A5015881286- Retinal Imaging and Analysis
- Retinal Diseases and Treatments
- Retinal and Optic Conditions
- Glaucoma and retinal disorders
- Ocular Diseases and Behçet’s Syndrome
- Artificial Intelligence in Healthcare and Education
- Retinal Development and Disorders
- Ophthalmology and Visual Impairment Studies
- Cerebral Venous Sinus Thrombosis
- AI in cancer detection
- COVID-19 diagnosis using AI
- Ocular Oncology and Treatments
- Optical Coherence Tomography Applications
- Acute Ischemic Stroke Management
- Ophthalmology and Visual Health Research
- Retinal and Macular Surgery
- Syphilis Diagnosis and Treatment
- Retinopathy of Prematurity Studies
- Corneal surgery and disorders
- Systemic Lupus Erythematosus Research
- Digital Imaging for Blood Diseases
- Healthcare Systems and Technology
- Corneal Surgery and Treatments
- Telemedicine and Telehealth Implementation
- Patient Satisfaction in Healthcare
Moorfields Eye Hospital NHS Foundation Trust
2015-2025
University College London
2016-2025
Moorfields Eye Hospital
2016-2025
Institute of Ophthalmology
2021-2024
National Institute for Health Research
2019-2024
University College Lahore
2024
University of Manchester
2014-2023
NIHR Moorfields Biomedical Research Centre
2019-2023
UK Biobank
2023
National Health Service
2019-2022
Abstract Medical artificial intelligence (AI) offers great potential for recognizing signs of health conditions in retinal images and expediting the diagnosis eye diseases systemic disorders 1 . However, development AI models requires substantial annotation are usually task-specific with limited generalizability to different clinical applications 2 Here, we present RETFound, a foundation model that learns generalizable representations from unlabelled provides basis label-efficient adaptation...
BackgroundDeep learning has the potential to transform health care; however, substantial expertise is required train such models. We sought evaluate utility of automated deep software develop medical image diagnostic classifiers by health-care professionals with no coding—and learning—expertise.MethodsWe used five publicly available open-source datasets: retinal fundus images (MESSIDOR); optical coherence tomography (OCT) (Guangzhou Medical University and Shiley Eye Institute, version 3);...
Abstract A number of large technology companies have created code-free cloud-based platforms that allow researchers and clinicians without coding experience to create deep learning algorithms. In this study, we comprehensively analyse the performance featureset six platforms, using four representative cross-sectional en-face medical imaging datasets image classification models. The mean (s.d.) F1 scores across for all model–dataset pairs were as follows: Amazon, 93.9 (5.4); Apple, 72.0...
Cadaveric studies have shown disease-related neurodegeneration and other morphological abnormalities in the retina of individuals with Parkinson disease (PD); however, it remains unclear whether this can be reliably detected vivo imaging. We investigated inner retinal anatomy, measured using optical coherence tomography (OCT), prevalent PD subsequently assessed association these markers development a prospective research cohort.
In recent years, there has been considerable interest in the prospect of machine learning models demonstrating expert-level diagnosis multiple disease contexts. However, is concern that excitement around this field may be associated with inadequate scrutiny methodology and insufficient adoption scientific good practice studies involving artificial intelligence health care. This article aims to empower clinicians researchers critically appraise clinical applications learning, through: (1)...
PurposeTo apply a deep learning algorithm for automated, objective, and comprehensive quantification of OCT scans to large real-world dataset eyes with neovascular age-related macular degeneration (AMD) make the raw segmentation output data openly available further research.DesignRetrospective analysis images from Moorfields Eye Hospital AMD Database.ParticipantsA total 2473 first-treated 493 second-treated that commenced therapy between June 2012 2017.MethodsA was used segment all baseline...
Abstract Deep learning may transform health care, but model development has largely been dependent on availability of advanced technical expertise. Herein we present the a deep by clinicians without coding, which predicts reported sex from retinal fundus photographs. A was trained 84,743 photos UK Biobank dataset. External validation performed 252 tertiary ophthalmic referral center. For internal validation, area under receiver operating characteristic curve (AUROC) code free (CFDL) 0.93....
Background Hospital Eye Services (HES) in the UK face an increasing number of optometric referrals driven by progress retinal imaging. The National Health Service (NHS) published a 10-year strategy (NHS Long-Term Plan) to transform services meet this challenge. In study, we implemented cloud-based referral platform improve communication between optometrists and ophthalmologists. Methods Retrospective cohort study conducted at Moorfields Hospital, Croydon Foundation Trust, London, UK)....
