Will robotic process automation have a greater impact on radiology over the next five years than deep learning? Dr. Bradley Erickson, PhD, makes the case for this "mundane" form of artificial intelligence (AI) technology.
In his May 5 presentation at the AuntMinnie.com Spring 2021 Virtual Conference, Erickson reviews key current applications for AI in radiology and discusses issues relating to trusting and monitoring the performance of AI algorithms.
He also shares how robotic process automation -- an approach increasingly adopted in many nonhealthcare industries -- could enable AI models to be automatically applied to specific imaging studies, as well as facilitate training of algorithms.
Erickson is medical director for AI at the Mayo Clinic in Rochester, MN.
![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&dpr=2&fit=crop&h=167&q=70&w=250)
