A5036785197- Retinal Imaging and Analysis
- Retinal Diseases and Treatments
- Glaucoma and retinal disorders
- Digital Imaging for Blood Diseases
- Retinal and Optic Conditions
- Medical Image Segmentation Techniques
- Intraocular Surgery and Lenses
- Corneal surgery and disorders
- Fuzzy Logic and Control Systems
- Oral and Maxillofacial Pathology
- Ophthalmology and Visual Impairment Studies
- Head and Neck Cancer Studies
- Smart Agriculture and AI
- Radiomics and Machine Learning in Medical Imaging
- Neural Networks and Applications
- Leaf Properties and Growth Measurement
- Oral Health Pathology and Treatment
- Retinopathy of Prematurity Studies
- AI in cancer detection
- Cancer Diagnosis and Treatment
- Distributed Control Multi-Agent Systems
- Fuzzy Systems and Optimization
- Anorectal Disease Treatments and Outcomes
- Artificial Intelligence in Healthcare
- Retinal and Macular Surgery
Kingston University
2016-2025
Kingston University
2013-2025
King's College London
1998-2024
UK Biobank
2021-2023
Moorfields Eye Hospital NHS Foundation Trust
2023
University College London
2023
University of Oxford
2019
Chalmers University of Technology
2017
University of Gothenburg
2017
National University of Sciences and Technology
2016
This paper presents a new supervised method for segmentation of blood vessels in retinal photographs. uses an ensemble system bagged and boosted decision trees utilizes feature vector based on the orientation analysis gradient field, morphological transformation, line strength measures, Gabor filter responses. The encodes information to handle healthy as well pathological image. is evaluated publicly available DRIVE STARE databases, frequently used this purpose also public vessel reference...
To examine the agreement of a novel computer program measuring retinal vessel tortuosity with subjective assessment in school-aged children.Cross-sectional study 387 vessels (193 arterioles, 194 veins) from 28 eyes 14 children (aged 10 years). Retinal digital images were analyzed using Computer Assisted Image Analysis Retina (CAIAR) program, including measures tortuosity. Vessels graded (from 0 = none; to 5 tortuous) independently by two observers. Interobserver was assessed kappa...
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...
Oral cancer is a major global health issue accounting for 177,384 deaths in 2018 and it most prevalent low- middle-income countries. Enabling automation the identification of potentially malignant lesions oral cavity would lead to low-cost early diagnosis disease. Building large library well-annotated key. As part MeMoSA <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">®</sup> (Mobile Mouth Screening Anywhere) project, images are currently...
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.
Purpose: To determine whether posterior capsule opacification (PCO) is influenced by intraocular lens (IOL) material. Setting: A British teaching hospital eye department. Methods: Ninety eyes were prospectively randomized to receive a poly(methyl methacrylate) (PMMA), silicone, or AcrySof® IOL. All lenses had 6,0 mm optics and PMMA haptics. standardized surgical protocol was performed single surgeon using an extracapsular technique with capsulorhexis. Patients having complications excluded,...
Exudates are the primary sign of Diabetic Retinopathy. Early detection can potentially reduce risk blindness. An automatic method to detect exudates from low-contrast digital images retinopathy patients with non-dilated pupils using a Fuzzy C-Means (FCM) clustering is proposed. Contrast enhancement preprocessing applied before four features, namely intensity, standard deviation on hue and number edge pixels, extracted supply as input parameters coarse segmentation FCM method. The first...
Automated retinal image analysis has been emerging as an important diagnostic tool for early detection of eye-related diseases such glaucoma and diabetic retinopathy. In this paper, we have presented a robust methodology optic disc boundary segmentation, which can be seen the preliminary step in development computer-assisted system images. The proposed method is based on morphological operations, Circular Hough transform Grow Cut algorithm. operators are used to enhance remove vasculature...
We examine whether inclusion of artificial intelligence (AI)-enabled retinal vasculometry (RV) improves existing risk algorithms for incident stroke, myocardial infarction (MI) and circulatory mortality.AI-enabled vessel image analysis processed images from 88 052 UK Biobank (UKB) participants (aged 40-69 years at capture) 7411 European Prospective Investigation into Cancer (EPIC)-Norfolk 48-92). Retinal arteriolar venular width, tortuosity area were extracted. Prediction models developed in...
Exudates are among the preliminary signs of diabetic retinopathy, a major cause vision loss in patients. Early detection exudates could improve patients' chances to avoid blindness. In this paper, we present series experiments on feature selection and classification using naive Bayes support vector machine (SVM) classifiers. We first fit model training set consisting 15 features extracted from each 115,867 positive examples exudate pixels an equal number negative examples. then perform...
Objective— To examine the association between cardiovascular risk factors and retinal arteriolar tortuosity in a multi-ethnic child population. Methods Results— Cross sectional study of 986 UK primary school children South Asian, black African Caribbean, white European origin aged 10 to 11 years. Anthropometric measurements imaging were carried out fasting blood sample collected. Digital images arterioles analyzed using validated semiautomated measure tortuosity. Associations cardiometabolic...
The potential of type-2 fuzzy sets to manage high levels uncertainty in the subjective knowledge experts or numerical information has focused on control and pattern classification systems recent years. One main challenges designing a logic system (FLS) is how estimate parameters membership function (T2MF) footprint (FOU) from imperfect noisy datasets. This paper presents an automatic approach learn tune Gaussian interval functions (IT2MFs) with application multidimensional problems. T2MFs...