Guardado en:
Detalles Bibliográficos
Autores principales: Hizmi, Arbel, Bakulin, Artemii, Bagon, Shai, Yosef, Nir
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.09076
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918438420611072
author Hizmi, Arbel
Bakulin, Artemii
Bagon, Shai
Yosef, Nir
author_facet Hizmi, Arbel
Bakulin, Artemii
Bagon, Shai
Yosef, Nir
contents Spatial transcriptomics provides a molecularly rich description of tissue organization, enabling unsupervised discovery of tissue niches -- spatially coherent regions of distinct cell-type composition and function that are relevant to both biological research and clinical interpretation. However, spatial transcriptomics remains costly and scarce, while H&E histology is abundant but carries a less granular signal. We propose to leverage paired spatial transcriptomics and H&E data to transfer transcriptomics-derived niche structure to a histology-only model via cross-modal distillation. Across multiple tissue types and disease contexts, the distilled model achieves substantially higher agreement with transcriptomics-derived niche structure than unsupervised morphology-based baselines trained on identical image features, and recovers biologically meaningful neighborhood composition as confirmed by cell-type analysis. The resulting framework leverages paired spatial transcriptomic and H&E data during training, and can then be applied to held-out tissue regions using histology alone, without any transcriptomic input at inference time.
format Preprint
id arxiv_https___arxiv_org_abs_2604_09076
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cross-Modal Knowledge Distillation from Spatial Transcriptomics to Histology
Hizmi, Arbel
Bakulin, Artemii
Bagon, Shai
Yosef, Nir
Computer Vision and Pattern Recognition
Spatial transcriptomics provides a molecularly rich description of tissue organization, enabling unsupervised discovery of tissue niches -- spatially coherent regions of distinct cell-type composition and function that are relevant to both biological research and clinical interpretation. However, spatial transcriptomics remains costly and scarce, while H&E histology is abundant but carries a less granular signal. We propose to leverage paired spatial transcriptomics and H&E data to transfer transcriptomics-derived niche structure to a histology-only model via cross-modal distillation. Across multiple tissue types and disease contexts, the distilled model achieves substantially higher agreement with transcriptomics-derived niche structure than unsupervised morphology-based baselines trained on identical image features, and recovers biologically meaningful neighborhood composition as confirmed by cell-type analysis. The resulting framework leverages paired spatial transcriptomic and H&E data during training, and can then be applied to held-out tissue regions using histology alone, without any transcriptomic input at inference time.
title Cross-Modal Knowledge Distillation from Spatial Transcriptomics to Histology
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.09076