Smart Medical Imaging

EPSRC Centre for Doctoral Training


Current Projects

  • Federico Luzi
  • Vassilis Baltatzis

    314 - Deep learning for early detection of lung cancer in patients at risk

    Vassilis Baltatzis - 2017 entry

    The project aim is to explore and develop novel machine learning approaches based on ‘deep learning’, as applied to serial low-dose lung CT imaging for early lung cancer identification in high-risk cohorts. Early identification is challenging because symptoms are non-specific (or absent), compounded by overlap with symptoms of chronic obstructive pulmonary disease (COPD). Early diagnosis using CT relies on the detection of lung nodules and an accurate evaluation of their growth. However, manual radiological assessment is problematic because of inter-observer and inter-scan variability. This project will address the key medical imaging challenges arising from co-existent emphysema, inter-current infection, differing levels of inspiratory effort and variable acquisition parameters in patients with CT-detected nodules, by devising novel solutions using machine learning methods belonging to the class of deep learning architectures, an emerging and particularly promising area of medical image analysis, in order to detect lung cancer at an early stage. More...

  • Elsa-Marie Otoo

    319 - Development of novel visualization techniques for medical images using a holographic volumetric display

    Elsa-Marie Otoo - 2017 entry

    The rapid development of technology and medical imaging concurrently over the last 20 years has resulted in an increase in the clinical demand for radiological images. More...

  • Hugh O'Brien

    320 - Comprehensive CRT CT Imaging (3CI)

    Hugh O'Brien - 2017 entry

    This project will aim to exploit recent advances in dual energy CT scanners that provide high image contrast and with low radiation dose cardiac imaging at exceptional spatial and improved temporal resolution. The objective of this PhD will be the design, development and testing of an image processing and visualisation platform for extracting key indices of cardiac function and anatomy from cardiac CT imaging to predict the outcome of CRT and guide therapies. More...

  • Woo-Jin Cho Kim
  • Samuel Budd

    322 - A Service-Oriented Architecture approach for collaborative and quality assured analysis of medical image data

    Samuel Budd - 2017 entry

    Exploration of medical image data has proven to be challenging and annotation is usually very labour intensive and done inefficiently by single expert observers. The aim of this project is the creation of tools and algorithms that enable the detection and diagnosis of abnormalities and the efficient exploration of new biomarkers in highly complex data sets. Development of these tools will be driven by brain imaging of the adult and developing connectome. Comprehensive data analysis using Machine Learning and advanced visualisation methods will be combined in full-stack high performance computing framework. This framework will provide a unique platform for collaborative data exploration, crowdsourcing of data annotation, visualisation in distributed environments, and biological and clinical research. The use of modern programming methods will guarantee global accessibility and coherent usability. More...

  • Aishwarya Mishra
  • Daniel Grzech

    Automated assessment of fetal movements as an indicator of postnatal neurological health and function

    Daniel Grzech - 2017 entry

    Neonatal movements are commonly assessed as a way of predicting neurological function of the baby, but methods currently in use are subjective, time-consuming and are not standardised. It has been shown that there is continuity between fetal and neonatal movement patterns, and that fetal movements are affected by certain neurological disorders, but fetal movement patterns are not routinely assessed. This project will develop a system for automatically tracking and characterising fetal movements visualised using cine MRI. A large bank of fetal movement data has already been gathered for normal subjects and for subjects at increased risk of neurological conditions, e.g., ventriculomegaly (enlarged lateral ventricle in the brain). From this data, this project will identify one or more movement-based ‘biomarkers’ indicative of neurological function using image-based feature identification and tracking methods combined with machine learning approaches. This project forms part of a platform approach to objective assessment of fetal and neonatal movement patterns for early diagnosis of neurological abnormalities. More...

  • Olivier Jaubert

    Cardiac Multiparametric Magnetic Resonance Fingerprinting

    Olivier Jaubert - 2017 entry

    In this project we aim to develop multiparametric reconstruction from a single free-breathing cardiac Magnetic Resonance (MR) acquisition. This approach will allow the simultaneous reconstruction of cardiac anatomical images as well as parametric mapping of magnetic relaxation properties (T1/T2) for tissue characterization (allowing to differentiate between pathological and healthy tissue). For this we propose to extend the recently proposed Magnetic Resonance Fingerprinting (MRF) approach and tailored for cardiovascular applications. The objectives of the project are: • Implementation of MR fingerprinting for breath hold 2D cardiac multiparametric imaging • Development and implementation of MR fingerprinting for free-breathing 2D cardiac multiparametric imaging • Development and implementation of MR fingerprinting for free-breathing M2D cardiac multiparametric imaging. More...

  • George Firth

    Development of tracers for in vivo trafficking of essential trace metals in health and disease using PET imaging

    George Firth - 2017 entry

    The aim is to develop methodology for production of radionuclides and tracers to support a programme of study on use of PET to help understand changes in trafficking of essential trace metals (Zn, Cu, Mn, Fe) in diseases where they are highly relevant, such as diabetes, cancer, dementia and pulmonary hypertension. The objectives will be (a) to set up Zn-63 production at KCL (Cu-64/62 already implemented at KCL; Fe-52 and Mn-52 purchased externally; Zn-62 production already in place); (b) develop suitable delivery vehicles e.g metastable lipophilic complexes, ionic salts, protein bound (albumin, transferrin)and routes to control trafficking of the metals via endogenous transport, retention and excretion mechanisms; (c) use them to map normal trafficking of Cu, Zn, Fe, Mn in mice, (d) map changes in trafficking in disease models, and (e) identify translational opportunities for human PET studies More...

Previous 123456789 Next