GE HealthCare and Boston, MA-based Mass General Brigham (MGB) plan to integrate medical imaging foundation models into AI research work, with a focus on responsible AI practices.
This work builds on a 10-year commitment undertaken by both organizations in 2017, which has seen the two working together on AI platforms and exploring the use of AI across a range of diagnostic and treatment models through sustainable AI development.
One area of exploration for the organizations revolves around foundation models, which they said have the potential to improve workflow efficiency and imaging diagnosis by solving a diverse set of tasks. They praised foundation models as being a reliable and adaptable foundation for developing AI applications tailored to the healthcare sector.
![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)
