Inferring super-resolution tissue architecture by integrating spatial transcriptomics with histology

Nat Biotechnol. 2024 Sep;42(9):1372-1377. doi: 10.1038/s41587-023-02019-9. Epub 2024 Jan 2.

Abstract

Spatial transcriptomics (ST) has demonstrated enormous potential for generating intricate molecular maps of cells within tissues. Here we present iStar, a method based on hierarchical image feature extraction that integrates ST data and high-resolution histology images to predict spatial gene expression with super-resolution. Our method enhances gene expression resolution to near-single-cell levels in ST and enables gene expression prediction in tissue sections where only histology images are available.

MeSH terms

  • Algorithms
  • Animals
  • Gene Expression Profiling* / methods
  • Humans
  • Image Processing, Computer-Assisted / methods
  • Single-Cell Analysis / methods
  • Transcriptome* / genetics