Synthetic chest X-ray images from text prompts: Machine learning

Research output: Contribution to journalComment/DebateContributedpeer-review

Contributors

Abstract

A latent diffusion model pre-trained on pairs of natural images and text descriptors can be adapted to generate realistic chest radiographs that are controlled by free-form medical text prompts.

Details

Original languageEnglish
Pages (from-to)439-440
Number of pages2
JournalNature biomedical engineering
Volume9
Issue number4
Early online date7 Oct 2024
Publication statusPublished - Apr 2025
Peer-reviewedYes

External IDs

ORCID /0000-0002-3730-5348/work/198594623