Harrison.ai has released Harrison.Rad 1.5, an update of its radiology-specific AI foundation model.
The new version builds on Harrison.Rad 1, which the company launched in 2024, and can now interpret a study in light of clinical questions being asked and the patient’s history, compare findings against prior studies, and generate a draft report in narrative radiologist prose, the company said. Other new capabilities include broader anatomical coverage and sharper localization across body parts.
Harrison.Rad 1.5 was trained on approximately 6 million diagnostic imaging studies, a 33% increase over Harrison.Rad 1, the company noted. It is available for research at chat.harrison.ai, with API access on request. Harrison.ai said it is pursuing regulatory clearance in the U.S. and EU; the model is not cleared for clinical use.
![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)
