From Gene Expression to Tissue Morphology: Can Generative Models Uncover the Link?

Frederieke Lohmann, Alberto Valdeolivas, Jelica Vasiljevic
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 316:301-317, 2026.

Abstract

Spatial Transcriptomics technologies enable capturing gene expression within the native tissue context. Platforms such as 10x Visium and Visium HD integrate gene expression with histological imaging, providing a multi-dimensional view of tissue organisation. Motivated by the success of generative models in computer vision and natural language processing, we investigate the largely unexplored task of synthesising histological images directly from gene expression profiles. Leveraging recent advancements in Spatial Transcriptomics, particularly the 10X Visium HD platform, we introduce the first two-stage conditional generative framework to infer tissue morphology from near-whole transcriptome profiles. Competitive FID scores and a study involving multiple pathologists confirm that the synthesised images are plausible and that our framework generalises well to unseen standard Visium samples. Furthermore, model interpretation reveals connections between structurally relevant gene sets and specific morphological patterns, opening new avenues for studying the relationship between gene expression and tissue morphology.

Cite this Paper

BibTeX
@InProceedings{pmlr-v316-lohmann26a, title = {From Gene Expression to Tissue Morphology: Can Generative Models Uncover the Link?}, author = {Lohmann, Frederieke and Valdeolivas, Alberto and Vasiljevic, Jelica}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {301--317}, year = {2026}, editor = {Studer, Linda and Ciompi, Francesco and Khalili, Nadieh and Faryna, Khrystyna and Faryna, Khrystyna and Yeong, Joe and Lau, Mai Chan and Chen, Hao and Liu, Ziyi and Brattoli, Biagio}, volume = {316}, series = {Proceedings of Machine Learning Research}, month = {27 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v316/main/assets/lohmann26a/lohmann26a.pdf}, url = {https://proceedings.mlr.press/v316/lohmann26a.html}, abstract = {Spatial Transcriptomics technologies enable capturing gene expression within the native tissue context. Platforms such as 10x Visium and Visium HD integrate gene expression with histological imaging, providing a multi-dimensional view of tissue organisation. Motivated by the success of generative models in computer vision and natural language processing, we investigate the largely unexplored task of synthesising histological images directly from gene expression profiles. Leveraging recent advancements in Spatial Transcriptomics, particularly the 10X Visium HD platform, we introduce the first two-stage conditional generative framework to infer tissue morphology from near-whole transcriptome profiles. Competitive FID scores and a study involving multiple pathologists confirm that the synthesised images are plausible and that our framework generalises well to unseen standard Visium samples. Furthermore, model interpretation reveals connections between structurally relevant gene sets and specific morphological patterns, opening new avenues for studying the relationship between gene expression and tissue morphology.} }
Endnote
%0 Conference Paper %T From Gene Expression to Tissue Morphology: Can Generative Models Uncover the Link? %A Frederieke Lohmann %A Alberto Valdeolivas %A Jelica Vasiljevic %B Proceedings of the MICCAI Workshop on Computational Pathology %C Proceedings of Machine Learning Research %D 2026 %E Linda Studer %E Francesco Ciompi %E Nadieh Khalili %E Khrystyna Faryna %E Khrystyna Faryna %E Joe Yeong %E Mai Chan Lau %E Hao Chen %E Ziyi Liu %E Biagio Brattoli %F pmlr-v316-lohmann26a %I PMLR %P 301--317 %U https://proceedings.mlr.press/v316/lohmann26a.html %V 316 %X Spatial Transcriptomics technologies enable capturing gene expression within the native tissue context. Platforms such as 10x Visium and Visium HD integrate gene expression with histological imaging, providing a multi-dimensional view of tissue organisation. Motivated by the success of generative models in computer vision and natural language processing, we investigate the largely unexplored task of synthesising histological images directly from gene expression profiles. Leveraging recent advancements in Spatial Transcriptomics, particularly the 10X Visium HD platform, we introduce the first two-stage conditional generative framework to infer tissue morphology from near-whole transcriptome profiles. Competitive FID scores and a study involving multiple pathologists confirm that the synthesised images are plausible and that our framework generalises well to unseen standard Visium samples. Furthermore, model interpretation reveals connections between structurally relevant gene sets and specific morphological patterns, opening new avenues for studying the relationship between gene expression and tissue morphology.
APA
Lohmann, F., Valdeolivas, A. & Vasiljevic, J.. (2026). From Gene Expression to Tissue Morphology: Can Generative Models Uncover the Link?. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 316:301-317 Available from https://proceedings.mlr.press/v316/lohmann26a.html.

Related Material