Learned morphological features guide cell type assignment of deconvolved spatial transcriptomics

Eduard Chelebian, Christophe Avenel, Julio Leon, Chung-Chau Hon, Carolina Wahlby
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:220-233, 2024.

Abstract

Spatial transcriptomics enables to study the relationship between gene expression and tissue organization. Despite many recent advancements, existing sequencing-based methods have a spatial resolution that limits identification of individual cells. To address this, several cell type deconvolution methods have been proposed to integrate spatial gene expression with single-cell and single-nucleus RNA sequencing, producing per spot cell typing. However, these methods often overlook the contribution of morphology, which means cell identities are randomly assigned to the nuclei within a spot. In this paper, we introduce MHAST, a morphology-guided hierarchical permutation-based framework which efficiently reassigns cell types in spatial transcriptomics. We validate our method on simulated data, synthetic data, and a use case on the broadly used Tangram cell type deconvolution method with Visium data. We show that deconvolution-based cell typing using morphological tissue features from self-supervised deep learning lead to a more accurate annotation of the cells.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-chelebian24a, title = {Learned morphological features guide cell type assignment of deconvolved spatial transcriptomics}, author = {Chelebian, Eduard and Avenel, Christophe and Leon, Julio and Hon, Chung-Chau and Wahlby, Carolina}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {220--233}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/chelebian24a/chelebian24a.pdf}, url = {https://proceedings.mlr.press/v250/chelebian24a.html}, abstract = {Spatial transcriptomics enables to study the relationship between gene expression and tissue organization. Despite many recent advancements, existing sequencing-based methods have a spatial resolution that limits identification of individual cells. To address this, several cell type deconvolution methods have been proposed to integrate spatial gene expression with single-cell and single-nucleus RNA sequencing, producing per spot cell typing. However, these methods often overlook the contribution of morphology, which means cell identities are randomly assigned to the nuclei within a spot. In this paper, we introduce MHAST, a morphology-guided hierarchical permutation-based framework which efficiently reassigns cell types in spatial transcriptomics. We validate our method on simulated data, synthetic data, and a use case on the broadly used Tangram cell type deconvolution method with Visium data. We show that deconvolution-based cell typing using morphological tissue features from self-supervised deep learning lead to a more accurate annotation of the cells.} }
Endnote
%0 Conference Paper %T Learned morphological features guide cell type assignment of deconvolved spatial transcriptomics %A Eduard Chelebian %A Christophe Avenel %A Julio Leon %A Chung-Chau Hon %A Carolina Wahlby %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-chelebian24a %I PMLR %P 220--233 %U https://proceedings.mlr.press/v250/chelebian24a.html %V 250 %X Spatial transcriptomics enables to study the relationship between gene expression and tissue organization. Despite many recent advancements, existing sequencing-based methods have a spatial resolution that limits identification of individual cells. To address this, several cell type deconvolution methods have been proposed to integrate spatial gene expression with single-cell and single-nucleus RNA sequencing, producing per spot cell typing. However, these methods often overlook the contribution of morphology, which means cell identities are randomly assigned to the nuclei within a spot. In this paper, we introduce MHAST, a morphology-guided hierarchical permutation-based framework which efficiently reassigns cell types in spatial transcriptomics. We validate our method on simulated data, synthetic data, and a use case on the broadly used Tangram cell type deconvolution method with Visium data. We show that deconvolution-based cell typing using morphological tissue features from self-supervised deep learning lead to a more accurate annotation of the cells.
APA
Chelebian, E., Avenel, C., Leon, J., Hon, C. & Wahlby, C.. (2024). Learned morphological features guide cell type assignment of deconvolved spatial transcriptomics. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:220-233 Available from https://proceedings.mlr.press/v250/chelebian24a.html.

Related Material