
Affiliation(s)
| | | | | | | | | | | | | | | | | | | | - Justis P. Ehlers
- Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, OH 44195, USA
| |
Collapse
|
44
|
Rispoli M, Cennamo G, Antonio LD, Lupidi M, Parravano M, Pellegrini M, Veritti D, Vujosevic S, Savastano MC. Practical guidance for imaging biomarkers in exudative age-related macular degeneration. Surv Ophthalmol 2023:S0039-6257(23)00039-5. [PMID: 36854371 DOI: 10.1016/j.survophthal.2023.02.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2022] [Revised: 02/17/2023] [Accepted: 02/21/2023] [Indexed: 02/27/2023]
Abstract
We provide an overview of current macular imaging techniques and identify and describe biomarkers that may be of use in the routine management of macular diseases, particularly exudative age-related macular degeneration (n-AMD). This perspective includes sections on macular imaging techniques including optical coherence tomography (OCT) and OCT angiography (OCTA), classification of exudative AMD, and biomarkers in structural OCT and OCTA. Fluorescein angiography remains a vital tool for assessing the activity of neovascular lesion, while indocyanine green angiography is the preferred option for choroidal vessels imaging in neovascular AMD. OCT provides a non-invasive three-dimensional visualization of retinal architecture in vivo and is useful in the diagnosis of many imaging biomarkers of AMD-related neovascular lesions including lesion activity. OCTA is a recent advance in OCT technology that allows accurate visualization of retinal and choroidal vascular flow. OCT and OCTA have led to an updated classification of exudative AMD lesions and provide several biomarkers that help to establish a diagnosis and the disease activity status of neovascular lesions. Individualization of therapy guided by OCT and OCTA biomarkers has the potential to further improve visual outcomes in exudative AMD. Moving forwards, integration of technologically advanced imaging equipment with AI software will help ophthalmologists to provide patients with the best possible care.
Collapse
Affiliation(s)
| | - Gilda Cennamo
- Eye Clinic, Department of Neurosciences, Reproductive and Odontostomatological Sciences, Federico II University; Public Health Department, University of Naples Federico II, Naples, Italy
| | - Luca Di Antonio
- UOC Ophthalmology and Surgery Department, ASL-1 Avezzano-Sulmona, L'Aquila, Italy
| | - Marco Lupidi
- Eye Clinic, Department of Experimental and Clinical Medicine, Polytechnic University of Marche, Ancona, Italy.
| | | | - Marco Pellegrini
- Department of Biomedical and Clinical Science "Luigi Sacco", Eye Clinic, Luigi Sacco Hospital, University of Milan, Milan, Italy
| | - Daniele Veritti
- Department of Medicine-Ophthalmology, University of Udine, Italy
| | - Stela Vujosevic
- University Eye Clinic, IRCCS Multimedica, Milan, Italy; Department of Biomedical, Surgical and Dental Sciences, University of Milan, Milan, Italy
| | - Maria Cristina Savastano
- Ophthalmology Unit, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy; Catholic University "Sacro Cuore", Rome, Italy
| |
Collapse
|
45
|
Retinitis Pigmentosa Associated with EYS Gene Mutations: Disease Severity Staging and Central Retina Atrophy. Diagnostics (Basel) 2023; 13:diagnostics13050850. [PMID: 36899994 PMCID: PMC10000790 DOI: 10.3390/diagnostics13050850] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2022] [Revised: 02/07/2023] [Accepted: 02/13/2023] [Indexed: 02/25/2023] Open
Abstract
BACKGROUND Eyes shut homolog (EYS) gene mutations are estimated to affect at least 5% of patients with autosomal recessive retinitis pigmentosa. Since there is no mammalian model of human EYS disease, it is important to investigate its age-related changes and the degree of central retinal impairment. METHODS A cohort of EYS patients was studied. They underwent full ophthalmic examination as well as assessment of retinal function and structure, by full-field and focal electroretinograms (ERGs) and spectral domain optical coherence tomography (OCT), respectively. The disease severity stage was determined by the RP stage scoring system (RP-SSS). Central retina atrophy (CRA) was estimated from the automatically calculated area of the sub-retinal pigment epithelium (RPE) illumination (SRI). RESULTS The RP-SSS was positively correlated with age, showing an advanced severity score (≥8) at an age of 45 and a disease duration of 15 years. The RP-SSS was positively correlated with the CRA area. LogMAR visual acuity and ellipsoid zone width, but not ERG, were correlated with CRA. CONCLUSIONS In EYS-related disease, the RP-SSS showed advanced severity at a relative early age and was correlated with the central area of the RPE/photoreceptor atrophy. These correlations may be relevant in view of therapeutic interventions aimed at rescuing rods and cones in EYS-retinopathy.
