Software Designed to Automatically Outline Bones in X-Rays

Research into such as arthritis and other disorders will soon get a helping hand from new software that automatically outlines bones, saving thousands of hours of manual work.

There is a shortage of radiographers in the United Kingdom and because of an increasing requirement for researchers to work with large databases of radiograph images, the software, which is being funded by the UK Engineering and Physical Sciences Research Council, is being designed to automatically detect the shapes of bones in the images, instead of relying on individual researchers.

The system can already identify hips; however, researchers from the University of Manchester’s (UK) Institute of Population Health will now modify it to map out knees and hands and to be able to learn to identify other bones and structures within the body. The funding will allow further development to ensure the system is accurate enough that it can be used in hospitals to help provide faster diagnosis of problems in patients.

Tim Cootes, a professor of computer vision, said, “Mapping the outlines of bones from radiographs is hard work that takes time and skill. When researchers into conditions like arthritis are working with hundreds of images, it’s a very inefficient way of obtaining data. The idea of this software is to take the routine tasks out of human hands, so scientists can focus on drawing conclusions and developing treatments.”

The funding of GBP 300,000 lasts for three years and builds on earlier research that helped to develop the software, called Bonefinder, to identify problems and find the outlines of hips. This free software has been implemented by a number of research groups, including some based in Oxford and the US state of California.

Prof. Cootes added, “We have a growing problem with arthritis which affects more than 30% of over 65s and costs around GBP 30 billion to the UK economy yearly. “Ultimately we want to get this technology into hospitals where it can save time and resources for the benefit of patients.”

Related Links:
University of Manchester