Related Experiment Video
Updated: Jan 18, 2026
06:27
Automated Analysis of C. elegans Fluorescence Images using SegElegans
Published on: October 10, 2025
595
SegJointGene: joint cell segmentation and spatial gene prioritization by information entropy guided convolutional
Biorxiv : the Preprint Server for Biology
|January 16, 2026
Summary
SegJointGene, a deep learning framework, improves cell segmentation in complex tissues by integrating imaging with gene expression data. This method accurately maps molecular signals to cell boundaries, advancing spatial biology research.
Area of Science:
- Spatial biology
- Computational biology
- Genomics
Background:
- Accurate cell segmentation is crucial for spatial sequencing technologies to study molecular organization in tissues.
- Segmentation solely on nuclear staining is insufficient in dense tissues, necessitating integration of molecular data like gene expression.
- Integrating molecular information for segmentation is computationally challenging.
Purpose of the Study:
- To develop a deep learning framework, SegJointGene, for joint cell segmentation and spatial gene prioritization.
- To improve the accuracy of cell boundary detection by integrating nuclei images with spatial gene or protein expression data.
- To identify genes critical for cell-type-specific segmentation in complex tissues.
Main Methods:
- Developed SegJointGene, a deep learning framework using an information-entropy-guided convolutional neural network.
- Integrated nuclei-based images with spatial gene/protein expression data.
- Employed a computational information discarding score for gene prioritization and iterative refinement of segmentation and gene prioritization.
Main Results:
- SegJointGene achieved 5-20% higher accuracy in assigning molecular signals to cell boundaries compared to existing methods across diverse spatial datasets (mouse brain, human tonsil).
- Demonstrated robust performance across varying gene numbers and imaging resolutions.
- Prioritized genes were enriched in structural, developmental, and synaptic signaling pathways relevant to tissue organization.
Conclusions:
- SegJointGene effectively integrates imaging and molecular data for accurate cell segmentation and gene prioritization in spatial biology.
- The framework enhances understanding of spatial tissue organization by identifying key genes driving cell morphology and boundaries.
- Offers a computationally efficient and robust solution for complex spatial omics data analysis.
Related Concept Videos
01:58Cell Specific Gene Expression
5.4K
5.4K
01:58Cell Specific Gene Expression
16.3K
Multicellular organisms contain a variety of structurally and functionally distinct cell types, but the DNA in all the cells originated from the same parent cells. The differences in the cells can be attributed to the differential gene expression. Liver cells, whose functions include detoxification of blood, production of bile to metabolize fats, and synthesis of proteins essential for metabolism, must express a specific set of genes to perform their functions. Gene expression also varies with...
16.3K