A5069398400- Cardiac Imaging and Diagnostics
- Advanced MRI Techniques and Applications
- Cardiovascular Function and Risk Factors
- Advanced X-ray and CT Imaging
- Cardiovascular Disease and Adiposity
- Cardiovascular Health and Disease Prevention
- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Medical Image Segmentation Techniques
- Cardiomyopathy and Myosin Studies
- Cerebrovascular and Carotid Artery Diseases
- Retinal Imaging and Analysis
- Aortic Disease and Treatment Approaches
- Renal cell carcinoma treatment
- Cardiac electrophysiology and arrhythmias
- Cardiac Fibrosis and Remodeling
- Viral Infections and Immunology Research
- Face recognition and analysis
- Aortic aneurysm repair treatments
- Acute Myocardial Infarction Research
- Lipoproteins and Cardiovascular Health
- COVID-19 diagnosis using AI
University of Oxford
2019-2024
John Radcliffe Hospital
2019-2024
Royal Marsden NHS Foundation Trust
2023
British Heart Foundation
2022
Oxford BioMedica (United Kingdom)
2021-2022
National Institute for Health Research
2021-2022
National Health Service
2021
Resonance Research (United States)
2019
Recent developments in artificial intelligence have generated increasing interest to deploy automated image analysis for diagnostic imaging and large-scale clinical applications. However, inaccuracy from methods could lead incorrect conclusions, diagnoses or even harm patients. Manual inspection potential inaccuracies is labor-intensive time-consuming, hampering progress towards fast accurate reporting high volumes. To promote reliable fully-automated analysis, we propose a quality...
Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging is the gold standard for noninvasive myocardial tissue characterization but requires intravenous contrast agent administration. It highly desired to develop a agent-free technology replace LGE faster and cheaper CMR scans.
Cardiac magnetic resonance quantitative T1-mapping is increasingly used for advanced myocardial tissue characterisation. However, cardiac or respiratory motion can significantly affect the diagnostic utility of T1-maps, and thus artefact detection critical quality control clinically-robust T1 measurements. Manual T1-maps may provide reassurance, but laborious prone to error. We present a deep learning approach with attention supervision automated in T1-mapping. Firstly, we customised...
Cardiac magnetic resonance native T1-mapping provides noninvasive, quantitative, and contrast-free myocardial characterization. However, its predictive value in population cohorts has not been studied. The associations of T1 with incident events were evaluated 42,308 UK Biobank participants over 3.17 ± 1.53 years prospective follow-up. Native was performed 1 midventricular short-axis slice using the Shortened Modified Look-Locker Inversion recovery technique (WIP780B) 1.5-T scanners (Siemens...
Introduction Aortic distensibility can be calculated using semi-automated methods to segment the aortic lumen on cine CMR (Cardiovascular Magnetic Resonance) images. However, these require visual quality control and manual localization of region interest (ROI) ascending (AA) proximal descending (PDA) aorta, which limit analysis in large-scale population-based studies. Using 5100 scans from UK Biobank, this study sought develop validate a fully automated method 1) detect locate ROIs AA PDA,...
Abstract Background The aim of this work is to evaluate the performance radiomics predictions for a range molecular, genomic and clinical targets in patients with clear cell renal carcinoma (ccRCC) demonstrate impact novel feature selection strategies sub-segmentations on model interpretability. Methods Contrast-enhanced CT scans from first 101 recruited TRACERx Renal Cancer study (NCT03226886) were used derive classification models predict 20 histopathology target variables. Manual 3D...
BackgroundCardiovascular magnetic resonance T1-mapping is increasingly used for tissue characterization, commonly based on Modified Look-Locker Inversion recovery (MOLLI). However, there are numerous MOLLI variants with differing normal ranges. This lack of standardization presents confusion and difficulty in inter-center comparisons, hindering widespread adoption T1-mapping.MethodsTo address this, we performed a structured literature search native left ventricular myocardial healthy humans...
Acute ST-segment elevation myocardial infarction (STEMI) has effects on the myocardium beyond immediate infarcted territory. However, pathophysiologic changes in noninfarcted and their prognostic implications remain unclear.The purpose of this study was to evaluate long-term value acute both post-STEMI.Patients with STEMI undergoing primary percutaneous coronary intervention underwent evaluation blood biomarkers cardiac magnetic resonance (CMR) at 2 days 6 months, follow-up for major adverse...
BackgroundAdenosine stress T1-mapping on cardiovascular magnetic resonance (CMR) can differentiate between normal, ischemic, infarcted, and remote myocardial tissue classes without the need for contrast agents. Regadenoson, a selective coronary vasodilator, is often used in perfusion imaging when adenosine contra-indicated, has advantages ease of administration, safety profile, clinical workflow. We aimed to characterize regadenoson response healthy individuals, investigate its ability...
