Lung Nodule Matching Software Improves Diagnostic Efficiency

Radiologists using an automated lung nodule matching program significantly improved diagnostic efficiency, according to results of a study published in the July issue of American Journal of Roentgenology.

“Pulmonary nodules may be benign or malignant, so we follow these nodules over time with repeated CT scans to watch for changes in each nodule,” said Chi Wan Koo, MD, lead author of the study. “When many nodules are present, it can be difficult to match nodules up for comparison purposes.”

Researchers from New York University Langone Medical Center in New York timed how long it took for four radiologists to assess each of 325 pulmonary modules, identified by CT, found in 57 patients. The radiologists identified and manually matched the pulmonary nodules on CT.
The same radiologists were evaluated again six weeks later, using the same CT images, but this time they were using the automated nodule matching software.

The researchers found that the nodule matching was significantly faster with the automated program, regardless of the interpreting physician. The maximal time saved with the automatic matching was 11.4 minutes. The software was particularly helpful when there were more nodules to be matched, as was matching nodules that were 6 mm or smaller, the researchers noted. The automated program achieved 90 percent, 90 percent, 79 percent, and 92 percent accuracy for the four readers.

As the radiologists became quicker at identifying the nodules, accuracy remained consistent with the automated program, from 79 percent to 92 percent of the time.

“Prior studies have evaluated automated nodule matching accuracy, however no study to our knowledge has assessed the impact of a nodule matching program use on CT interpretation efficiency, where efficiency entails both accuracy and speed,” said Koo.