Robust Systems for Automated Analysis of Structures in 2D Medical Images

This project aims to develop robust and accurate systems for locating the outlines of bones and other structures in widely used medical images such as radiographs. A key motivation is to provide a set of tools for the clinical research community to help analyse bone shape and thus better understand, monitor and treat musculoskeletal disease. Such diseases affect about 16% of all adults and more than 30% in the over 65s. The annual total cost of arthritis alone is estimated to be more than £30 billion for the UK. There is increasing clinical interest in studying bone shape, but progress is hampered by the time required to annotate the outlines of structures of interest on the large databases now available.

We have recently developed new machine-learning based methods for fitting statistical shape models to images which are achieving state-of-the-art performance. In this project we will build on this approach. Our goal is to provide the clinical research community with a system to allow analysis of large medical image databases as efficiently as possible. To achieve this we will address fundamental research challenges including (i) How to ensure model matching is robust and (ii) How to construct models from un-labelled images efficiently, with minimal human interaction. The project will produce both a practical and useful system for clinicians, and new algorithms and insights into tackling fundamental problems in computer vision and medical image analysis.

This project will benefit the following groups:

Clinicians and Radiologists:
Clinicians will benefit from a better understanding of the range of variation of the human body and the changes caused by disease. The improved information provided by the models will lead to earlier and more accurate diagnosis and more effective choice of treatment and treatment monitoring.
We are working with a range of clinicians in the UK and abroad, who will be able to use the technology developed in the project.

Patients:
In the longer term this will lead to improvements to patients - their diseases will be better understood, diagnosed earlier and more accurately, and it will be easier to select the most appropriate treatment.
A better understanding of who is at risk of disease will lead to more targeted therapies and intervention, helping delay and prevent the worst effects.

Medical Image Analysis Companies:
There are many companies in the UK who develop products to help manage and analyse medical images who will benefit from the algorithms and technology developed in this project. We currently have close links with three local companies working in the field who could license the technology and help take it into wider use.

Pharmaceutical Companies:
Accurately detecting and monitoring the effect of new drugs on disease is of critical importance to pharmaceutical companies
during drug development. The methods developed will be directly applicable to this field, making it easier to study how bones and joints change over time during clinical trials.

Epidemiologists and Health Service Planners:
The project will provide tools to allow the analysis of large groups of images. These will produce valuable data for epidemiologists to understand variations in populations and diseases across populations.
This in turn will allow those in the health service to plan ahead and evaluate the cost and benefits of screening programs and interventions.