Abstract Stress and rest T1-mapping may assess for myocardial ischemia extracellular volume (ECV). However, the stress T1 response is method-dependent, underestimation lead to misdiagnosis. Further, ECV quantification be affected by time, as well number dosage of gadolinium (Gd) contrast administered. We compared two commonly available approaches in their measurement stability. Healthy subjects (n = 10, 50% female, 35 ± 8 years) underwent regadenoson CMR (1.5 T) on separate days. Prototype...
TOMATO (Total Mapping Toolbox) is a C++ library for the calculation of parametric maps in cardiac magnetic resonance imaging (MRI). As an open source project, allows transparent and standardised longitudinal relaxation time (T1) mapping clinical applications. With implementation, can easily interface translate between research software environments commercial vendors' closed-source on scanners as well post-processing software. To complement core ready-to-use command line tool has been provided.
Background Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging is the gold standard for non-invasive myocardial tissue characterisation. However, accurate segmentation of left ventricular (LV) myocardium remains a challenge due to limited training data and lack quality control. This study addresses these issues by leveraging generative adversarial networks (GAN)-generated virtual native (VNE) images expand set incorporating an automated control-driven (QCD)...
Abstract Background Heart failure is a common cardiovascular complication to diabetes. Increased fibrosis of the myocardium has been suggested be mechanism, however, no convincing clinical evidence so far presented. A better understanding how myocardial tissue characteristics influence functional aberration in diabetes could aid diagnosis, risk assessment and guide treatment. Native T1 CMR marker diffuse with diagnostic prognostic value (1,2), feature tracking (CMR-FT) strain sensitive...
<h3>Introduction</h3> Coffee is widely reported to be the world's most popular drink and previous studies revealed acute increases in arterial stiffness with its consumption. But, chronic effects of coffee on are inconsistent limited by modest number studied subjects. This study aims evaluate association consumption using two forms measures a large population cohort. Aortic distensibility (AoD) local measure whilst index (ASI) wave reflection. Both have been shown predictors cardiovascular...
Abstract Background Although arterial stiffness has demonstrated moderate heritability, our knowledge of the genes modulating is still limited. We conducted genome-wide association studies (GWASs) aortic distensibility (AoD) in both ascending (AA) and proximal descending aorta (PDA) to discover novel genetic loci. Methods Our study included ~14,500 European-ancestry participants UK Biobank study. AoD AA PDA were assessed at level pulmonary artery bifurcation using transverse cine images...
Abstract Funding Acknowledgements Type of funding sources: Foundation. Main source(s): British Heart Foundation Academy Medical Sciences Background LV myocardial interstitial fibrosis has been reported to influence LA morphology and function via remodelling diastolic dysfunction. However, this association, as well their combined on clinical outcomes remains poorly characterised. Aim To evaluate the relationship between left ventricular (LV) quantified by native T1 times atrial (LA) global...
<h3>Background</h3> Artificial intelligence (AI) is increasingly used in diagnostic imaging. Deep convolutional neural networks (CNN) are able to learn from datasets presented them, and then provide independent interpretations on new cases, but often without traceability of how they came the conclusions. Such 'black box' behaviour not desirable for clinical use. We propose concepts visualising guiding AI attention an application artefact detection cardiac T1-mapping - a critical quality...
Background: Traditional cardiovascular risk factors are associated with atherosclerosis, alterations to cardiac structure and function major determinants of disease.In parallel this process, increasing stiffness the arterial vasculature plays a complementary role in development conditions.Aortic distensibility is marker stiffness.Purpose: This study examines effect traditional non-modifiable modifiable on aortic large cohort, free from disease.Methods: Age, sex, ethnicity (non-modifiable)...
<h3>Background</h3> Artificial intelligence (AI) is increasingly used in diagnostic imaging. Deep convolutional neural networks (CNN) can learn from labelled datasets, and then provide independent interpretations on new cases, but often without traceability to how such conclusions were made. This 'black box' behaviour not desirable for clinical applications. We propose a novel framework visualising guiding the AI attention, using artefact detection cardiac T1-mapping as an example - critical...
Abstract Introduction Left ventricular (LV) myocardial fibrosis is posited to result in left atrial (LA) changes via LV remodelling and diastolic dysfunction, though the association remains poorly characterised. Native T1 mapping a non-invasive modality that quantifies diffuse fibrosis. This study examines relationship between (quantified by native times) LA function, drawing upon data from UK Biobank. Methods 40,818 participants underwent cardiovascular magnetic resonance (CMR) using...