Radiologists' use of CAD systems as a second reader to catch missed nodules during lung cancer screening.
Computer-aided detection (CAD) systems can be a useful second reader back-up for radiologists screening for lung cancer, according to an article published in Radiology.
Researchers from the Icahn School of Medicine at Mount Sinai in New York City and Cornell University, Ithaca, NY, sought to determine if CAD was a useful tool to help radiologists detect lung cancers during early imaging.
The researchers obtained images of 50 lung cancers that manifested as a solid nodule on CT scans in annual rounds of screening (time 1). Time zero was when all cancers were missed. Four CAD systems (CAD 1, CAD 2, CAD 3, and CAD 4) were compared to the radiologists’ findings. Two radiologists assessed the CAD-system detected nodules, and they also documented the solid nodules that were not detected by the CAD system.
The average diameter of the 50 cancers at time 0 and time 1 was 4.8 mm and 11.4 mm, respectively. The results showed that the CAD systems detected at least 56% of the nodules.
The number of CAD-system–detected nodules that were rejected per CT scan for CAD systems 1 to 4 at time 0 was 7.4, 1.7, 0.6, and 4.5 respectively.
The researchers concluded that most of the lung cancers, up to 70%, that had not been detected by the radiologist upon screening were detected by the CAD systems, however, about 20% of the nodules that were detected by radiologists were not picked up by the CAD system.
MRI-Based AI Radiomics Model Offers 'Robust' Prediction of Perineural Invasion in Prostate Cancer
July 26th 2024A model that combines MRI-based deep learning radiomics and clinical factors demonstrated an 84.8 percent ROC AUC and a 92.6 percent precision-recall AUC for predicting perineural invasion in prostate cancer cases.
Breast MRI Study Examines Common Factors with False Negatives and False Positives
July 24th 2024The absence of ipsilateral breast hypervascularity is three times more likely to be associated with false-negative findings on breast MRI and non-mass enhancement lesions have a 4.5-fold likelihood of being linked to false-positive results, according to new research.
Can Polyenergetic Reconstruction Help Resolve Streak Artifacts in Photon Counting CT?
July 22nd 2024New research looking at photon-counting computed tomography (PCCT) demonstrated significantly reduced variation and tracheal air density attenuation with polyenergetic reconstruction in contrast to monoenergetic reconstruction on chest CT.