CAD with chest X-ray to screen for lung cancer may reveal abnormalities, but more study is required.
Computer-aided detection (CAD) with standard chest radiography screening for lung cancer among high-risk patients identified additional actionable lung nodules not found by standard X-ray, according to a study published this month in PLOS One. However, the authors warned that the number of nodules found was too small to draw definitive conclusions and further study is needed.
Researchers from the Cleveland Clinic undertook a randomized screening trial and enrolled 1,424 patients, aged 40 to 75, who had 10 or more pack-years of smoking history and/or who had an additional risk for developing lung cancer. The subjects were randomized to receive either a posterior-anterior view chest radiograph or a sham X-ray.
Researchers evaluated 1,423 patients, 701 of whom received a CAD chest radiograph. Both the plain and CAD images were interpreted by two experienced readers blinded to each other’s findings. Actionable nodules were reported and additional evaluation was tracked. The primary outcome was the rate of developing symptomatic advanced stage lung cancer.
Data were available at six-month follow up for 80.8 percent of the patients, at 12 months for 66.5 percent, at 18 months for 38.5 percent and at 24 months or longer for 1.8 percent.
The researchers found that the readers spotted 22 nodules (11 each reader) among the unaided X-rays and 29 actionable nodules among the CAD X-rays, 11 of which were deemed not to require follow-up.
Of the nodules detected by CAD X-ray and not on standard X-ray, the researchers noted that the nodules were more likely to be smaller and less solid than the ones noted on the standard X-ray.
According to the authors, “the cumulative incidence of symptomatic advanced lung cancer was 0.42 cases per 100 person-years in the control arm; there were no events in the screening arm.”
They concluded that more research is necessary to determine if CAD chest radiography can have a future role as a lung cancer screening tool.
FDA Clears Updated AI Platform for Digital Breast Tomosynthesis
November 12th 2024Employing advanced deep learning convolutional neural networks, ProFound Detection Version 4.0 reportedly offers a 50 percent improvement in detecting cancer in dense breasts in comparison to the previous version of the software.
FDA Clears New Features in AI-Powered Mammography Software Suite
October 11th 2024Therapixel’s MammoScreen suite has received 510(k) FDA clearances for a breast density assessment feature and updated software that includes automated pre-reporting, which reportedly expedites reporting of mammography findings.