Title:	ST-BERT
DNr:	Berzelius-2024-407
Project Type:	LiU Berzelius
Principal Investigator:	Sanja Vickovic <sanja.vickovic@scilifelab.uu.se>
Affiliation:	Uppsala universitet
Duration:	2024-10-15 – 2025-05-01
Classification:	30401
Homepage:	https://github.com/adaly/gridnext
Keywords:

Abstract

Registration of histology images from multiple sources is a pressing problem in large-scale studies of spatial -omics data. Researchers often perform ‘common coordinate registration’, akin to segmentation, in which samples are partitioned based on tissue type to allow for quantitative comparison of similar regions across samples. Accuracy in such registration requires both high image resolution and global awareness, which mark a difficult balancing act for contemporary deep learning architectures. We plan to build a spatial transcriptomics (ST) and histology large language model to solve this problem.