A5021191757- Cardiac Imaging and Diagnostics
- Advanced MRI Techniques and Applications
- Advanced X-ray and CT Imaging
- AI in cancer detection
- Pulmonary Hypertension Research and Treatments
- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Cardiovascular Function and Risk Factors
- Radiation Dose and Imaging
- Pediatric Urology and Nephrology Studies
- Artificial Intelligence in Healthcare and Education
- Ureteral procedures and complications
- Renal and Vascular Pathologies
- Genetic and Kidney Cyst Diseases
- Trigeminal Neuralgia and Treatments
- Artificial Intelligence in Healthcare
- Radiology practices and education
- Kidney Stones and Urolithiasis Treatments
- Neurological disorders and treatments
- ECG Monitoring and Analysis
- Digital Radiography and Breast Imaging
- Thyroid Cancer Diagnosis and Treatment
- Cardiac Structural Anomalies and Repair
- Colorectal Cancer Screening and Detection
- Digital Imaging for Blood Diseases
Sheffield Teaching Hospitals NHS Foundation Trust
2014-2025
Imperial Valley College
2025
Northern General Hospital
2021-2023
Royal Hallamshire Hospital
2011-2018
University of Sheffield
2008-2017
Chinook Regional Hospital
2015
McMaster University
2012
Regional Cancer Center
2011
Womack Army Medical Center
2010
Royal Derby Hospital
1981
The results of treating 143 patients with trigeminal neuralgia carbamazepine (CBZ) over a 16-year period have been reviewed. drug was effective initially few mild side effects in 99 (69%). Of these, 19 developed resistance later, i.e. between 2 months and 10 years after commencing treatment, required alternative measures. the remaining 80 (56%), 49 for 1-4 31 5-16 years. Thirty-six (25%) failed to respond CBZ measures, as did 8 (6%) who were intolerant drug. One patient CBZ-induced water...
Pulmonary arterial hypertension (PAH) is a progressive condition with high mortality. Quantitative cardiovascular magnetic resonance (CMR) imaging metrics in PAH target individual cardiac structures and have diagnostic prognostic utility but are challenging to acquire. The primary aim of this study was develop test tensor-based machine learning approach holistically identify features using CMR, secondarily, visualize interpret key discriminative associated PAH.Consecutive treatment naive...
Objectives Early identification of lung cancer on chest radiographs improves patient outcomes. Artificial intelligence (AI) tools may increase diagnostic accuracy and streamline this pathway. This study evaluated the performance commercially available AI-based software trained to identify cancerous nodules radiographs. Design retrospective included primary care acquired in a UK centre. The each radiograph independently outputs were compared with two reference standards: (1) radiologist...
Semi-quantification methods are well established in the clinic for assisted reporting of (I123) Ioflupane images. Arguably, these limited diagnostic tools. Recent research has demonstrated potential improved classification performance offered by machine learning algorithms. A direct comparison between is required to establish whether a move towards widespread clinical adoption algorithms justified. This study compared three with that range semi-quantification methods, using Parkinson's...
Introduction Computed tomography pulmonary angiography (CTPA) is an essential test in the work-up of suspected vascular disease including hypertension and embolism. Cardiac great vessel assessments on CTPA are based visual assessment manual measurements which known to have poor reproducibility. The primary aim this study was develop automated whole heart segmentation (four chamber vessels) model for CTPA. Methods A nine structure semantic vessels developed using 200 patients (80/20/100...
Glioblastoma (GBM) is an extremely infiltrative brain cancer that impossible to fully remove surgically and almost always recurs at the borders of resection cavity. There increasing focus on inducing cell death using magneto-mechanical therapy (MMT), which involves energy conversion external low-frequency magnetic field into mechanical forces nanoparticles. Here, we combined MMT with enhanced radiotherapy (RT)─the standard care treatment for GBM─to increase efficiency gold-iron nanowires...
Objectives: The aim of this study is to develop a scar detection method for routine computed tomography angiography (CTA) imaging using deep convolutional neural networks (CNN), which relies solely on anatomical information as input and compatible with existing clinical workflows. Background: Identifying cardiac patients tissue important assisting diagnosis guiding interventions. Late gadolinium enhancement (LGE) magnetic resonance (MRI) the gold standard imaging; however, there are common...
