Computer-Aided Diagnosis Tool Might Help Distinguish Small Lung Cancer Nodules From Benign Nodules
The National Lung Screening Trial reported a 20% reduction in lung cancer mortality achieved through low-dose computed tomography (CT) screening of the at-risk population, compared to screening with chest x-ray. However, challenges with the clinical implication of CT screening for lung cancer remain, including the high number of lesions detected that require further follow-up, approximately 97% of which are ultimately diagnosed as benign.
A computer-aided diagnosis tool can be designed to determine the probability of malignancy of a lung nodule based on objective measurements. While current computer-aided diagnosis tools examine the pulmonary nodule’s shape, density, and border, analyzing the lung tissue surrounding the nodule is an area that has been minimally explored.
Study Details
Preliminary findings from researchers from the University of Iowa indicate that computer-aided diagnosis can help distinguish between a benign and malignant lesion from the distinguishable features in the nodule and the surrounding tissue. The findings were presented yesterday at the International Association for the Study of Lung Cancer’s 15th World Conference on Lung Cancer in Sydney, Australia
“CT-mediated lung cancer screening in the most at risk patient population has significant potential to save lives; however, there is widespread concern regarding the increase in follow-up procedures and associated health-care cost involved with following every identified small nodule, of which less than 5% will be determined to be cancer,” said Jessica C. Sieren, PhD, Assistant Professor of Radiology and Biomedical Engineering at the University of Iowa. “The computer-aided diagnosis tool we have developed is unique in its designed applicability to small nodules less than 3 cm, and preliminary findings show high potential to assist in early nodule diagnoses.”
The content in this post has not been reviewed by the American Society of Clinical Oncology, Inc. (ASCO®) and does not necessarily reflect the ideas and opinions of ASCO®.
