Computer Aided Diagnosis for the Analysis of the Fetal Brain and Heart on Ultrasound

Lead Research Organisation: University of Oxford
Department Name: Engineering Science

Abstract

All over the world pregnant women are monitored during their pregnancy with fetal ultrasound. The correct interpretation of these scans is of the utmost importance in the detection of any abnormalities, indicating the possible presence of more serious conditions of the fetus. Early detection of deficiencies can assist clinicians in deciding whether they should provide any additional treatment. However, ultrasound scans have a relatively low spatial resolution, which makes the correct assessment a challenging task and very dependent on the experience of the clinician. The issue becomes even more pressing in situations where doctors lack the necessary education. Computer Aided Diagnosis (CAD) systems have the potential to remedy this situation. Hence it is important to develop CAD systems, able to automatically analyse ultrasounds and aid clinicians in the interpretation of scans. Besides the clinical advantages offered by the development of these new technologies there are also benefits from a research point of view. CAD systems enable the analysis of large amounts of ultrasounds, yielding possible new insights into the fetal development.
Two important fetal organs which should be monitored closely during pregnancy are the brain and heart. Deficits in the normal development of the brain can indicate impaired brain maturation, whereas insufficient development of certain heart structures suggests the presence of congenital heart defects (CHD). The development of both organs individually has been studied widely both with magnetic resonance imaging and ultrasound. However, because heart defects cause a change in the blood flow of the fetus this can change the nutrient and oxygen supply to other developing organs such as the brain. This can potentially result in abnormal brain development of the fetus. To understand the complete development of the fetus it is thus crucial to understand the dependencies between the different organs. Furthermore, a better understanding of the relationships between deficiencies in these organs could enable the prevention of certain abnormalities in the fetus. Therefore, in this project we will develop automated methods to analyse both the fetal heart and brain and study the dependencies between these organs during fetal development.
This project falls within the EPSRC Healthcare technologies research area. With this project we aim to improve pregnancy monitoring and obtain new insights in the fetal development. More specifically, we think that this can result in earlier diagnosis of fetal deficiencies and as such enable timely intervention. Therefore, this project is in the scope of the "optimising treatment" grand challenge.
For this project we collaborate with the gynaecology department of the Leiden University Medical Centre in the Netherlands. This department is specialized in fetal heart defects, and they will be acquiring part of the necessary ultrasound scans for this study.

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/R513295/1 01/10/2018 30/09/2023
2283490 Studentship EP/R513295/1 01/10/2019 30/09/2022 Linde Hesse