Collapse
|
46
|
Bakaliou A, Georgakopoulos C, Tsilimbaris M, Farmakakis N. Posterior Vitreous Detachment and Its Role in the Evolution of Dry to Wet Age Related Macular Degeneration. Clin Ophthalmol 2023; 17:879-885. [PMID: 36960325 PMCID: PMC10029933 DOI: 10.2147/opth.s403242] [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: 12/31/2022] [Accepted: 03/03/2023] [Indexed: 03/18/2023] Open
Abstract
Purpose To examine the state of the posterior vitreous in eyes with exudative age-related macular degeneration, AMD, non-exudative AMD and in normal eyes. Study This is a prospective, cross-sectional study. Methods B-scan ultrasonography and Optical Coherence Tomography, OCT were performed in 165 patients older than 65 years with any AMD and in 22 patients older than 65 years with normal eyes in order to diagnose the eyes with complete posterior vitreous detachment, PVD and the eyes with persistent central vitreomacular adhesion, VMA. All patients were selected from the outpatient clinic of the Ophthalmology Department in the University Hospital of Patras. Fundus Fluoroangiography, FFA was used in order to determine the development of exudative AMD from non-exudative AMD. Follow up time was 48 months. Results 16/171 eyes with exudative AMD (9.36%) had complete PVD, and the rest 155/171 (90.64%) had central VMA. Eleven of 138 eyes with non-exudative AMD (7.97%) had complete PVD and the remaining 127 eyes (92.03%) had central VMA. During the 48 months of the study, 28 eyes, all with central VMA progressed to exudative AMD. Conclusion Vitreomacular adhesion is associated with both exudative and non-exudative AMD. Progression of the non-exudative eyes to exudative AMD seems to be lower in eyes with complete PVD. On the other hand, the progression of normal eyes to exudative AMD appears to be independent of the posterior vitreous status. Larger and longer studies need to replicate these findings and support the potential of a protective role of complete posterior vitreous detachment in the evolution of the disease.
Collapse
Affiliation(s)
- Anastasia Bakaliou
- Ophthalmology Department, Medical School of Patras, University of Patras, Patras, Greece
| | - Constantine Georgakopoulos
- Ophthalmology Department, Medical School of Patras, University of Patras, Patras, Greece
- Correspondence: Constantine Georgakopoulos, Email
| | - Miltiadis Tsilimbaris
- Ophthalmology Department, Medical School of Crete, University of Crete, Heraklion, Greece
| | - Nikolaos Farmakakis
- Ophthalmology Department, Medical School of Patras, University of Patras, Patras, Greece
| |
Collapse
|
47
|
Kar SS, Cetin H, Lunasco L, Le TK, Zahid R, Meng X, Srivastava SK, Madabhushi A, Ehlers JP. OCT-Derived Radiomic Features Predict Anti-VEGF Response and Durability in Neovascular Age-Related Macular Degeneration. OPHTHALMOLOGY SCIENCE 2022; 2:100171. [PMID: 36531588 PMCID: PMC9754979 DOI: 10.1016/j.xops.2022.100171] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/09/2022] [Revised: 04/15/2022] [Accepted: 05/12/2022] [Indexed: 06/17/2023]
Abstract
PURPOSE No established biomarkers currently exist for therapeutic efficacy and durability of anti-VEGF therapy in neovascular age-related macular degeneration (nAMD). This study evaluated radiomic-based quantitative OCT biomarkers that may be predictive of anti-VEGF treatment response and durability. DESIGN Assessment of baseline biomarkers using machine learning (ML) classifiers to predict tolerance to anti-VEGF therapy. PARTICIPANTS Eighty-one participants with treatment-naïve nAMD from the OSPREY study, including 15 super responders (patients who achieved and maintained retinal fluid resolution) and 66 non-super responders (patients who did not achieve or maintain retinal fluid resolution). METHODS A total of 962 texture-based radiomic features were extracted from fluid, subretinal hyperreflective material (SHRM), and different retinal tissue compartments of OCT scans. The top 8 features, chosen by the minimum redundancy maximum relevance feature selection method, were evaluated using 4 ML classifiers in a cross-validated approach to distinguish between the 2 patient groups. Longitudinal assessment of changes in different texture-based radiomic descriptors (delta-texture features) between baseline and month 3 also was performed to evaluate their association with treatment response. Additionally, 8 baseline clinical parameters and a combination of baseline OCT, delta-texture features, and the clinical parameters were evaluated in a cross-validated approach in terms of association with therapeutic response. MAIN OUTCOME MEASURES The cross-validated area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to validate the classifier performance. RESULTS The cross-validated AUC by the quadratic discriminant analysis classifier was 0.75 ± 0.09 using texture-based baseline OCT features. The delta-texture features within different OCT compartments between baseline and month 3 yielded an AUC of 0.78 ± 0.08. The baseline clinical parameters sub-retinal pigment epithelium volume and intraretinal fluid volume yielded an AUC of 0.62 ± 0.07. When all the baseline, delta, and clinical features were combined, a statistically significant improvement in the classifier performance (AUC, 0.81 ± 0.07) was obtained. CONCLUSIONS Radiomic-based quantitative assessment of OCT images was shown to distinguish between super responders and non-super responders to anti-VEGF therapy in nAMD. The baseline fluid and SHRM delta-texture features were found to be most discriminating across groups.
