Guardado en:
| Autores principales: | , , , |
|---|---|
| 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 |