Related Experiment Video
Updated: Jul 24, 2025
09:19
Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection
Published on: July 6, 2022
5.0K
SCS: cell segmentation for high-resolution spatial transcriptomics
Hao Chen1, Dongshunyi Li1, Ziv Bar-Joseph1,2
1Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
Biorxiv : the Preprint Server for Biology
|July 3, 2023
Summary
Spatial transcriptomics methods now offer sub-cellular resolution. Our new tool, SCS, improves cell segmentation accuracy by combining imaging and sequencing data for better RNA localization insights.
Area of Science:
- Molecular Biology
- Genomics
- Bioinformatics
Background:
- Spatial transcriptomics enables understanding tissue organization and cell interactions.
- Current platforms often lack cellular resolution, limiting insights.
- Emerging sub-cellular resolution technologies face challenges in cell segmentation and spot assignment.
Approach:
- We introduce SCS, a novel method combining imaging and sequencing data for enhanced cell segmentation.
- SCS utilizes a transformer neural network to learn spot positions relative to cell centers.
- The approach was validated on two sub-cellular spatial transcriptomics technologies.
Key Points:
- SCS significantly outperforms traditional image-based segmentation methods.
- Achieved higher accuracy, identified more cells, and provided more realistic cell size estimations.
- Enables sub-cellular RNA localization analysis, supporting segmentation accuracy.
Conclusions:
- SCS advances cell segmentation for sub-cellular spatial transcriptomics.
- Improves the analysis of RNA localization within cells.
- Facilitates deeper understanding of cellular architecture and function.
