Medical Imaging

EPSRC Centre for Doctoral Training


Esther Puyol


I completed my Bachelors and Masters of Science at the Polytechnic University of Catalonia (Spain) in Biomedical Signal Processing.  In order to expand my knowledge and have an international experience, I enrolled into a double degree programme with Telecom Bretagne (France), where I obtained the French Masters of Engineering and a Research Master in medical imaging. My research interests lie in the fields of Machine Learning and Computer Vision focused on medical image processing and object recognition. More concretely, I am passionate in clinical applications such as non-invasive imaging, navigation and Vascular and Interventional Radiology.

I believe that a PhD at the CDT will empower me to work at the forefront of scientific research and develop excellent domain expertise in imaging science, applying this knowledge to clinical applications with the aim to improve people’s lives. I also believe that doing a PhD in King’s College is a great opportunity to contribute and learn from some of the very best scientists and investigators of the world.

Project: Multimodal analysis of cardiac motion and deformation

The main aim of this project is to develop a statistical atlas of normal heart shape and function from imaging and non-imaging data (e.g. patient data from the clinical record). The atlas will be based on freely available data as well as retrospective datasets held by KCL (consisting of cine/tagged MR and 2-D/3-D ultrasound). It will be used to develop novel pattern analysis tools that extract indicators able to characterize and predict pathologies such as myocardial infarction, valve diseases, hypertrophy, and hypertension. The intended workflow of the developed system would be to make use of prior knowledge from the atlas to enable robust extraction of indicators from 2D and 3D ultrasound images, enabling early screening and characterization of pathologies. The atlas would be built from data acquired from healthy subjects, and pathological cases will be learned using tailored dissimilarity metrics with respect to the atlas.


Esther Puyol