AI could kickstart early radiation therapy for cancer patients
Image credit: Katarzyna Bialasiewicz - Dreamstime
Artificial intelligence (AI) could one day be used to help cancer patients start their radiation therapy sooner, thereby decreasing the odds of the cancer spreading, by instantly translating complex clinical data into an optimal plan of attack.
Typically, cancer patients must wait from several days to over a week to begin therapy while doctors manually develop treatment plans. However, new research from the University of Texas (UT) Southwestern Medical Center shows how enhanced deep-learning models were able to streamline this process down to a fraction of a second.
“Some of these patients need radiation therapy immediately, but doctors often have to tell them to go home and wait,” said Steve Jiang, the director of UT Southwestern’s Medical Artificial Intelligence and Automation (MAIA) Lab. “Achieving optimal treatment plans in near real-time is important and part of our broader mission to use AI to improve all aspects of cancer care.”
Radiation therapy is the most common form of cancer treatment that utilises high radiation beams to destroy cancer cells and shrink tumours. Previous research shows that delaying this therapy by even a week can increase the chance of some cancers either recurring or spreading by 12-14 per cent.
These statistics motivated Jiang and his team to explore methods of using AI in order to improve multiple facets of radiation therapy – from the initial dosage plans required before the treatment can begin to the dose recalculations that occur as the plan progresses. These dosage plans may also help to avoid a potentially crucial delay in treatment.
Jiang said that developing a sophisticated treatment plan can be a time-consuming and tedious process that involves a careful review of the patient’s imaging data and several phases of feedback within the medical team.
However, a new study from the MAIA Lab on dose prediction, published in Medical Physics, has demonstrated AI’s ability to produce optimal treatment plans within five-hundredths of a second after receiving clinical data for patients.
A second study by Jiang and his team, also published in Medical Physics, showcased how AI can quickly and accurately recalculate dosages before each radiation session, considering how the patient’s anatomy may have changed since the last therapy. The study also found a conventional, accurate recalculation sometimes required patients to wait 10 minutes or more, in addition to the time needed to conduct anatomy imaging before each session.
To overcome this challenge, Jiang’s team developed an AI algorithm that combined two conventional models that had been previously used for dose calculation: a simple, fast model that lacked accuracy and a complex one that was accurate but required a much longer time, often around half an hour.
The newly developed AI assessed the differences between the models – based on data from 70 prostate cancer patients – and learned how to utilise both speed and accuracy to generate calculations within one second.
UT Southwestern plans to use the new AI capabilities in clinical care after implementing a patient interface. Meanwhile, the MAIA Lab is currently developing deep-learning tools for several other purposes. These include enhanced medical imaging and image processing, automated medical procedures, and improved disease diagnosis and treatment outcome prediction.
At the start of the year, a Nature study found that an AI programme proved as effective as expert radiologists at detecting breast cancer based on screening mammograms and showed promise in reducing errors.
Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.