315 - Automated detection of cardiac arrhythmia locations to optimise treatments using a combined physics and machine-learning approach
Sofia Monaci - 2018 entry
Jonathan Jackson - 2017 entry
The aim of the project is to develop a non-invasive computational diagnosis pipeline for assessing the severity of coronary lesions that could easily be applied under real-time interventional settings. To achieve this, a combination of computational fluid dynamics and machine learning techniques will be used. As the full-scale CFD modelling is time-consuming, requires expertise not widely available in clinical environments, and is unsuitable for direct implementation into cathlab consoles, in this project we will seek to develop a reduced-complexity model for which the lumped shape parameters are estimated directly from the medical images using statistical learning techniques. The developed framework will be applied to 200+ clinical cases for validation, and evaluated in a pilot study in the final year of the project. More...
Esther Puyol - 2014 entry
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. More...