Smarter Radiation Therapy Enhances Personalized Care for Cancer Patients

The latest advance in radiation therapy—using artificial intelligence to adjust treatments as needed without delay—is now available for select cancer patients at Columbia University Irving Medical Center/NewYork-Presbyterian. 

The new advance solves a long-standing issue in radiation oncology: the difficulty of adapting treatment to anatomical changes in the patient or the tumor that can occur during the many weeks of therapy.

“Patients can undergo many physical changes during radiation treatment—the size and shape of the tumor may start to change, the patient may lose a lot of weight, or nearby organs may shift position,” says Tony Wang, MD, professor of radiation oncology at Columbia University Vagelos College of Physicians and Surgeons. “Radiation oncologists have long recognized this issue, but we haven’t had the technological capability or computing power to recalculate the treatment plan quickly enough to account for these changes without causing a delay in treatment.”   

With the new system, known as adaptive online radiation therapy, patients undergoing weeks of radiation treatment may have their treatment plan reassessed and optimized before every session, allowing the maximal radiation dose to be delivered to the tumor while reducing the risk of irradiating nearby healthy tissues. 

“The benefits to the patient are potentially substantial,” says Michael Price, PhD, associate professor of radiation oncology at Columbia University Vagelos College of Physicians and Surgeons and director of the system’s installation at Columbia/NewYork-Presbyterian. “With conventional radiotherapy, if a tumor shrinks after several weeks of treatment, the patient still receives radiation designed for the full-sized tumor. We can create a new plan based on these changes, but it frequently leads to a pause in a patient’s course of treatment since it requires an additional CT scan and time to create a new plan from scratch.”

“With the new system, the plan is automatically recalculated based on the patient’s condition during each treatment, allowing us to offer a highly personalized treatment experience. That means potentially better cancer control while simultaneously reducing radiation side effects.” 

A paradigm shift in radiation treatment planning 

Currently, radiation therapy planning is a complex process that can take up to two weeks to prepare and test before the patient receives the first dose.  

Once treatment begins, the patient is positioned exactly the same way during each session to ensure that the radiation is delivered to the intended location. Imaging may be used to help align the patient before each treatment, but these scans cannot be used to quickly alter a patient’s treatment plan. 

The new system uses sophisticated three-dimensional CT imaging to identify changes in the patient’s anatomy—including the tumor and nearby structures—that have occurred since the patient was last treated. A machine learning module automatically recalculates the plan based on the patient’s changed anatomy. 

Each recalculated treatment plan is reviewed and approved by the radiation therapy team before it is implemented. The entire process adds only a few minutes to each treatment. 

“The adaptive radiotherapy system predicts what the treatment team would do when faced with the patient's anatomy on the day of treatment versus day zero, giving us the ability to align the plan to the patient. That’s a paradigm shift,” Price says. 

Potential benefits for some cancers  

The adaptive radiotherapy system may be used to treat patients with prostate, cervical, and rectal cancers, which are located near organs that frequently change in volume, such as the bladder, bowel, and colon.  

The system also may be used to treat head and neck cancers and other tumors that tend to shrink quickly when treated with radiation. 

“Irradiating large head and neck cancers also poses a risk to nearby structures such as the optic nerve or brainstem,” says Wang. “With the adaptive system, we can deliver very focused radiation doses to the tumor while reducing the risk to nearby structures.” 

“A recent study, in patients with cervical or rectal tumors, shows that adaptive online radiation therapy improves treatment precision without adding substantial time and resources,” Price says. “We are currently planning additional studies to see if the new system can improve outcomes and reduce side effects for patients with prostate, pancreas, or anal tumors.” 


More information 

For additional information, contact the Department of Radiation Oncology at 212-305-7077.

Price is also vice chairman for physics and director of enterprise technical strategy and innovation in the Department of Radiation Oncology.