SpaCut: Transcript-Aware Morphology Fusion for Robust Cell Segmentation in Subcellular Spatial Transcriptomics.
- 1School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China.
- 2School of Health and Nursing, Yunnan Open University, Kunming, Yunnan, China.
Abstract
Subcellular Spatial Transcriptomics (SST) offers unprecedented opportunities to decipher tissue architecture at subcellular resolution. Consequently, accurate cell segmentation is a fundamental prerequisite for analyzing SST data, as precise transcript assignment is essential for downstream single-cell interpretation. Existing methods often overlook the spatial organization of transcripts, rely on simplified geometric priors, or struggle to coordinate transcript-derived features with morphology-derived spatial guidance. This limitation restricts their adaptability to irregular cell shapes, often leading to transcript misassignment. To address this, we propose SpaCut, a unified deep learning framework designed to effectively integrate transcriptomic feature learning with dynamic morphological guidance. SpaCut comprises a Gene-Wise Attention (GWA) module and a Nuclei-Guided Attentive Fusion (NGAF) module. GWA encodes the high-dimensional transcript map and aggregates features across multiple depths. NGAF uses the encoded transcript features to modulate distance-based nuclear softmasks and refine nucleus-anchored cell boundaries through progressive training. Extensive evaluations across seven datasets from diverse platforms (including Xenium, CosMx, MERSCOPE, and Stereo-seq) demonstrate that SpaCut significantly outperforms state-of-the-art methods in both segmentation accuracy and consistency with single-cell reference data. The source code is available at https://github.com/wenwenmin/SpaCut.
Related
- STRAND: a comprehensive subcellular-resolved spatial transcriptome RNA architecture and navigation database
- High‐resolution spatial transcriptomic atlas of mouse soleus muscle: Unveiling single cell and subcellular heterogeneity in health and denervation
- A morphology-driven workflow to decipher 3D electron microscopy segmentation in diatoms
- Physics and Morphology Constrained Quantitative Susceptibility Based Segmentation of Cerebral Veins
- Comments on "SpatialDG: a novel spatial domain identification method for spatially resolved transcriptomics data based on dual-graph neural network".
BibTeX
@article{li2026spacut,
title = {{SpaCut: Transcript-Aware Morphology Fusion for Robust Cell Segmentation in Subcellular Spatial Transcriptomics.}},
author = {Yongheng Li and Fangfang Zhu and Wenwen Min},
journal = {Advanced science (Weinheim, Baden-Wurttemberg, Germany)},
year = {2026},
month = oct,
doi = {10.1002/advs.78423},
url = {https://europepmc.org/article/MED/42958707},
note = {CC BY},
}
RIS
TY - JOUR
TI - SpaCut: Transcript-Aware Morphology Fusion for Robust Cell Segmentation in Subcellular Spatial Transcriptomics.
AU - Yongheng Li
AU - Fangfang Zhu
AU - Wenwen Min
PY - 2026
DA - 2026/10/29
JO - Advanced science (Weinheim, Baden-Wurttemberg, Germany)
DO - 10.1002/advs.78423
UR - https://europepmc.org/article/MED/42958707
AB - Subcellular Spatial Transcriptomics (SST) offers unprecedented opportunities to decipher tissue architecture at subcellular resolution. Consequently, accurate cell segmentation is a fundamental prerequisite for analyzing SST data, as precise transcript assignment is essential for downstream single-cell interpretation. Existing methods often overlook the spatial organization of transcripts, rely on simplified geometric priors, or struggle to coordinate transcript-derived features with morphology-derived spatial guidance. This limitation restricts their adaptability to irregular cell shapes, often leading to transcript misassignment. To address this, we propose SpaCut, a unified deep learning framework designed to effectively integrate transcriptomic feature learning with dynamic morphological guidance. SpaCut comprises a Gene-Wise Attention (GWA) module and a Nuclei-Guided Attentive Fusion (NGAF) module. GWA encodes the high-dimensional transcript map and aggregates features across multiple depths. NGAF uses the encoded transcript features to modulate distance-based nuclear softmasks and refine nucleus-anchored cell boundaries through progressive training. Extensive evaluations across seven datasets from diverse platforms (including Xenium, CosMx, MERSCOPE, and Stereo-seq) demonstrate that SpaCut significantly outperforms state-of-the-art methods in both segmentation accuracy and consistency with single-cell reference data. The source code is available at https://github.com/wenwenmin/SpaCut.
SN - 2198-3844
ER -