A5017052604- Cardiac Imaging and Diagnostics
- Cardiovascular Function and Risk Factors
- Advanced MRI Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Cardiac Valve Diseases and Treatments
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Congenital Heart Disease Studies
- Artificial Intelligence in Healthcare and Education
- Cardiovascular Health and Disease Prevention
- Cardiomyopathy and Myosin Studies
- Cardiovascular Effects of Exercise
- Pulmonary Hypertension Research and Treatments
- Medical Imaging and Analysis
- Explainable Artificial Intelligence (XAI)
- Machine Learning in Healthcare
- Heart Rate Variability and Autonomic Control
- Cardiac pacing and defibrillation studies
- Autopsy Techniques and Outcomes
- Cardiovascular Disease and Adiposity
- Atomic and Subatomic Physics Research
- Cardiac electrophysiology and arrhythmias
- Cardiac Structural Anomalies and Repair
- Medical Image Segmentation Techniques
- Blood Pressure and Hypertension Studies
St Thomas' Hospital
2016-2025
King's College London
2016-2024
University Medical Center Utrecht
2018-2024
Guy's and St Thomas' NHS Foundation Trust
2017-2023
Utrecht University
2022-2023
Kings Health Partners
2020-2023
University College London
2023
King's College School
2023
Heidelberg University
2022
University Hospital Heidelberg
2022
This study sought to develop a fully automated framework for cardiac function analysis from magnetic resonance (CMR), including comprehensive quality control (QC) algorithms detect erroneous output.Analysis of cine CMR imaging using deep learning (DL) could automate ventricular assessment. However, variable image quality, variability in phenotypes disease, and unavoidable weaknesses training DL currently prevent their use clinical practice.The consists pre-analysis QC, followed by algorithm...
Good quality of medical images is a prerequisite for the success subsequent image analysis pipelines. Quality assessment therefore an essential activity and large population studies such as UK Biobank (UKBB), manual identification artefacts those caused by unanticipated motion tedious time-consuming. Therefore, there urgent need automatic techniques. In this paper, we propose method to automatically detect presence motion-related in cardiac magnetic resonance (CMR) cine images. We compare...
Segmenting anatomical structures in medical images has been successfully addressed with deep learning methods for a range of applications. However, this success is heavily dependent on the quality image that being segmented. A commonly neglected point analysis community vast amount clinical have severe artefacts due to organ motion, movement patient and/or acquisition related issues. In paper, we discuss implications motion cardiac MR segmentation and compare variety approaches jointly...
Artificial intelligence (AI) techniques have been proposed for automation of cine CMR segmentation functional quantification. However, in other applications AI models shown to potential sex and/or racial bias. The objective this paper is perform the first analysis sex/racial bias AI-based using a large-scale database.
To present a method that uses novel free-running self-gated acquisition to achieve isotropic resolution in whole heart 3D Cartesian cardiac CINE MRI.3D MRI using navigator gating results long times. Recently, several frameworks based on non-Cartesian trajectories have been proposed accelerate this acquisition. However, reconstructions are computationally expensive due gridding, particularly 3D. In work, we propose highly efficient approach for MRI. Acquisition is performed CArtesian...
Pathogenic and likely pathogenic variants associated with arrhythmogenic right ventricular cardiomyopathy (ARVC), dilated (DCM), hypertrophic (HCM) are recommended to be reported as secondary findings in genome sequencing studies. This provides opportunities for early diagnosis, but also fuels uncertainty variant carriers (G+), since disease penetrance is incomplete. We assessed the prevalence expression of G+ general population.We identified ARVC, DCM and/or HCM 200 643 UK Biobank...
Dysfunction of either the right or left ventricle can lead to heart failure (HF) and subsequent morbidity mortality. We performed a genome-wide association study (GWAS) 16 cardiac magnetic resonance (CMR) imaging measurements biventricular function structure.
Tissue characterisation with CMR parametric mapping has the potential to detect and quantify both focal diffuse alterations in myocardial structure not assessable by late gadolinium enhancement. Native T1 particular shown promise as a useful biomarker support diagnostic, therapeutic prognostic decision-making ischaemic non-ischaemic cardiomyopathies. Convolutional neural networks Bayesian inference are category of artificial which model uncertainty network output. This study presents an...
