Software Identifies and Stratifies Risk Posed by Lung Nodules

A multidisciplinary group of researchers has devised a new software tool that noninvasively characterizes pulmonary adenocarcinoma, a common type of cancerous nodule in the lungs.

The pilot study’s findings of the computer-aided nodule assessment and risk yield (CANARY) were published April 2013 in the Journal of Thoracic Oncology. “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,” said Tobias Peikert, MD, a Mayo Clinic (Rochester, MN, USA) pulmonologist and senior author of the study. “However, a subgroup of the detected adenocarcinomas identified by CT may grow very slowly and may be treatable with less extensive surgery.”

CANARY can noninvasively stratify the risk lung adenocarcinomas pose by characterizing the nodule as aggressive or indolent with high-sensitivity, specificity, and predictive values. The software utilizes data gathered from existing high-resolution diagnostic or screening computed tomography (CT) images of pulmonary adenocarcinomas to correlate each pixel of the lung nodule to one of nine unique radiologic exemplars. In testing, the CANARY classification of these lesions had an excellent correlation with the microscopic analysis of the surgically removed lesions that were examined by lung pathologists, according to Dr. Peikert.

“Without effective screening, most lung cancer patients present with advanced stage disease, which has been associated with poor outcomes,” Dr. Peikert said. “While CT lung cancer screening has been shown to improve patient survival, the initiation of a nationwide screening program would carry the risk of overtreatment of slow growing tumors and would be associated with substantial health care costs. CANARY represents a new tool to potentially address these issues.”

Related Links:
Mayo Clinic