# Cross-Modal Knowledge Distillation from Spatial Transcriptomics to Histology

Source: [Cross-Modal Knowledge Distillation from Spatial Transcriptomics to Histology](<https://www.sota2.com/research/paper/69dc78667d0172140ec78953>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-14T05:00:04.234Z

Authors: Arbel Hizmi, Artemii Bakulin, Shai Bagon, Nir Yosef

Published: 2026-04-10T07:59:50.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Niche Assignment on 10x Genomics Xenium 16 datasets (test)](<https://www.sota2.com/research/sota/niche-assignment-on-10x-genomics-xenium-16-datasets-test.md>): Niche Assignment; 10x Genomics Xenium 16 datasets (test); ARI: 0.615.

- [Pathology label prediction on Xenium human ovarian cancer dataset](<https://www.sota2.com/research/sota/pathology-label-prediction-on-xenium-human-ovarian-cancer-dataset.md>): Pathology label prediction; Xenium human ovarian cancer dataset; Macro-F1: 54.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.09076>)

[PDF](<https://arxiv.org/pdf/2604.09076.pdf>)
