Metraipolis › archive › dc_0bfebf0fb2a3

Is H&E Image-to-Spatial Transcriptomics Simpler Than It Looks? — arXiv:2609.32857

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32857
License (as archived)
CC0-1.0
Archived
2026-10-07T22:39:50.270Z
SHA-256 of the archived text
be797e68798dd13e547336bd280592a9ec19bf4f32631001c993c1965dcb5062
Stable URL of this page
https://metraipolis.com/documento/dc_0bfebf0fb2a3

How to cite

Is H&E Image-to-Spatial Transcriptomics Simpler Than It Looks? — arXiv:2609.32857 — arXiv (en), https://arxiv.org/abs/2609.32857 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0bfebf0fb2a3 (Metraipolis archive dc_0bfebf0fb2a3, sha256 be797e68798dd13e547336bd280592a9ec19bf4f32631001c993c1965dcb5062)
BibTeX
@misc{dc0bfebf0fb2a3,
  title = {Is H&E Image-to-Spatial Transcriptomics Simpler Than It Looks? — arXiv:2609.32857},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32857},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0bfebf0fb2a3; sha256 be797e68798dd13e547336bd280592a9ec19bf4f32631001c993c1965dcb5062},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32857. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Predicting spatial gene expression from routine H&E histology offers a scalable route toward spatial molecular profiling. Recent work has pursued increasingly sophisticated architectures to capture spatial context and richer expression structure. At the same time, simple estimators have shown strong performance in several studies, but what they already solve and where additional complexity is needed remain unclear. We study this behavior through the structure of prediction error under the mean-squared error (MSE) objective. Differences in average expression across genes can account for a substantial part of aggregate prediction performance, while a key unresolved error lies in recovering variation within each slide. Decomposing MSE into slide-level and within-slide components, we find that the within-slide component has lower residual-normalized parameter sensitivity in controlled neural experiments. This motivates Component-Guided Loss (CGL), which increases supervision of the within-slide component. CGL-Linear is a closed-form affine instantiation that achieves overall state-of-the-art performance across HEST-1k cohorts and gene-panel sizes. The same within-slide supervision improves existing neural models. These results suggest that substantial gains can come from aligning the training objective with prediction-error structure rather than increasing model complexity.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.32857 — 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 2026-10-07T22:14:28.665Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).