Building upon recent advances in image analysis and metadata-driven data management, AccelRT provides computational tools that can be used to overcome the bottlenecks in clinical radiotherapy delivery
Speeding up the preparation of high precision radiotherapy treatment

Our goal

To provide a computerised decision support system and optimised computing support that can be used to overcome the bottlenecks in clinical radiotherapy delivery. AccelRT project builds upon STFC-funded research to deliver a high performance, service-based computing solution, ready for use with existing treatment platforms. This solution will be validated in partnership with one of the largest providers of radiotherapy equipment and software in the UK, Oncology Systems Limited (OSL).

The challenge of delivering high precision radiotherapy

Whether treatment is implemented with X-rays or particle beams, a common characteristic is increased precision in dose delivery. The ability to target only the cancerous tissue has immediate benefits in terms of both survival and quality of life. However, high precision radiotherapy treatment comes at a cost, in terms of manual, labour-intensive treatment planning.

In multimodal imaging, the data throughput for treatment planning objects is modest: a typical image data set for one patient receiving high precision skull base radiotherapy requires 300MB of storage space; if the patient is undergoing daily imaging to verify the correct position of the tumour target, the verification image data for one patient is 2.3GB. For a facility treating 600 patients per year with high precision image-guided radiotherapy, this would generate a data set of 1.4TB per year for each institution. In order to perform a complete multiple timepoint image registration for a dataset of this size in near real time requires 16 Teraflops of processing power (approximately 100 times the power of a standard PC workstation). This all makes the large data throughput difficult to query and computationally intensive. All these factors introduce a bottleneck in the clinical delivery workflow, remarkably with the increasing number of cancer patients, which can cause long queues and less survivability rates.

To undertake this kind of processing in a clinical environment - and the refinement and optimisation of the algorithms involved - will require the application of techniques developed for Grid and many-core GPU computing. To translate the research successes in novel radiotherapy into routine, medical practice, we need to provide computing support for the treatment planning process, building upon recent advances in image analysis and the progress made in metadata-driven data management and integration.

Work programme and deliverables

The project forks into main two paths of research, which both concern better targeting of tumours for an accurate delivery and reduction of side effects of the treatment.

The first, AccelRT-DB, makes use of meta-driven data management and integration to design and implement a computerised decision support system that can be used as a ‘search engine’ for the radiotherapy community. AccelRT-DB offers a large database of clinical studies that can be queried interactively to pinpoint treatment plan parameters from similar cases to the case under study.

The second research path, AccelRT-App, is a software suite designed and implemented based on recent advances in medical image analysis. AccelRT-App offers a catalogue of image registration and segmentation methods that are optimised for radiotherapy applications.

The tools produced by AccelRT will be available as working open-source software to be used by radiation oncologists and therapy radiographers, to complement existing radiotherapy treatment planning and delivery tools.

The project team

University of Cambridge: Andy Parker, Neil Burnet, Raj Jena, Mark Hayes, Michael Simmons and Mohammad Al Sa'd.

University of Oxford: Jim Davies, Steve Harris, Ken Peach and Charles Crichton.

Some of the Cambridge AccelRT team

Project funded by

AccelRT is funded by the STFC Innovations Partnership Scheme (ref. ST/1004297/1), from December 2011 to June 2015. Michael Simmons was part-funded as an STFC IPS Fellow until September 2014. (ref. ST/G000077/1).