New NHS AI tool developed in Cambridge 'could slash waiting times for cancer treatment'

The new tool could be rolled out across the entire NHS.
Credit: Cambridge University Hospitals NHS Foundation Trust
The new tool could be rolled out across the entire NHS. Credit: Cambridge University Hospitals NHS Foundation Trust

Radiotherapy waiting times for NHS cancer patients could be drastically reduced thanks to the development of a new health tool which uses artificial intelligence.

Known as OSAIRIS, it is claimed the tool could save doctors hours in preparing scans and helping to slash the time patients have to wait between referral for radiotherapy and starting treatment.

The tool, which has been developed by oncologists at Addenbrooke's Hospital in Cambridge, works by cutting the amount of time a doctor needs to spend drawing around healthy organs on scans before radiotherapy.

Those behind the new tool say cancer doctors can plan for radiotherapy treatments two and half times faster than if they were working alone.

Outlining the organs, known as segmentation, is critical in order to protect the healthy tissue around the cancer from radiation.

It can take up to three hours per patient to perform this task.

Dr Raj Jena carried out 18 months of rigorous testing on the tool Credit: Cambridge University Hospitals NHS Foundation Trust

Dr Raj Jena, oncologist at Cambridge University Hospitals NHS Foundation Trust, led the research for the NHS and University of Cambridge in collaboration with Microsoft.

With a £500,000 grant from the NHS AI Lab, Dr Jena’s team created the tool using open-source software from Microsoft and data from patients who had previously been treated in the hospital and agreed to contribute to the research.

He hopes that OSAIRIS can be rolled out to the rest of the 60 radiotherapy centres in the NHS.

Dr Jena said: "OSAIRIS does much of the work in the background so that when the doctor sits down to start planning treatment, most of the heavy lifting is done.

"It is the first cloud-based AI technology to be developed and deployed within the NHS. Having carried out 18 months of rigorous testing, we are now able to share this technology safely across the NHS for patient benefit.”

Testing used "Turing tests" - or masked tests in which doctors were unable to tell the difference between the work of OSAIRIS and the work of a doctor colleague.

Dr Jena said the tool was already being used at Addenbrooke’s for prostate, head and neck cancers, but had the potential to work for many other types of cancer too.

“We’ve already started to work on a model that works in the chest, so that will work for lung cancer and breast cancer particularly.

“And also, from my perspective as a neuro-oncologist, I’m interested that we’re building the brain model as well so that we’ve got something that works for brain tumours too.”

Aditya Nori, general manager of gealthcare for Microsoft Research, said: “By combining the power of AI with the world-class clinical expertise of the NHS, we have an amazing opportunity for revolutionising healthcare together, while preserving the human element that is the essence of high-quality and safe care.”

News of the new tool follows an announcement last week that the government was pumping £21m into new AI-driven diagnostic tools.

Health Secretary and North East Cambridgeshire MP Steve Barclay said the new tech would help free up doctors.

That view was backed by University of Cambridge's professor of machine learning Neil Lawrence. Earlier this month he told ITV News Anglia that new AI tools could allow NHS staff to focus on care.


Want a quick and expert briefing on the biggest news stories? Listen to our latest podcasts to find out What You Need To Know