Saved in:
Bibliographic Details
Main Authors: Chelebian, Eduard, Dasgupta, Pratiti, Samadi, Zainalabedin, Wählby, Carolina, Askary, Amjad
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.13974
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913699442196480
author Chelebian, Eduard
Dasgupta, Pratiti
Samadi, Zainalabedin
Wählby, Carolina
Askary, Amjad
author_facet Chelebian, Eduard
Dasgupta, Pratiti
Samadi, Zainalabedin
Wählby, Carolina
Askary, Amjad
contents This study introduces SEFI (SEgmentation-Free Integration), a novel method for integrating morphological features of cell nuclei with spatial transcriptomics data. Cell segmentation poses a significant challenge in the analysis of spatial transcriptomics data, as tissue-specific structural complexities and densely packed cells in certain regions make it difficult to develop a universal approach. SEFI addresses this by utilizing self-supervised learning to extract morphological features from fluorescent nuclear staining images, enhancing the clustering of gene expression data without requiring segmentation. We demonstrate SEFI on spatially resolved gene expression profiles of the developing retina, acquired using multiplexed single molecule Fluorescence In Situ Hybridization (smFISH). SEFI is publicly available at https://github.com/eduardchelebian/sefi.
format Preprint
id arxiv_https___arxiv_org_abs_2502_13974
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Segmentation-free integration of nuclei morphology and spatial transcriptomics for retinal images
Chelebian, Eduard
Dasgupta, Pratiti
Samadi, Zainalabedin
Wählby, Carolina
Askary, Amjad
Image and Video Processing
Computer Vision and Pattern Recognition
This study introduces SEFI (SEgmentation-Free Integration), a novel method for integrating morphological features of cell nuclei with spatial transcriptomics data. Cell segmentation poses a significant challenge in the analysis of spatial transcriptomics data, as tissue-specific structural complexities and densely packed cells in certain regions make it difficult to develop a universal approach. SEFI addresses this by utilizing self-supervised learning to extract morphological features from fluorescent nuclear staining images, enhancing the clustering of gene expression data without requiring segmentation. We demonstrate SEFI on spatially resolved gene expression profiles of the developing retina, acquired using multiplexed single molecule Fluorescence In Situ Hybridization (smFISH). SEFI is publicly available at https://github.com/eduardchelebian/sefi.
title Segmentation-free integration of nuclei morphology and spatial transcriptomics for retinal images
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.13974