Collapse
Key Words
- 3D, 3-dimensional
- AMD, age-related macular degeneration
- AUC, area under the receiver operating characteristic curve
- AUC-PRC, area under the precision recall curve
- IAI, intravitreal aflibercept injection
- ILM, internal limiting membrane
- IRF, intraretinal fluid
- ML, machine learning
- OCT
- QDA, quadratic discriminant analysis
- RFI, retinal fluid index
- RPE, retinal pigment epithelium
- Radiomics
- SHRM, subretinal hyperreflective material
- SRF, subretinal fluid
- SRFI, subretinal fluid index
- TRFI, total retinal fluid index
- Wet age-related macular degeneration
- mRmR, minimum redundancy maximum relevance
- nAMD, neovascular age-related macular degeneration
Collapse
Affiliation(s)
- Sudeshna Sil Kar
- The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio
| | - Hasan Cetin
- The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio
| | - Leina Lunasco
- The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio
| | - Thuy K. Le
- The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio
| | - Robert Zahid
- Novartis Pharmaceuticals, East Hanover, New Jersey
| | - Xiangyi Meng
- Novartis Pharmaceuticals, East Hanover, New Jersey
| | - Sunil K. Srivastava
- The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio
- Vitreoretinal Service, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio
| | - Anant Madabhushi
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio
- Louis Stokes Cleveland Veterans Administration Medical Center, Cleveland, Ohio
| | - Justis P. Ehlers
- The Tony and Leona Campane Center for Excellence in Image-Guided Surgery and Advanced Imaging Research, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio
- Vitreoretinal Service, Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio
| |
Collapse
|
48
|
Au A, Santina A, Abraham N, Levin MF, Corradetti G, Sadda S, Sarraf D. Relationship Between Drusen Height and OCT Biomarkers of Atrophy in Non-Neovascular AMD. Invest Ophthalmol Vis Sci 2022; 63:24. [PMID: 36306145 PMCID: PMC9624265 DOI: 10.1167/iovs.63.11.24] [Citation(s) in RCA: 23] [Impact Index Per Article: 11.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022] Open
Abstract
Purpose To determine if increasing drusen height correlates with predictive optical coherence tomography (OCT) biomarkers of atrophy. Methods Retrospective cross-sectional study that enrolled patients with drusen associated with intermediate AMD. Macular drusen were classified as small, intermediate, large, or very large based on OCT quartile measurement of height. Drusen diameter was also tabulated. The presence and localization of the OCT biomarkers of atrophy were assessed: disruption of the external limiting membrane and ellipsoid zone, intraretinal hyper-reflective foci, RPE disruption, choroidal hypertransmission, and presence of hyporeflective cores. Predictive OCT biomarkers of atrophy were correlated with drusen height. Results A total of 155 eyes from 104 patients met the inclusion and exclusion criteria. The mean age was 75.7 ± 8.7 years, and patients were predominantly female (74.0%). The mean visual acuity was logMAR 0.2 ± 0.2 (Snellen equivalent 20/32). The average drusen height was 134.6 ± 107.5 µm and the greatest horizontal diameter was 970.7 ± 867.4 µm. Disruption of the external limiting membrane and ellipsoid zone, RPE thickening or thinning, intraretinal hyper-reflective foci, choroidal hypertransmission, and presence of hyporeflective cores (P < 0.05) were more common in eyes with large drusen and very large drusen versus small or intermediate drusen. All biomarkers were positively correlated with drusen height. OCT biomarkers of atrophy were predominantly located at the apex of the drusen. Conclusions Predictive OCT biomarkers of atrophy, specifically signs of RPE breakdown and disruption, occur more commonly in large or very large drusen, especially in drusen with greater height and separation of the RPE from the underlying choroid.
