{"entity":{"id":"merlin-ct","kind":"technology","name":"Merlin (Stanford abdominal CT vision-language model)","aka":[],"tldr":"Merlin is a model trained on 15,000 CT scans with their reports that can find and describe hundreds of findings.","summary":"Merlin is a 3D vision-language model for abdominal CT from Stanford whose image encoder is aligned with both the free-text radiology report and structured electronic health record codes. The 2024 arXiv paper describes training on 15,000 CT scans, amounting to 6M images and 6M EHR codes, and shows zero-shot classification of hundreds of findings plus report generation. It is aimed at radiology research groups exploring report-supervised learning, a route that avoids hand labelling every finding. Its limits are that the data come from a single institution and cover the abdomen only, so generalisation to other scanners, populations and body regions is untested; for oncology the relevance is in finding and describing lesions rather than staging. For a newcomer: Merlin learned to read abdominal CT scans by studying the reports radiologists wrote about them.","status":"emerging","asOf":"2026-09-08","links":[{"label":"Merlin (arXiv 2024)","url":"https://arxiv.org/abs/2406.06512"}],"tags":["foundation-model","radiology"],"related":[],"cancers":[],"sections":["ai-computation","imaging"],"technologies":["radiology-ai-screening","ct"],"targets":[],"drugs":[],"companies":[],"institutions":["stanford"],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":[],"keyPapers":[],"journals":[],"dependsOn":[],"notes":[],"principle":"3D image encoder aligned with report text and structured codes.","strengths":["Report-supervised 3D learning"],"limitations":["Single institution","Abdomen only"],"since":2024},"route":"/technologies/merlin-ct/","neighbours":{"section":[{"id":"ai-computation","kind":"section","name":"AI & Computation","route":"/fronts/ai-computation/"},{"id":"imaging","kind":"section","name":"Imaging","route":"/fronts/imaging/"}],"technology":[{"id":"radiology-ai-screening","kind":"technology","name":"AI in radiology","route":"/technologies/radiology-ai-screening/"},{"id":"ct","kind":"technology","name":"CT (computed tomography)","route":"/technologies/ct/"},{"id":"pathology-foundation-model","kind":"technology","name":"Pathology & radiology foundation models","route":"/technologies/pathology-foundation-model/"}],"institution":[{"id":"stanford","kind":"institution","name":"Stanford Health Care / Stanford Cancer Institute","route":"/institutions/stanford/"}],"roadmap":[{"id":"ai-oncology-roadmap","kind":"roadmap","name":"AI in oncology roadmap: pattern readers → foundation models → agents in the workflow","route":"/roadmaps/ai-oncology-roadmap/"}]}}