New deep learning framework integrates histology and genomics for cancer research

Researchers have developed JASPR, a self-supervised deep learning framework designed to integrate histology images (HE) and spatial transcriptomics (ST) data. This novel approach aims to capture universal spatial properties across both modalities while encoding modality-specific features. JASPR has demonstrated its effectiveness in improving the prediction of gene expression and providing prognostic value for breast cancer outcomes. AI

IMPACT This framework could enhance the accuracy of predicting gene expression and patient prognoses in cancer research.

RANK_REASON The cluster contains a research paper detailing a new deep learning framework for integrating medical imaging and genomic data. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• breast cancer
• Marija Pizurica
• ST

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →