The MMAG has worked extensively in the past on the imaging, modelling and estimation of repetitive motion. Organ motion due to respiration and the beating of the heart is approximately periodic, so measurements of this motion made from imaging data can be used to construct mathematical models of the periodic motion and its variability. Such models can be applied to update guidance information in image-guided interventions or to correct acquired imaging data for the corrupting effects of motion. The group has worked on applying such models in a range of applications, but predominantly in the context of image-guided cardiac interventions and PET-MR imaging.
Currently, the main research theme of the group is the analysis of motion with the aim of extracting clinically useful biomarkers. Here, work focuses on cardiac cycle motion, in which changes in heart function will manifest themselves as subtle changes in the observed motion of the heart as it beats. The group works
on developing novel machine learning techniques to learn motion features that are useful for a range of clinical prediction tasks.
The group is also involved in developing machine learning solutions to other problems, such as radiotherapy and vocal tract imaging.
6 Mar 2019: James Clough's work on incorporating topological knowledge into deep learning based image segmentation has been accepted for oral presentation at IPMI 2019. Preprint available here - see project summary.
22 Feb 2019: Data download now available for MRI images used in Clough et al, IEEE T-PAMI 2019.
