Treating cancer is a race against time. Each moment which passes is an opportunity for it to spread and become untreatable.
How long it takes for radiation therapy plans to be created today can take days. Individual maps need to be created for each patient to determine where tumours need to be targeted.
This lengthy process is frustrating for the patient, their loved ones, and medical professionals who’d love nothing more than to spend time saving lives instead of creating plans.
Engineering researcher Aaron Babier and his team have stepped-in with AI-based software to automate the process and cut down how long it takes for a radiation therapy plan to be created from days to hours, potentially even minutes.
The team – from the University of Toronto’s Department of Mechanical & Industrial Engineering – also includes Justin Boutilier, Professor Timothy Chan, and Professor Andrea McNiven. Each of the researchers sees radiation therapy design as an optimisation problem.
By analysing historical radiation therapy data, the AI behind the software applied it to an optimisation engine to develop treatment plans. When the plans their software tool created was compared with those manually created for 217 patients treated for throat cancer, they were almost indistinguishable.
The difference, however, is their AI-powered tool created the plans within 20 minutes.
Babier explained:
“Right now treatment planners have this big time sink. If we can intelligently burn this time sink, they’ll be able to focus on other aspects of treatment.
The idea of having automation and streamlining jobs will help make health-care costs more efficient. I think it’ll really help to ensure high-quality care.”
Most of us have some unwelcome connection to cancer. According to statistics, one in two people in the UK born after 1960 will be diagnosed with some form of cancer during their lifetime.
Babier has a personal vendetta against the disease. He shares when he was 12 years old his stepmom sadly passed away from a brain tumour.
“I think it’s something that’s always been at the back of my head. I know what I want to do, and that’s to improve cancer treatment,” he says. “I have a family connection to it.”
What are your thoughts on the use of AI in cancer treatment?
