CAD boosts ID rate for lung nodules

The use of computer-aided detection with chest X-rays increased the identification rate for actionable lung nodules in at-risk patients, according to a study recently published in the journal PLoS One. The number of nodules identified in the study, however, was too small to determine whether CAD has a role as a lung cancer screening tool.

Lung cancer is most curable at an early stage, according to Peter Mazzone, M.D., and his colleagues at the Cleveland Clinic, but the problem remains that a majority of patients with lung cancer present at an advanced stage, leaving them with poor long-term survival odds. Consequently, there has been much interest in imaging- based lung cancer screening.

Chest X-ray screening trials have demonstrated improved survival, but have not reduced mortality, while chest CT has demonstrated promising survival data, but at a cost of a high number of false positives, according to the study's authors.

"As an alternative to standard chest X-ray and CT screening, the use of a chest X-ray system with an improved ability to detect lung cancer could have some advantages," the authors wrote. "Chest X-rays are readily available, less costly, identify fewer false positives, and subject patients to less radiation. Computer aided detection [CAD] of lung nodules on chest X-rays has the potential to improve the sensitivity of standard chest X-rays to detect early lung cancer."

Mazzone, in an interview with FoxNews.com, added that "the hope is that this specialized kind of X-ray might improve the ability over a standard X-ray to find cancers and minimize some of the drawbacks of CT scans."

The researchers conducted a placebo-controlled trial with more 1,400 subjects between the ages of 40 and 75, who had more than 10 or more pack years of smoking and other risk factors for lung cancer. Half of the subjects underwent chest X-rays with CAD, while the control group went through a placebo screening procedure.

Twenty-nine actionable nodules were identified in the screened arm of the study. Twenty-two of the nodules were identified with X-ray, while the remaining seven were first seen through the use of CAD. Fifteen of the subjects had chest CT performed for further evaluation and a lung nodule was confirmed in four of them. Two were diagnosed as lung cancer and both were identified with chest X-ray and CAD, but were also identified unaided.

"The data suggest that advances in the CAD technology, beyond the version used, are required before an impact of the technology could be expected and that these advances could be of significant benefit to chest x-ray interpretation," the authors said. They added, however, that the number of cancers identified was too small to make any judgments about the intended primary endpoint--the reduction in symptomatic advanced stage lung cancer in the screened group.

To Learn more:
- read the study in the journal PLoS One
- see the article in FoxNews.com

Suggested Articles

When KLAS Research asked more than 300 healthcare leaders to identify the most disruptive company in healthcare, one tech giant was top of mind.

People are demanding free and secure access to their complete health record now. Upcoming federal data-sharing rules will help make that a reality.

A healthcare nonprofit wants to build a “moonshot factory” to bring data science and precision health to remote villages in the developing world.