Auto anomaly detection for brain imaging awarded £1m grant
29 October 2014
Researchers at UCL have been awarded a grant of £1m by the Department of Health and Wellcome Trust under the Health Innovation Challenge Fund initiative to tackle an obstacle to the continued growth of brain imaging by applying computer algorithms to detect anomalies in brain scans.
Modern brain imaging contains vastly more information than historical radiographs, yet its clinically informative output has remained the same: a radiologist’s verbal report. As the information content of imaging increases, a void between the information collected and the information actually used has opened.
Dr Parashkev Nachev and his collaborators Professors Geraint Rees, Professor Sebastian Ourselin, Professor Rolf Jager and Professor Xavier Golay are seeking to close this gap by applying novel computer-assisted algorithms so as to exploit much more of the information in each brain scan than a radiologist’s verbal report.
The system—intended to be embedded within the standard radiological infrastructure of a hospital—will produce a measure of the anomaly of each magnetic resonance brain image as soon as the patient is scanned.
An automatic “anomaly map” for each scan will assist radiological reporting, allow the application of computer systems that predict clinical outcomes from patterns of anomaly and guide radiological triage; all without changing any clinical pathways or adding new investigations.
The project aims to
demonstrate the value of using this technology and to deliver a pilot
system capable of translation into a full clinical product.