“AI (artificial intelligence) can help treatment planners and dosimetrists by saving a lot of time doing simpler and more repetitive tasks…,” explained Steve Jiang, Ph.D., director of the medical artificial intelligence and automation lab of the Dept. of Radiation Oncology, University of Texas Southwestern.
For those unfamiliar with AI, we are referring to computer or machine intelligence systems that can perform tasks that usually require human intelligence, such as visual perception, speech recognition, decision-making abilities.
Discussions about how AI will impact humanity have been occurring for many years in many industries; however, AI has been making headway into the radiation therapy and oncology fields within the past few years.
Two such companies making the technological leap in AI for radiation oncology and treatment planning are Varian and RaySearch – both have developed machine-learning technologies to automate treatment plans.
“The fully automated system takes in the patient imaging and the target defined by the physician, and out on the other end comes a fully deliverable therapy plan,” said Kevin Moore, Ph.D., DABR, deputy director of medical physics and associate professor, University of California San Diego.
Dr. Moore said that “The comparisons were very good,” about tests that were made when SCSD began using the software in tandem with traditional treatment planning. After a human plan was developed, they ran the AI, and it only took 5-20 minutes to complete depending on the complexity of the plan. UCSD has now treated well over 1,000 patients with its AI-assisted planning.
RaySearch has incorporated machine learning clinically since 2019. The system is trained to take the treatment planning computed tomography (CT) scans and automatically segment the anatomy and auto-contour to help speed the planning process.
“The automated treatment planning system works by training the algorithm with curated sets of similar treatment plans, and it is able to detect the patients who are most similar to a novel patient and create a new treatment plan…,” explained Leigh Conroy, Ph.D., physics resident, at Princess Margaret Cancer Center, who has been working on the AI implementation.
RaySearch is developing several other machine learning applications, including target volume estimation and large-scale data extraction and analysis.
Other highlights of AI technologies are adaptive AI-driven onboarding planning within the radiotherapy system, auto contouring for treatment plans, and creating MRI-derived CT scans for planning. To read more on these exciting technologies, read the full article here.