Dear AuntMinnie Member,
The application of computer-aided detection to CT lung studies is a relatively new technique. CT lung CAD could have a potentially big diagnostic payoff if it proves itself able to boost radiologist performance in CT lung cancer screening -- itself an emerging discipline.
A pair of presentations at last month's RSNA meeting in Chicago assessed the performance of a new work-in-progress CAD algorithm in a lung screening environment, according to an article by staff writer Eric Barnes that we're featuring in our Advanced Visualization Digital Community. While the results weren't a slam dunk for CAD, they showed that the technology offered some improvements.
The first study, by U.S. researchers in several institutions, found that CAD provided a modest increase in overall radiologist sensitivity, and the software was able to detect some lung nodules that the radiologists had missed.
In the second study, German researchers not only examined CAD's impact on sensitivity, but also assessed its effect on radiologist workflow when used concurrently -- that is, when CAD is applied during image interpretation rather than in a second-reader mode after the primary read.
Their results indicate that CAD can actually shorten radiologist reading times when used concurrently. But there's a down side to this interpretation method, the researchers found. Find out more by clicking here, or visit our Advanced Visualization Digital Community at av.auntminnie.com.













![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=112&q=70&w=112)





