Hidden Data Behind Imaging Scans for Cancer May offer New Radiotherapy Strategies

“Currently, there is a one-size-fits-all process for selecting radiation therapy doses, which might be too much for some patients and not enough for others,” said Joseph Deasy, PhD, senior author of the study and chair of the department of medical physics at Memorial Sloan-Kettering Cancer Center (New York, NY, USA). “Radiomics will help us know when we can turn down the treatment intensity with confidence, knowing we can still control the disease.”

In the study, researchers performed PET scanning in 163 non-small-cell lung cancer patients and 174 head and neck cancer patients before and after treatment. They extracted a range of information from each tumor, including the intensity value of the PET image, the roughness of the image, and other information, such as how round the tumor was. In PET, the brighter an area is, the higher the intensity, revealing that the tumor is consuming a greater amount of energy from the injected radioactive glucose substitute tracer.

Comparing the data gathered from the before and after scans to how the patient fared—including whether the tumor shrank or how long the patient survived—researchers can create models that will help direct future therapy. In this study, for instance, researchers determined that lung tumors that have a higher uptake of the tracer need to be treated with a higher dose of radiation than is typically prescribed.

“Standard protocol today is to only use PET imaging to define the extent of a tumor to be treated,” said Dr. Deasy. “Based on the information from this study, the data would be extracted from those images and put into models that would tell the physician what dose was required to kill the tumor with a high probability.” He noted that radiomics is a team effort that requires good collaboration between physicians, physicists, and computer scientists.

Related Links:
Memorial Sloan-Kettering Cancer Center