With lung cancer being the leading cause of cancer-related deaths in the U.S., effective early screening is key to saving lives. Researchers at the Mayo Clinic say they've developed new software that can help classify lung nodules noninvasively, saving lives and health care costs.
A pilot study of the program called Computer-aided Nodule Assessment and Risk Yield, or Canary, appears in the April issue of the Journal of Thoracic Oncology.
Canary leans on data from high-resolution CT images of a common type of cancerous nodule in the lung called pulmonary adenocarcinomas. It matches every pixel of the lung image to one of nine unique radiological exemplars. In the pilot study, it was able to classify the lesions as aggressive or indolent with high sensitivity, as compared to microscopic analyses of the lesions after being surgically removed and analyzed by lung pathologists.
"Pulmonary adenocarcinoma is the most common type of lung cancer and early detection using traditional computed tomography (CT) scans can lead to a better prognosis," Tobias Peikert, a Mayo Clinic pulmonologist and senior author of the study, said in a news release. "However, a subgroup of the detected adenocarcinomas identified by CT may grow very slowly and may be treatable with less extensive surgery."
Peikert says that without effective screening, most lung cancer patients don't identify the disease until they are at an advanced stage and far more likely to die from it. Yet, screening via CT scans would be an expensive way to improve the survival rate, as it often can lead to overtreating slow-growing tumors. The hope is that Canary can identify those tumors that can be treated with less extensive -- and expensive -- surgery.