An automated lung nodule matching program can improve radiologists’ efficiency almost two-fold, according to a study published in the July issue of American Journal of Roentgenology.

Serial CT assessment and comparison of pulmonary nodules has been a manual, time-consuming process. The advent of automated lung nodule matching software may offer a new model to improve diagnostic performance and efficiency.

A research team, led by Chi Wan Koo, MD, of the department of radiology at Mayo Clinic Health System in Mankato, Minn., designed a retrospective study to determine the impact of an automated program on lung nodule matching efficiency.

The study, conducted at New York University Langone Medical Center in New York City, included 57 patients who underwent serial CT between 2007 and 2009, yielding a total of 325 pulmonary nodules identified on CT. Four thoracic radiologists manually identified and manually matched the pulmonary nodules on serial CT examinations while being timed. After six weeks, the radiologists evaluated the same CT studies using the automated nodule matching software and were timed again.

The researchers found that the time required for manual nodule matching ranged from one second to approximately 11.4 minutes, whereas automated nodule matching ranged from less than one second to approximately 6.6 minutes, Koo said in a press release. “The maximal time saved per case was 684 seconds (mean, 138 seconds).”

The software provided high accuracy and delivered match rates of 90 percent for two readers and 79 percent and 92 percent for the remaining two radiologists.

The study found that “the greater the number of nodules needing to be matched, the greater the benefit in using the software,” reported Koo. Matching of nodules 6 mm or smaller was “particularly aided by use of the automated program.” The locations of the nodules and change in nodule size did not have a significant impact on matching efficiency, she added.

Koo and colleagues concluded, “The significantly improved matching efficiency supports the incorporation of such automated programs into clinical practice.”