A5048847079- Glaucoma and retinal disorders
- Biometric Identification and Security
- Ocular Surface and Contact Lens
- Face recognition and analysis
- Face and Expression Recognition
- Corneal surgery and disorders
- Retinal Imaging and Analysis
- Optical Imaging and Spectroscopy Techniques
- COVID-19 and healthcare impacts
- COVID-19 Clinical Research Studies
- COVID-19 diagnosis using AI
- Retinal Diseases and Treatments
- Non-Invasive Vital Sign Monitoring
- Pain Mechanisms and Treatments
- Mobile Health and mHealth Applications
- Medical Image Segmentation Techniques
- Medical Imaging and Analysis
- Dental Radiography and Imaging
- User Authentication and Security Systems
- Advanced Steganography and Watermarking Techniques
- Psoriasis: Treatment and Pathogenesis
- Genomic variations and chromosomal abnormalities
- Digital Mental Health Interventions
- Industrial Vision Systems and Defect Detection
- Gait Recognition and Analysis
Toshiba (United Kingdom)
2014-2016
University of Manchester
2010-2015
NIHR Wellcome Trust Southampton Clinical Research Facility
2015
Manchester Academic Health Science Centre
2014
Manchester University NHS Foundation Trust
2012
National Health Service
2012
Juvenile Diabetes Research Foundation
2012
Newcastle University
2005-2008
University of Newcastle Australia
2008
OBJECTIVE Quantitative assessment of small fiber damage is key to the early diagnosis and progression or regression diabetic sensorimotor polyneuropathy (DSPN). Intraepidermal nerve density (IENFD) current gold standard, but corneal confocal microscopy (CCM), an in vivo ophthalmic imaging modality, has potential be a noninvasive objective image biomarker for identifying damage. The purpose this study was determine diagnostic performance CCM IENFD by using guidelines as reference standard....
Purpose.: To assess the diagnostic validity of a fully automated image analysis algorithm in vivo confocal microscopy images quantifying corneal subbasal nerves to diagnose diabetic neuropathy. Methods.: One hundred eighty-six patients with type 1 and 2 diabetes mellitus (T1/T2DM) 55 age-matched controls underwent assessment neuropathy bilateral (IVCCM). Corneal nerve fiber density (CNFD), branch (CNBD), length (CNFL) were quantified expert, manual, fully-automated analysis. The areas under...
Purpose: To establish intraobserver and interobserver repeatability, agreement, symmetry of corneal nerve fiber (NF) morphology in healthy subjects using vivo confocal microscopy. Methods: Nineteen underwent microscopy (Heidelberg Retinal Tomograph III Rostock Cornea Module) at baseline 7 days apart. Bland–Altman plots were generated to assess the intraclass correlation coefficient repeatability calculated estimate for NF density (numbers per square millimeter), branch (NBD; numbers length...
We describe and evaluate an automated software tool for nerve-fiber detection quantification in corneal confocal microscopy (CCM) images, combining sensitive nerve- fiber with morphological descriptors.We have evaluated the of Diabetic Sensorimotor Polyneuropathy (DSPN) using both new previously published features. The evaluation used 888 images from 176 subjects (84 controls 92 patients type 1 diabetes). patient group was further subdivided into those ( n = 63) without 29) DSPN.We achieve...
Purpose: To analyze the repeatability of measuring nerve fiber length (NFL) from images human corneal subbasal plexus using semiautomated software. Methods: Images were captured corneas 50 subjects with type 2 diabetes mellitus who showed varying severity neuropathy, Heidelberg Retina Tomograph 3 Rostock Corneal Module. Semiautomated analysis software was independently used by two observers to determine NFL plexus. This procedure undertaken on occasions, days apart. Results: The intraclass...
In this paper, we present a new technique to protect the face biometric during recognition, using so called cancellable biometric. The is based on image-based (statistical) recognition 2DPCA algorithm. data transformed its domain polynomial functions and co-occurrence matrices. Original facial images are non-linearly by function whose parameters can be change accordingly issuing version of secure template. Co-occurrence matrices also used in transform generate distinctive feature vector...
Neuropad is currently a categorical visual screening test that identifies diabetic patients at risk of foot ulceration. The diagnostic performance was compared between the and continuous (image-analysis (Sudometrics)) outputs to diagnose peripheral neuropathy (DPN). 110 subjects with type 1 2 diabetes underwent assessment Neuropad, Neuropathy Disability Score (NDS), peroneal motor nerve conduction velocity (PMNCV), sural action potential (SNAP), Deep Breathing-Heart Rate Variability...
The automatic detection and localization of anatomical landmarks has wide application, including intra interpatient registration, study location navigation, the targeting specialized algorithms. In this paper, we demonstrate 127 anatomically defined distributed throughout body, excluding arms. Landmarks are on skeleton, vasculature major organs. Our approach builds classification forests method,<sup>1</sup> using classifier with simple image features which can be efficiently computed. For...
The COVID-19 pandemic has created an urgent need for robust, scalable monitoring tools supporting stratification of high-risk patients. This research aims to develop and validate prediction models, using the UK Biobank, estimate mortality risk in confirmed cases. From 11,245 participants testing positive COVID-19, we a data-driven random forest classification model with excellent performance (AUC: 0.91), baseline characteristics, pre-existing conditions, symptoms, vital signs, such that...
Mobile health (mHealth) offers potential benefits to both patients and healthcare systems. Existing remote technologies measure respiratory rates have limitations such as cost, accessibility reliability. Using smartphone sensors may offer a solution these issues.The aim of this study was conduct comprehensive assessment novel mHealth application designed using movement sensors.In Study 1, 15 participants simultaneously measured their with the app Food Drug Administration-cleared reference...
Although, biometrics provide high-confidence and trusted security, they suffer from a fatal weakness that emerges permanence limitation in quantities. Such drawback puts biometric data under substantial risk of fraudulent, which makes the replacement traditional authentication systems infeasible with lack proper protection. This paper presents novel protection method to generate secure facial templates used statistical-based recognition algorithms such as 2DPCA. Original are polynomially...
Abstract The COVID-19 pandemic has created an urgent need for robust, scalable monitoring tools supporting stratification of high-risk patients. This research aims to develop and validate prediction models, using the UK Biobank, estimate mortality risk in confirmed cases. From 11,245 participants testing positive COVID-19, we a data-driven random forest classification model with excellent performance (AUC: 0.91), baseline characteristics, pre-existing conditions, symptoms, vital signs, such...
Without sufficient protection during the entire authentication procedure, biometrics cannot supersede traditional methods. In this paper a new method of cancellable biometric transformation is presented. Random finite spaces are utilized to map original facial into secure domain, in which can be accurately performed using PCA. Each face mapped up independent random generate (cancellable) template. Replacing previous results template, issued from same image. Evaluation has shown significant...
The authors present a secure facial recognition system. biometric data are transformed to the cancellable domain using high-order polynomial functions and co-occurrence matrices. proposed method has provided both high-recognition accuracy protection. Protection of relies on functions, where new reissued can be obtained by changing parameters. Besides protection data, reconstructed matrices also contributed enhancement. Hadamard product is used reconstruct measure shown high flexibility in...
Biometrics has become a strong candidate to replace traditional authentication systems however biometric data in itself is vulnerable and requires protection. This paper presents new method protect face using one-way transformation which original images cannot be retrieved. The secure reissueable templates are generated by utilizing the Radon transformed signatures of multi-space random projection. Using an image-based statistical algorithm, conducted on without need reverse them back....