Geographic atrophy is a major vision-threatening manifestation of age-related macular degeneration, one the leading causes blindness globally. has no proven treatment or method for easy detection. Rapid, reliable, and objective detection quantification geographic from optical coherence tomography (OCT) retinal scans necessary disease monitoring, prognostic research, to serve as clinical endpoints therapy development. To this end, we aimed develop validate fully automated detect quantify...
Importance The potential association of schizophrenia with distinct retinal changes is clinical interest but has been challenging to investigate because a lack sufficiently large and detailed cohorts. Objective To the between biomarkers from multimodal imaging (oculomics) in real-world population. Design, Setting, Participants This cross-sectional analysis used data retrospective cohort 154 830 patients 40 years older AlzEye study, which linked ophthalmic hospital admission across England....
Purpose To benchmark the human and machine performance of spectral-domain (SD) swept-source (SS) optical coherence tomography (OCT) image segmentation, i.e., pixel-wise classification, for compartments vitreous, retina, choroid, sclera. Methods A convolutional neural network (CNN) was trained on OCT B-scan images annotated by a senior ground truth expert retina specialist to segment posterior eye compartments. Independent data sets (30 SDOCT 30 SSOCT) were manually segmented three classes...
Background The increasing incidence of medical retinal diseases has created capacity issues across UK. In this study, we describe the implementation and outcomes virtual retina clinics (VMRCs) at Moorfields Eye Hospital, South Division, London. It represents a promising solution to ensure that patients are seen treated in timely fashion Methods First attendances VMRC (September 2016–May 2017) were included. was open non-urgent external referrals existing face-to-face clinic (F2FC). All...
Purpose To evaluate the utility of widefield optical coherence tomography angiography (WF-OCTA) compared with clinical examination in grading diabetic retinopathy patients diagnosed clinically proliferative (PDR) or severe non-proliferative (NPDR). Design This retrospective observational case series included PDR NPDR. Patients underwent standard and WF-OCTA imaging (PLEX Elite 9000, Carl Zeiss Meditec AG) using 12×12 montage scans between August 2018 January 2019. Two trained graders...
To examine the associations of air pollution with both self-reported age-related macular degeneration (AMD), and in vivo measures retinal sublayer thicknesses.We included 115 954 UK Biobank participants aged 40-69 years old this cross-sectional study. Ambient particulate matter, nitrogen dioxide (NO2) oxides (NOx). Participants ocular conditions, high refractive error (< -6 or > +6 diopters) poor spectral-domain optical coherence tomography (SD-OCT) image were excluded. Self-reported AMD was...
We sought to develop and validate a deep learning model for segmentation of 13 features associated with neovascular atrophic age-related macular degeneration (AMD).Development validation deep-learning feature segmentation.Data development were obtained from 307 optical coherence tomography volumes. Eight experienced graders manually delineated all abnormalities in 2712 B-scans. A neural network was trained these data perform voxel-level the most common (features). For evaluation, 112 B-scans...
To describe past trends and future projections for the number of intravitreal injections being administered at a large tertiary hospital in London, United Kingdom.Retrospective data from Moorfields Eye Hospital were collected using electronic medical record system. Descriptive statistics used to visualise overall trends. Time series forecasting was predict that will be up including year 2029.The has increased nearly 11-fold 2009 2019, with total 44,924 delivered 2019. The majority given...
Purpose Retinal signatures of systemic disease (‘oculomics’) are increasingly being revealed through a combination high-resolution ophthalmic imaging and sophisticated modelling strategies. Progress is currently limited not mainly by technical issues, but the lack large labelled datasets, sine qua non for deep learning. Such data derived from prospective epidemiological studies, in which retinal typically unimodal, cross-sectional, modest number relates to cohorts, enriched with...
PurposeRare disease diagnosis is challenging in medical image-based artificial intelligence due to a natural class imbalance datasets, leading biased prediction models. Inherited retinal diseases (IRDs) are research domain that particularly faces this issue. This study investigates the applicability of synthetic data improving AI-enabled IRDs using Generative Adversarial Networks (GANs).DesignDiagnostic gene-labeled fundus autofluorescence (FAF) IRD images Deep Learning...