Medical Imaging

EPSRC Centre for Doctoral Training



  • 103 - Multidimensional and Multiparametric Quantitative Cardiac MRI from Continuous Free-Breathing Acquisition

    Magnetic Resonance Imaging (MRI) has become an increasingly important non-invasive tool for risk assessment and treatment monitoring of cardiovascular disease. In comparison to alternative imaging modalities (e.g. echocardiography, X-ray fluoroscopy, computed tomography and positron emission tomography) MRI has the advantage of combining excellent soft tissue characterization with high spatial resolution, and does not require ionizing radiation. Cardiac MRI has been established as a clinically important technique for the assessment of cardiac morphology, function (CINE MRI), perfusion (MR-perfusion) and viability (LGE, infarct). More...

  • 301 - Explaining the predictions of deep learning models in cardiology

    The use of machine learning techniques in cardiology is an active research area and recently state-of-the-art results have been achieved by applying the latest ‘deep learning’ techniques to tasks such as segmentation of the myocardium and blood pool [1]. Machine learning has also been used to identify and exploit the useful information carried by the motion and deformation of the heart as it beats [2,3]. More...

  • 312 - A twist of heart: investigating the myocardial rotational function

    Left ventricular twist observed during contraction arises from the underlying fibrous architecture of the heart tissue. The muscle fibres, which are helically oriented and varies smoothly from a left- to right-handed sense throughout the depth of the wall, leads to a wringing motion of the chamber as the heart contracts [1]. While LV torsion is known to be consistent across healthy individuals, it is affected by a variety of pathologies such as ischemia and cardiomyopathies, that may increase or decrease torsion depending on the pathophysiological process involved [2]. More...