Imaging Research in the NHS

A Summary of Discussions from the NIHR Workshop on Delivering Imaging Research in the NHS: 7th February 2017, Kings College London

Lucy 1By Dr Lucy Walton

Imaging Research in the NHS – CHALLENGES!

Delivering Imaging Research within the NHS always has been a challenge. We are all aware of the pressures the NHS is under from the recent news coverage if not from personal experience, and diagnostic imaging units are certainly no exception. The majority of CT & MRI machines are in use 24 hours a day, therefore finding a window of time for research studies is not a priority.

Despite this there is no denying that research ultimately improves patient experience through improving diagnostic capabilities, reducing the time for diagnosis (through the development of automated reporting, for example) and improving disease prevention through identifying disease biomarkers. Further, for every £ put into Imaging research the NHS receives pay back.

Aside from access to equipment, the difficulty in recruiting radiographer and radiologists to posts was also a theme of discussions. When the number of vacancies far outweighs the number of practitioners to fill them it can be difficult to engage radiographers and radiologists in research beyond that required to acquire their accreditation and secure a position. There is no clear career structure for academic clinical radiographers or radiologists so encouraging students to develop a career in research may also be misleading.

Lucy article
Prof Erika Denton presenting on ‘Developing the NHS workforce’


Honorary University Appointments?

A solution may be to encourage practitioners to adopt honorary appointments at Universities, where they can engage in research studies alongside a wider collaborative academic team and continue their clinical roles. Certainly at Kings College London, 70-80% of clinicians are also research scientists and this improves patient care as research findings can be quickly translated into clinical practice.

Machine variability

One of the major limiting factors in imaging research in the NHS is the large variability in machine manufacturers and protocols used to collect & reconstruct images. This makes it incredibly difficult to design rigorous research studies, to conduct large scale (multicentre) studies & limits the conclusions that can be made from the data. The application of deep learning approaches from computer science to diagnostic imaging creates many promising opportunities in this respect.

Particularly of note during these discussions was the applicability of deep learning approaches to develop algorithms based on images collected using variable protocols & machines, therefore improving generalisability of the algorithm in the process.

Data sharing

Another common theme through the workshop was the need to develop data repositories in order to support multi-centre research studies (which are often confounded by issues surrounding data transfer) and the development of more rigorously controlled datasets. Obviously, obtaining patients consent to share images anonymously via repositories is required and may be difficult to obtain.

In summary, imaging research within the NHS is challenging; equipment is in great demand, units are often understaffed and data is often collected and analysed with a multitude of uncontrolled variables. Some practical ways in which challenges to imaging research may be overcome include: the application of deep learning approaches, the development of large & well controlled data repositories, multicentre studies & honorary University appointments for radiographers/radiologists.

Call for Action

The Radiography Directorate at the University of Salford holds a number of honorary appointments and we’re always interested in discussing these opportunities. If you’re interested don’t hesitate to contact us.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s