Image source: Microsoft
Addenbrooke’s Hospital in Cambridge has deployed an AI system for radiotherapy treatments, saying it can significantly reduce waiting times.
As part of Cambridge University Hospitals (CUH) NHS Foundation Trust, it has carried out a project funded by £500,000 from the NHS AI Lab to create the OSAIRIS tool, using Microsoft’s open source software toolkit from Project InnerEye and the Azure Machine Learning service.
OSAIRIS streamlines the process of outlining healthy organs on scans prior to radiotherapy, known as ‘segmentation’. This is critical to protect the healthy tissue around the cancer from radiation but can take up to three hours when done manually.
Using the new AI system is said to save an oncologist considerable time before reviewing each scan.
Addenbrookes has initially deployed the technology for prostate and head and neck cancers, but said it has potential across the NHS for a range of cancer types.
Heavy lifting
Oncologist Dr Raj Jena said: “OSAIRIS does much of the work in the background so that when the oncologist 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, which we will be able to share across the NHS for patient benefit.”
The Project InnerEye team had previously carried out peer reviewed research, working with eight clinical centres around the world, to show that machine learning can segment images faster than doing it manually, and with an accuracy within the bounds of human expert variability.
The CUH project has involved a series of tests and risk assessments, including ‘Turing tests’ in which doctors were unable to tell the difference between the work of OSAIRIS and that of another doctor.
Jena added: “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,” he explains. “And also, from my perspective as a neurooncologist, I’m interested that we’re building the brain model as well so that we’ve got something that works for brain tumours as well.”
Aditya Nori, general manager of healthcare for Microsoft Research, said: “The fact that we have AI finally in the NHS also will open the doors for other kinds of AI technologies to really reduce the burden that’s placed on clinicians, and more importantly, improve patient safety, outcomes, and experiences.”