Collapse
Affiliation(s)
- Adrian Au
- Retinal Disorders and Ophthalmic Genetics Division, Stein Eye Institute, University of California Los Angeles, Los Angeles, California, United States
| | - Ahmad Santina
- Retinal Disorders and Ophthalmic Genetics Division, Stein Eye Institute, University of California Los Angeles, Los Angeles, California, United States
| | - Neda Abraham
- Retinal Disorders and Ophthalmic Genetics Division, Stein Eye Institute, University of California Los Angeles, Los Angeles, California, United States
| | - Miri Fogel Levin
- Retinal Disorders and Ophthalmic Genetics Division, Stein Eye Institute, University of California Los Angeles, Los Angeles, California, United States
| | - Giulia Corradetti
- Doheny Eye Institute, Department of Ophthalmology, University of California, Los Angeles, Los Angeles, California, United States
| | - SriniVas Sadda
- Doheny Eye Institute, Department of Ophthalmology, University of California, Los Angeles, Los Angeles, California, United States
| | - David Sarraf
- Retinal Disorders and Ophthalmic Genetics Division, Stein Eye Institute, University of California Los Angeles, Los Angeles, California, United States
- Greater Los Angeles VA Healthcare Center, Los Angeles, California, United States
| |
Collapse
|
49
|
Bui PTA, Reiter GS, Fabianska M, Waldstein SM, Grechenig C, Bogunovic H, Arikan M, Schmidt-Erfurth U. Fundus autofluorescence and optical coherence tomography biomarkers associated with the progression of geographic atrophy secondary to age-related macular degeneration. Eye (Lond) 2022; 36:2013-2019. [PMID: 34400806 PMCID: PMC9499954 DOI: 10.1038/s41433-021-01747-z] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2021] [Revised: 07/27/2021] [Accepted: 08/04/2021] [Indexed: 11/09/2022] Open
Abstract
OBJECTIVES To investigate the impact of qualitatively graded and deep learning quantified imaging biomarkers on growth of geographic atrophy (GA) secondary to age-related macular degeneration. METHODS This prospective study included 1062 visits of 181 eyes of 100 patients with GA. Spectral-domain optical coherence tomography (SD-OCT) and fundus autofluorescence (FAF) images were acquired at each visit. Hyperreflective foci (HRF) were quantitatively assessed in SD-OCT volumes using a validated deep learning algorithm. FAF images were graded for FAF patterns, subretinal drusenoid deposits (SDD), GA lesion configuration and atrophy enlargement. Linear mixed models were calculated to investigate associations between all parameters and GA progression. RESULTS FAF patterns were significantly associated with GA progression (p < 0.001). SDD was associated with faster GA growth (p = 0.005). Eyes with higher HRF concentrations showed a trend towards faster GA progression (p = 0.072) and revealed a significant impact on GA enlargement in interaction with FAF patterns (p = 0.01). The fellow eye status had no significant effect on lesion enlargement (p > 0.05). The diffuse-trickling FAF pattern exhibited significantly higher HRF concentrations than any other pattern (p < 0.001). CONCLUSION Among a wide range of investigated biomarkers, SDD and FAF patterns, particularly in interaction with HRF, significantly impact GA progression. Fully automated quantification of retinal imaging biomarkers such as HRF is both reliable and merited as HRF are indicators of retinal pigment epithelium dysmorphia, a central pathogenetic mechanism in GA. Identifying disease markers using the combination of FAF and SD-OCT is of high prognostic value and facilitates individualized patient management in a clinical setting.
Collapse
Affiliation(s)
- Patricia T A Bui
- Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Gregor S Reiter
- Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Maria Fabianska
- Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Sebastian M Waldstein
- Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Christoph Grechenig
- Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Hrvoje Bogunovic
- Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Mustafa Arikan
- Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria
| | - Ursula Schmidt-Erfurth
- Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria.
| |
Collapse
|
50
|
Artificial Intelligence in Biological Sciences. Life (Basel) 2022; 12:life12091430. [PMID: 36143468 PMCID: PMC9505413 DOI: 10.3390/life12091430] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2022] [Revised: 08/25/2022] [Accepted: 09/10/2022] [Indexed: 12/03/2022] Open
Abstract
Artificial intelligence (AI), currently a cutting-edge concept, has the potential to improve the quality of life of human beings. The fields of AI and biological research are becoming more intertwined, and methods for extracting and applying the information stored in live organisms are constantly being refined. As the field of AI matures with more trained algorithms, the potential of its application in epidemiology, the study of host–pathogen interactions and drug designing widens. AI is now being applied in several fields of drug discovery, customized medicine, gene editing, radiography, image processing and medication management. More precise diagnosis and cost-effective treatment will be possible in the near future due to the application of AI-based technologies. In the field of agriculture, farmers have reduced waste, increased output and decreased the amount of time it takes to bring their goods to market due to the application of advanced AI-based approaches. Moreover, with the use of AI through machine learning (ML) and deep-learning-based smart programs, one can modify the metabolic pathways of living systems to obtain the best possible outputs with the minimal inputs. Such efforts can improve the industrial strains of microbial species to maximize the yield in the bio-based industrial setup. This article summarizes the potentials of AI and their application to several fields of biology, such as medicine, agriculture, and bio-based industry.
Collapse
|