Agfa Healthcare is unveiling a work-in-progress system that integrates digital pathology and its Impax PACS at this week's RSNA 2011 meeting in Chicago. The company is also highlighting recent Impax installations.
The integrated pathology system includes a high-throughput, whole slide scanning device coupled with dedicated analytical workstation used by pathologists to view digital pathology images. Once slides are digitally scanned, the pathologist selects the regions of interest to be automatically integrated into the Impax PACS.
The system enhances data sharing of radiology and pathology images, and improves productivity and enhances quality assurance in pathology for university hospitals and large clinics, according to the company.
The system is now undergoing clinical review at La Pitié-Salpêtrière hospital, a 1600-bed teaching hospital in Paris.
Agfa also announced that it has signed an agreement with the Maastricht Universitair Medisch Centrum+ in the Netherlands to install its Impax RIS/PACS and Impax for Nuclear Medicine. The systems will provide workflow support to both the radiology and nuclear medicine departments. Implementation will begin in January 2012.
In addition, the Cleveland Clinic in Ohio has successfully deployed Impax 6.5 PACS software as part of its contract with Agfa to provide its Impax platform.
![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&dpr=2&fit=crop&h=167&q=70&w=250)
