Technology out of Vanderbilt University and Mayo Clinic could be cutting false positive rates in CT-based lung cancer screenings, researchers announced in PLOS One this week.
“As physicians, one of the most challenging problems in screening patients for lung cancer is that the vast majority of the detected pulmonary nodules are not cancer,” first author Tobias Peikert, MD, said in a release. “Even in individuals who are at high risk for lung cancer, up to 96 percent of nodules are not cancer.”
Increased lung cancer screening, as well as an increased use of computed tomography, means more than 1.5 million indeterminate lung nodules are incidentally discovered each year in the U.S., Peikert and colleagues wrote in PLOS. It’s becoming what they call “a potential emerging global epidemic of newly detected lung nodules.”
The discovery nodules—benign or not—can often lead to anxiety in patients, Peikert said, and increased risks for physicians. Also, not only do more false positives mean more expensive tests, but they can also lead to surgery and unintentional physician-caused injury or mortality.
According to their study, Peikert and his team pulled data from the National Lung Cancer Screening Trial and used a radiomics approach to test a set of 57 variables for lung nodule density, shape, surface characteristics and the texture of any surrounding tissue.
They found eight variables that were able to distinguish benign from malignant nodules, they wrote, but the research needs further validation.
“Our novel radiomic low-dose computed tomography-based approach for indeterminate screen-detected nodule characterization appears extremely promising,” Peikert et al. wrote. “However, independent external validation is needed.”