AI tools can change almost overnight, keeping researchers, clinicians, and journals on their toes. In a video interview, Radiology: Artificial Intelligence editor Dr. Charles Kahn explains how the field is keeping pace, where AI could improve scientific publishing, and which technologies he is following most closely.
“There is a greater understanding of what it takes to provide scientifically valid, rigorously evaluated AI tools,” Kahn said. “The reproducibility of the work has gotten better, and the quality of the science has improved considerably.”
Kahn also points out strong collaboration across national and regional borders and previews the journal’s plans to look “just over the horizon” at developments in AI and machine learning, including robotics, agentic AI, and quantum machine learning.
![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&dpr=2&fit=crop&h=167&q=70&w=250)
