Metraipolis › archive › dc_a6968910fbcb
Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images — arXiv:2609.36429
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36429
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:38:09.466Z
- SHA-256 of the archived text
391c78e679b6e6cd36e9760da47caf10d3f014404ce22076b87d6d93f8ac37f3- Stable URL of this page
https://metraipolis.com/documento/dc_a6968910fbcb
How to cite
Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images — arXiv:2609.36429 — arXiv (en), https://arxiv.org/abs/2609.36429 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6968910fbcb (Metraipolis archive dc_a6968910fbcb, sha256 391c78e679b6e6cd36e9760da47caf10d3f014404ce22076b87d6d93f8ac37f3)
BibTeX
@misc{dca6968910fbcb,
title = {Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images — arXiv:2609.36429},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36429},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6968910fbcb; sha256 391c78e679b6e6cd36e9760da47caf10d3f014404ce22076b87d6d93f8ac37f3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36429. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Predicting gene expression from H&E-stained histology images offers a scalable alternative to costly spatial transcriptomics, yet most existing methods operate at the spot level, where signals from multiple cells are aggregated and critical cellular heterogeneity is obscured. Extending this paradigm to single-cell resolution is non-trivial. Naively applying pathology foundation models faces a scale mismatch: their patch-level representations mix multiple cells, whereas per-cell cropping or resizing distorts morphology and removes local context. Conversely, segmentation-based models without strong pretrained visual encoders often lack the morphological representation capacity needed for accurate molecular prediction and inherit errors from imperfect cell boundary masks. Here, we present CELLO, an efficient end-to-end framework that performs a single pathology foundation model forward pass per image and uses grid sampling to extract location-specific features for all cells simultaneously. We further introduce a distance-decay cross-attention module that refines each cell representation using spatially biased local morphological context. Using 52 public Xenium-H&E pairs from HEST-1k that span 12 organs and approximately 10 million cells, CELLO improves the average predictive accuracy over the evaluated baselines while reducing the mean whole-slide inference time compared to DeepSpot2Cell, a 14.0x speed-up on average that excludes upstream cell segmentation. Our work establishes a scalable foundation for single-cell gene expression prediction from H&E images. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.36429 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T18:04:24.697Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).