AI tool speeds up cancer treatment, cuts backlog

The Addenbrooke's Hospital in Cambridge, England, has become the first in the world to use cutting-edge artificial intelligence technology from Microsoft that could improve survival rates for some cancers.

Experts believe the new software could help cut the backlog in cancer treatment that has been exacerbated by the novel coronavirus pandemic, without compromising quality of care.

Addenbrooke's is the first to use InnerEye, an AI deep learning tool that computes the hospital's data to accurately identify tumors on patient scans and therefore accelerate the treatment process.

Microsoft said the use of the software would shorten the lengthy treatment planning stage, and expects survival rates to increase, as a result.

The technology, being introduced in other National Health Service (NHS) trusts across the country, can help reduce the processing time it takes specialists to prepare radiotherapy treatment for a patient by up to 90 percent, the company said.

Delays in receiving treatment for cancer were a concern for the NHS even before the pandemic struck, The Times reported.

According to Cancer Research, the pandemic has meant an estimated three million people in the UK have missed out on cancer screenings due to hospital restrictions, creating a severe backlog of patients waiting for treatment.

"The results from InnerEye are a game-changer," said Raj Jena, an oncologist at Addenbrooke's and co-lead on the InnerEye project.

"To be diagnosed with a tumor of any kind is an incredibly traumatic experience for patients. So as clinicians we want to start radiotherapy promptly to improve survival rates and reduce anxiety. Using machine learning tools can save time for busy clinicians and help get our patients into treatment as quickly as possible."

It is predicted that up to half of UK residents will be diagnosed with cancer at some point in their lives, and out of these, half will be treated using radiotherapy.

Javier Alvarez-Valle, principal research manager at Microsoft Research Cambridge, said: "AI models trained with InnerEye are changing the way cancer is treated, speeding up the process to give patients greater peace of mind and empowering clinical oncologists with an AI assistant.

"The AI works in the background, so clinical oncologists just open up the scans on their computer and they can see what their AI model has highlighted. The clinical oncologist then decides what to do with that information."

Addenbrooke's has been working with Microsoft to develop and pilot InnerEye over the past eight years, and it is believed to mark the first time an NHS trust has introduced a deep learning solution trained on its own data, which improves accuracy.

The tech giant has made Inner-Eye freely available as open-source software for hospital use.