Computer-aided diagnosis was evaluated to determine efficacy in radiologic assessment of lung cancer.
Computer-aided diagnosis (CADx) improves the accuracy of radiologic assessment of lung cancer, according to a study published in Academic Radiology.
Researchers from Johns Hopkins University in Baltimore, MD, sought to evaluate the improved accuracy of lung cancer radiologic assessment if CADx was added to the process. The researchers performed a systematic review of the literature for studies that evaluated CADx for lung cancer with chest X-ray or CT. They found 14 articles, representing 1,868 scans, for inclusion in the study. In nine studies, the accuracy of the radiologist was evaluated twice, once without CADx and then again with CADx. These were evaluated for the review. The five other studies used pathological diagnosis for verification.[[{"type":"media","view_mode":"media_crop","fid":"44911","attributes":{"alt":"lungs","class":"media-image media-image-right","id":"media_crop_2412023048692","media_crop_h":"0","media_crop_image_style":"-1","media_crop_instance":"5067","media_crop_rotate":"0","media_crop_scale_h":"0","media_crop_scale_w":"0","media_crop_w":"0","media_crop_x":"0","media_crop_y":"0","style":"height: 160px; width: 160px; border-width: 0px; border-style: solid; margin: 1px; float: right;","title":"©Treter/Shutterstock.com","typeof":"foaf:Image"}}]]
Among the nine observer-performance studies, there was an average of 10.3 radiologists per study, and eight of these studies showed a significant accuracy improvement with CADx. “Increases in the receiver operating characteristic (ROC) area under the curve of .8 or higher were seen in all nine studies that reported it, except for one that employed subspecialized radiologists,” the authors wrote.
They concluded that their review demonstrated that CADx improved the accuracy of lung cancer assessment over manual review, suggesting that more research be conducted into incorporating its use into screening and regular clinical workflow.
Stay at the forefront of radiology with the Diagnostic Imaging newsletter, delivering the latest news, clinical insights, and imaging advancements for today’s radiologists.
Study Shows Enhanced Diagnosis of Coronary Artery Stenosis with Photon-Counting CTA
July 10th 2025In a new study comparing standard resolution and ultra-high resolution modes for patients undergoing coronary CTA with photon-counting detector CT, researchers found that segment-level sensitivity and accuracy rates for diagnosing coronary artery stenosis were consistently > 89.6 percent.
Considering Breast- and Lesion-Level Assessments with Mammography AI: What New Research Reveals
June 27th 2025While there was a decline of AUC for mammography AI software from breast-level assessments to lesion-level evaluation, the authors of a new study, involving 1,200 women, found that AI offered over a seven percent higher AUC for lesion-level interpretation in comparison to unassisted expert readers.