Related Experiment Video
Updated: May 9, 2026
07:46
Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments
Published on: April 30, 2021
4.6K
ROICellTrack: a deep learning framework for integrating cellular imaging modalities in subcellular spatial
Xiaofei Song1, Xiaoqing Yu1, Carlos M Moran-Segura2
1Department of Biostatistics and Bioinformatics, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL 33612, United States.
Bioinformatics (Oxford, England)
|April 8, 2025
Summary
ROICellTrack integrates imaging with spatial transcriptomics to reveal distinct cancer-immune cell mixtures. This deep learning framework enhances understanding of tumor heterogeneity for personalized therapies.
Area of Science:
- Oncology
- Bioinformatics
- Genomics
Background:
- Spatial transcriptomic (ST) technologies are vital for studying tumor microenvironments in cancer progression and treatment response.
- Current ST studies often underutilize spatial imaging data, limiting downstream analysis and interpretation.
Purpose of the Study:
- To develop a novel deep learning framework, ROICellTrack, for enhanced integration of cellular imaging and spatial transcriptomic data.
- To improve the analysis of spatial omics data by leveraging morphological and transcriptomic signatures.
Main Methods:
- Developed ROICellTrack, a deep learning-based framework for integrating imaging with ST profiling.
- Analyzed 56 regions of interest (ROIs) from urothelial carcinoma samples.
Main Results:
- ROICellTrack identified distinct cancer-immune cell mixtures with specific transcriptomic and morphological signatures.
- Revealed receptor-ligand interactions associated with tumor content and immune infiltration.
- Demonstrated the value of integrating imaging and transcriptomics for spatial omics analysis.
Conclusions:
- Integrating imaging with transcriptomics significantly enhances the understanding of tumor heterogeneity.
- ROICellTrack provides a powerful tool for analyzing spatial omics data, aiding in the development of personalized and targeted cancer therapies.