Abstract Aims Artificial intelligence (AI) methods are being used increasingly for the automated segmentation of cine cardiac magnetic resonance (CMR) imaging. However, these have been shown to be subject race bias, i.e. they exhibit different levels performance races depending on (im)balance data train AI model. In this paper we investigate source seeking understand its root cause(s). Methods and Results We trained models perform classification CMR images and/or segmentations from White...
We present a framework for combining cardiac motion atlas with non-motion data. The represents cycle across number of subjects in common space based on rich descriptors capturing 3D displacement, velocity, strain and rate. data are derived from variety sources such as imaging, electrocardiogram (ECG) clinical reports. Once the space, we apply novel supervised learning approach random projections ensemble to learn relationship between some desired output. our problem predicting response...
The aim of this paper is to describe an automated diagnostic pipeline that uses as input only ultrasound (US) data, but at the same time informed by a training database multimodal magnetic resonance (MR) and US image data.We create cardiac motion atlas from three-dimensional (3-D) MR 3-D data followed multi-view machine learning algorithms combine extract most meaningful descriptors for classification dilated cardiomyopathy (DCM) patients using only. More specifically, we propose two based...
Abstract Many cardiovascular diseases lead to local increases in relative pressure, reflecting the higher costs of driving blood flow. The utility this biomarker for stratifying severity disease has thus driven development methods measure these pressures. While intravascular catheterisation remains most direct measure, its invasiveness limits clinical application many instances. Non-invasive Doppler ultrasound estimates have partially addressed gap; however only provide pressure a range...
First, our proposed methods for CV parameter estimation and a comprehensive set of from the literature were tested using in silico clinical datasets. Second, optimized algorithms estimating cBP aortic flow developed wide range morphologies, including catheter data. Third, dataset simulated waves was created three-element Windkessel model. Fourth, model are freely available.
Introduction: Atrial fibrillation (AF) is a widespread cardiac arrhythmia that commonly affects the left atrium (LA), causing it to quiver instead of contracting effectively. This behavior triggered by abnormal electrical impulses at specific site in atrial wall. Catheter ablation (CA) treatment consists isolating this driver burning surrounding tissue restore sinus rhythm (SR). However, evidence suggests CA can concur formation blood clots promoting coagulation near heat source and regions...
BackgroundChildren with a single systemic right ventricle, such as in hypoplastic left heart syndrome (HLHS), frequently experience reduced exercise capacity. Elucidating the causes could help optimising treatment strategies.MethodsProspective data from 10 consecutive symptomatic patients HLHS undergoing clinical cardiac magnetic resonance catheterisation (XMR) were analysed. Mean age 8.6 years (range 3.5–11.6 years), mean time since Fontan completion 5.5 years. MR-compatible catheters...
Artificial intelligence (AI) techniques have been proposed for automating analysis of short-axis (SAX) cine cardiac magnetic resonance (CMR), but no CMR tool exists to automatically analyse large (unstructured) clinical datasets. We develop and validate a robust AI start-to-end automatic quantification function from SAX in databases.
Cardiovascular magnetic resonance myocardial feature tracking (CMR-FT) is a promising method for quantification of cardiac function from standard steady-state free precession (SSFP) images. However, currently available techniques require operator dependent and time-consuming manual intervention, limiting reproducibility clinical use. In this paper, we propose fully automated pipeline to compute left ventricular (LV) longitudinal radial strain 2- 4-chamber cine acquisitions, LV...
Cardiac catheterization is a common procedure in patients with congenital heart disease (CHD). Although cardiovascular magnetic resonance imaging (CMR) represents promising alternative approach to fluoroscopy guidance, simultaneous high contrast visualization of catheter, soft tissue and the blood pool remains challenging. In this study, novel passive tracking technique proposed for enhanced positive gadolinium-filled balloon catheters using partial saturation (pSAT) magnetization preparation.
Understanding (patho)physiological phenomena and mechanisms of failure in patients with Fontan circulation—a surgically established circulation for born a functionally single ventricle—remains challenging due to the complex hemodynamics high inter-patient variations anatomy function. In this work, we present biomechanical model heart augment diagnostic evaluation early-stage failure. The proposed framework employs reduced-order coupled simplified including venous return, creating closed-loop...
Background Automated analysis of cardiovascular magnetic resonance images provides the potential to assess aortic distensibility in large populations. The aim this study was compare prediction events by automated with those other simple measures stiffness suitable for population screening. Methods and Results Aortic measured from segmentation cine using artificial intelligence 8435 participants. associations distensibility, brachial pulse pressure, index (obtained finger...