Olivier Gevaert: “Generation of synthetic whole-slide image tiles of tumours from RNA-sequencing data via cascaded diffusion models” published in Nature Biomedical Engineering

HomeStanford - Department of Biomedical Data Science  > DBDS  > Research News  > Olivier Gevaert: “Generation of synthetic whole-slide image tiles of tumours from RNA-sequencing data via cascaded diffusion models” published in Nature Biomedical Engineering
Olivier Gevaert and team have developed a biomedical model inspired by DALL-E, we use RNA expression profiles to generate synthetic digital pathology images across several cancer tissues. We show that these synthetic data can be used in combination with real data, cell type distributions are representative of real tissues and synthetic data can be used for self supervised learning. You can try the model here: https://lnkd.in/egWGGDYJ. We also generated 1M images for download: https://lnkd.in/eSsM9ZqA Amazing work by Francisco Carrillo Pérez in the lab, and only possible thanks to the Polaris compute resources and collaboration with Ravi Madduri at Argonne National Laboratory, U.S. Department of Energy (DOE). Full text is available here: https://rdcu.be/dBZJK. https://www.nature.com/articles/s41551-024-01193-8
Posted on
Olivier Gevaert and team have developed a biomedical model inspired by DALL-E, we use RNA expression profiles to generate synthetic digital pathology images across several cancer tissues.
You can try the model here: https://lnkd.in/egWGGDYJ. We also generated 1M images for download: https://lnkd.in/eSsM9ZqA
Amazing work by Francisco Carrillo Pérez in the lab, and only possible thanks to the Polaris compute resources and collaboration with Ravi Madduri at Argonne National Laboratory, U.S. Department of Energy (DOE).
Full text is available here: https://rdcu.be/dBZJK.
https://www.nature.com/articles/s41551-024-01193-8