Dear Advanced Visualization Insider,
While computer-aided detection (CAD) software has shown potential for improved visualization of pulmonary nodules on low-dose CT studies used in lung cancer screening programs, these sensitivity gains have often come at the cost of a significant number of false-positive results. However, a Dutch team has found that excluding small nodules could still yield high sensitivity while cutting the false-positive rate nearly in half. Find out how they could achieve that performance by visiting here.
CAD isn't a panacea, of course, and French researchers have noted that CAD should not replace radiologists. While CAD can assist radiologists as a second reviewer in evaluating screening mammograms, the software shouldn't be responsible for omitting the complete evaluation of mammograms by a radiologist, according to the group. For full coverage of the research, click here.
In other articles featured recently in your Advanced Visualization Digital Community, a research team found strong results from the use of an advanced reading technique in virtual colonoscopy studies. Radiologists who looked only at CAD results for polyp reduction were able to slash interpretation times down to just three minutes per patient, according to the group. They were also able to retain per-patient sensitivity of 100% for adenomas 6 mm and larger. For the details, click here.
An Israeli research group also found that a computer-assisted surgery system that employs image analysis is showing promise as an orthopedic surgery tool. They determined that the system, which provides virtual trajectory of the guidewire, intraoperative planning, and various measurements, correlated well with manual methods. Find out more here.



![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.auntminnieeurope.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=100&q=70&w=100)






![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.auntminnieeurope.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)







