Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.
Skip to main content

Re-using routinely collected maternity data for the development of a new diagnostic tool during childbirth

Dr Antoniya Georgieva, Oxford Centre for Fetal Monitoring Technologies, Big Data Institute

Abstract

Monitoring continuously the fetal heart rate during childbirth is the gold standard to assess whether a baby is at risk of oxygen starvation. This is achieved with a cardiotocogram, CTG, showing continuously the fetal heart rate and contraction signals (Figure 1). This is to identify babies that could benefit from an emergency operative delivery (e.g. Caesarean section), in order to prevent death or permanent brain injury of the baby. The long, dynamic and complex heart rate patterns are poorly understood and known to have high false positive and false negative rates. Visual interpretation by clinicians in real-time is challenging and fetal monitoring in labour remains an enormous unmet medical need.

 

Complex motion modelling for medical imaging applications

Dr Bartek Papiez, Rutherford Fund Fellow at Health Data Research UK, Big Data Institute

Abstract

During this talk, I will present an overview of my work on the development of accurate, thus complex and realistic but still computationally efficient models of organ motion. The presented framework has established a solid foundation both to remove unwanted motion and motion-related imaging artefacts to perform image analysis, and to construct atlases (or shape models) from imaging. The previous application of this framework supported various cancer imaging modalities primarily providing reliable quantitative image analysis of lung and liver tumour. In this talk, I will also present our initial results on constructing a 3D atlas from ultrasound (US) volumes. Our method simultaneously aligns a set of images from population to a reference space thereby representing the population average. The resulting atlas shows high structural(anatomical) overlap, and correspondence between the US-based and an age-matched fetal MRI-based atlas is also observed.​