Health AI Central
Peer-Reviewed Publication
Nat Biomed Eng2026;10(8):1610-1628.August 1, 2026Journal Article

Generalist foundation models from a multimodal dataset for 3D computed tomography.

Ibrahim Ethem Hamamci1,2,3, Sezgin Er4,5, Chenyu Wang6, Furkan Almas5, Ayse Gulnihan Simsek5, Sevval Nil Esirgun5, Irem Dogan5, Omer Faruk Durugol5, Benjamin Hou7, Suprosanna Shit4,8, Weicheng Dai6, Murong Xu4,8, Hadrien Reynaud9, Muhammed Furkan Dasdelen5, Bastian Wittmann4,8, Tamaz Amiranashvili4,8, Enis Simsar10, Mehmet Simsar5, Emine Bensu Erdemir5, Abdullah Alanbay5, Anjany Sekuboyina4,8, Berkan Lafci4,8, Ahmet Kaplan5, Zhiyong Lu7, Malgorzata Polacin11, Bernhard Kainz9,12, Christian Bluethgen11, Kayhan Batmanghelich6, Mehmet Kemal Ozdemir5, Bjoern Menze4,8
1Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland. ibrahim.hamamci@uzh.ch.
2ETH AI Center, ETH Zurich, Zurich, Switzerland. ibrahim.hamamci@uzh.ch.
3International School of Medicine, Istanbul Medipol University, Istanbul, Turkey. ibrahim.hamamci@uzh.ch.
4Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland.
5International School of Medicine, Istanbul Medipol University, Istanbul, Turkey.
6Department of Electrical and Computer Engineering, Boston University, Boston, MA, USA.
7Division of Intramural Research, National Institutes of Health, Bethesda, MD, USA.
8ETH AI Center, ETH Zurich, Zurich, Switzerland.
9Department of Computing, Imperial College London, London, UK.
10Department of Computer Science, ETH Zurich, Zurich, Switzerland.
11Institute for Diagnostic and Interventional Radiology, University Hospital Zurich, Zurich, Switzerland.
12Department Artificial Intelligence in Biomedical Engineering, FAU Erlangen-Nürnberg, Erlangen, Germany.
PubMed DOI

Abstract

Advancements in medical imaging AI, particularly in 3D imaging, have been limited due to the scarcity of comprehensive datasets. We introduce CT-RATE, a public dataset that pairs 3D medical images with corresponding textual reports. CT-RATE comprises 25,692 non-contrast 3D chest CT scans from 21,304 unique patients. Each scan is accompanied by its corresponding radiology report. Leveraging CT-RATE…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.