French precision radiology developer Raidium unveiled its work-in-progress AI-native PACS viewer at RSNA 2025.
The PACS Viewer, which is based on the company’s foundation model Curia, is trained on a dataset of over 1 billion images, has the ability to interpret an imaging exam produced by any radiology modality, and automatically contextualizes information and executes complete diagnostic reading workflows, according to the company.
Raidium said that the objective of the viewer and the foundation model is to provide a reliable, interactive copilot capable of executing an entire workflow from a single prompt to support the interpreting radiologist and to provide faster, more precise, and more reproducible practice.
The company also established an office this year in the U.S. to accelerate its scientific and operational expansion.
![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)
