Bristol Myers Squibb (BMS) and Microsoft have announced a collaboration aimed at providing improved and more equitable early lung cancer detection.
Under this agreement, Microsoft’s Precision Imaging Network will incorporate U.S. Food and Drug Administration (FDA)-cleared radiology AI algorithms developed with BMS.
The algorithms now available through Precision Imaging Network automatically analyze x-ray and CT images to help identify non-small cell lung cancer (NSCLC), according to the partners. These AI tools are designed to assist clinicians with detecting lung nodules, potentially identifying patients at earlier stages of lung cancer, and aiding in triage.
More than 80% of hospitals in the U.S. use Precision Imaging Network to share medical imaging and access third-party imaging AI, the firms added.
The collaboration is prioritizing expanded access to the algorithms for resource-limited rural hospitals and community clinics across the U.S., according to BMS and Microsoft, promoting earlier diagnosis and follow-up to medically underserved communities.
















![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=112&q=70&w=112)