IntroductionAccurate tools to inform individual prognosis in patients with autosomal dominant polycystic kidney disease (ADPKD) are lacking. Here, we report an artificial intelligence (AI) generated method for routinely measuring total volume (TKV).MethodsAn ensemble U-net algorithm was created using the nnUNet approach. The training and internal cross-validation cohort consisted of all 1.5T MRI data acquired 5 different scanners (454 kidneys, 227 scans) CYSTic consortium which first...
Purpose: To report the results of Mersilene mesh wrapped hydroxyapatite orbital implantation.Materials and methods: Records 63 patients operated between April 2002 March 2006 were retrospectively reviewed. Parameters studied included sex, cause enucleation, length follow-up after operation, implant exposure, secondary implantation, surgeon experience. Student's t-test χ2 used for comparison group having exposure those without exposure.Results: The rate with use was found to be 4.7%. Gender...
3D reconstruction and printing of subject-specific anatomy is a promising technology for supporting clinicians in the visualisation disease progression planning surgical intervention. In this context, model typically obtained from segmentation magnetic resonance imaging (MRI), computed tomography (CT) or echocardiography images. Although these modalities allow tissues vivo, assessment quality limited by lack reference geometry as unknown prior to image acquisition. work, an optical method...
Left atrial volume is commonly estimated using the bi-plane area-length method from two-chamber (2CH) and four-chamber (4CH) long axes views. However, this can be inaccurate due to a violation of geometric assumptions. We aimed develop deep learning neural network infer 3D left shape, surface area 2CH 4CH A UNet was trained tested segmentations generated coronary computed tomography angiography (CCTA) (n = 1700, with 1400/100/200 cases for training/validating/testing). An independent test...
For (123I)FP-CIT imaging, a number of algorithms have shown high performance in distinguishing normal patient images from those with disease, but none yet been tested as part reporting workflows. This study aims to evaluate the impact on reporters' computer-aided diagnosis (CADx) tool developed established machine learning technology. Three experienced reporters (two radiologists and one clinical scientist) were asked visually score 155 reconstructed research 5-point diagnostic confidence...
The aim of this retrospective investigation was to devise a protocol for obtaining consistent myocardial counts patients attending perfusion imaging.A total 229 were included in the study sample. For each rest single-photon emission computed tomography data set, three-dimensional ellipse manually defined isolate left ventricle. count rate per voxel measured from threshold region interest covering normally perfused myocardium (70-100% maximum counts). Data normalized net administered activity...
Objectives With disease-modifying therapies in development for neurological disorders, quantitative brain imaging techniques become increasingly relevant objective early diagnosis and assessment of response to treatment. The aim this study was evaluate the use Brain SPECT PET scans UK explore drivers barriers using analysis through an online survey. Methods A web-based survey with 27 questions used capture a snapshot UK. included multiple-choice assessing availability quantification DaTscan,...
Abstract BACKGROUND AND AIMS A major barrier to the routine adoption of total kidney volume (TKV) as a clinical biomarker disease for autosomal dominant polycystic (ADPKD) is significant human operator time required even by experienced analysts (typically, 45–90 min per patient). Several groups have investigated automated and semi-automated segmentation methods either reduce or eliminate interaction required. However, such tools mostly been developed using data from single centers, which may...
A national audit of quantitative thyroid uptake imaging was conducted by the Nuclear Medicine Software Quality Group Institute Physics and Engineering in 2014/2015. The aims were to measure assess variability results across UK compare local protocols with British Society (BNMS) guidelines.Participants invited through a combination emails on public mailbase targeted invitations from regional co-ordinators. All participants given set images which calculate measures spreadsheet for capturing...
The Alderson striatal phantom is frequently used to assess I-FP-CIT (Ioflupane) image quality and test semi-quantification software. However, its design associated with a number of limitations, in particular: unrealistic appearances inflexibility. A new physical approach proposed on the basis subresolution technology. incorporates thin slabs attenuating material generated through additive manufacturing, paper sheets radioactive ink patterns printed their surface, created conventional inkjet...
Foreign bodies in the ureter are extremely rare. We report a case of an 82-year-old man who, after incidental presentation with asymptomatic hydroureteronephrosis, had intraureteric foreign body. The patient was managed atraumatic endoscopic extraction specimen.