Dr. Julian Caspers of University Hospital Düsseldorf has evaluated the future prospects of radiology AI in an interview posted by the German Roentgen Society (DRG).
Caspers notes AI's increasingly important role in modern radiology and AI-supported technologies in facilitating the work of radiologists by analyzing image data, assisting with diagnoses, and automating routine tasks.
"In the long term, we are striving for comprehensive AI systems that integrate seamlessly into everyday work and not only evaluate images but also summarize clinical data and support administrative tasks," he explained.
However, there are still technical and economic hurdles that AI must overcome.
"The integration of AI into everyday clinical practice is still limited," Caspers said. "Many of the products are highly specialized and only cover niche areas. In addition, profitability is a hurdle for many hospitals, as the use of AI is often not remunerated separately."
Radiologists' acceptance of AI lags, Caspers added.
"There are still many uncertainties, especially due to systematic misjudgments and insufficiently validated products," Caspers explained. "This is where research can make a decisive contribution to making the technology suitable for practical use."
You can read the full interview 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&dpr=2&fit=crop&h=167&q=70&w=250)
