Real Time Tomography debuted its new AndaraGPU breast image processing software at this week's RSNA meeting in Chicago. The software is designed to speed image reconstruction and improve clinical workflow in breast imaging, according to the Philadelphia-based firm.
Using Quadro professional graphics processing units (GPUs) from NVIDIA of Santa Clara, CA, and AdaraGPU yields processing speeds up to 10 times faster than conventional central processing unit (CPU)-based image processes, according to the companies. AdaraGPU features an integrated plug-and-play design to enhance performance of mammography systems.
The companies are also demonstrating Briona, a real-time GPU-accelerated 3D image reconstruction software for digital breast tomosynthesis, at RSNA 2010. Briona is currently in beta development and for investigational use only.
Related Reading
NVIDIA launches new graphics package, February 22, 2008
NVIDIA partners with Planar, November 25, 2007
Road to RSNA, Medical Displays, Planar Systems, November 2, 2007
NVIDIA upgrades board technology, September 13, 2007
Planar, Matrox announce joint venture at SIIM, June 7, 2007
Copyright © 2010 AuntMinnie.com
![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&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.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)
