{"slug": "stanford-s-merlin-puts-vision-language-ai-on-full-3d-ct-scans", "title": "Stanford's Merlin puts vision-language AI on full 3D CT scans", "summary": "Stanford researchers led by Louis Blankemeier, Ashwin Kumar and Akshay S. Chaudhari published Merlin, a 3D vision-language foundation model for CT scans, in Nature on March 4. The model was trained on over 6 million images from 15,331 CT scans and evaluated on 752 tasks including disease prediction and report generation, addressing the gap of 2D-focused medical AI models.", "body_md": "Louis Blankemeier, Ashwin Kumar and Akshay S. Chaudhari's Stanford-led team published Merlin, a 3D vision-language foundation model for computed tomography, in a March 4 [Nature paper](https://www.nature.com/articles/s41586-026-10181-8) that takes aim at one of radiology AI's practical gaps: most medical vision-language models have been built around 2D images and shorter text, while CT interpretation is volumetric, text-heavy and tied to patient history.\n\nMerlin was trained on paired abdominal CT scans, diagnosis codes and radiology reports, using more than 6 million images from 15,331 CT scans, more than 1.8 million diagnosis codes and more than 6 million report tokens in the training set. The researchers evaluated the model on 6 task types and 752 individual tasks, including zero-shot findings classification, phenotype classification, image-report retrieval, 5-year chronic disease prediction, radiology report generation and 3D organ segmentation.", "url": "https://wpnews.pro/news/stanford-s-merlin-puts-vision-language-ai-on-full-3d-ct-scans", "canonical_source": "https://runtimewire.com/article/stanford-merlin-3d-ct-vision-language-model", "published_at": "2026-07-03 05:16:43+00:00", "updated_at": "2026-07-03 21:17:36.580391+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "computer-vision", "ai-research", "natural-language-processing"], "entities": ["Stanford", "Louis Blankemeier", "Ashwin Kumar", "Akshay S. Chaudhari", "Merlin", "Nature"], "alternates": {"html": "https://wpnews.pro/news/stanford-s-merlin-puts-vision-language-ai-on-full-3d-ct-scans", "markdown": "https://wpnews.pro/news/stanford-s-merlin-puts-vision-language-ai-on-full-3d-ct-scans.md", "text": "https://wpnews.pro/news/stanford-s-merlin-puts-vision-language-ai-on-full-3d-ct-scans.txt", "jsonld": "https://wpnews.pro/news/stanford-s-merlin-puts-vision-language-ai-on-full-3d-ct-scans.jsonld"}}