# Spatial Transcriptomics as Images for Large-Scale Pretraining

arXiv: https://arxiv.org/abs/2603.13432 · HTML: https://mlsanity.com/paper/2603.13432/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 33 references that are in the map.
- First posted on arXiv 13 Mar 2026.

## Builds on (most cited first, 5 of 5)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Accurate Spatial Gene Expression Prediction by integrating Multi-resolution features](https://mlsanity.com/paper/2403.07592/) (2024)
- [ST-Align: A Multimodal Foundation Model for Image-Gene Alignment in Spatial Transcriptomics](https://mlsanity.com/paper/2411.16793/) (2024)
- [SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics](https://mlsanity.com/paper/2507.11588/) (2025)

## Abstract (arXiv)

Spatial Transcriptomics (ST) profiles thousands of gene expression values at discrete spots with precise coordinates on tissue sections, preserving spatial context essential for clinical and pathological studies. With rising sequencing throughput and advancing platforms, the expanding data volumes motivate large-scale ST pretraining. However, the fundamental unit for pretraining, i.e., what constitutes a single training sample, remains ill-posed. Existing choices fall into two camps: (1) treating each spot as an independent sample, which discards spatial dependencies and collapses ST into single-cell transcriptomics; and (2) treating an entire slide as a single sample, which produces prohibitively large inputs and drastically fewer training examples, undermining effective pretraining. To address this gap, we propose treating spatial transcriptomics as croppable images. Specifically, we define a multi-channel image representation with fixed spatial size by cropping patches from raw slides, thereby preserving spatial context while substantially increasing the number of training samples. Along the channel dimension, we define gene subset selection rules to control input dimensionality and improve pretraining stability. Extensive experiments show that the proposed image-like dataset construction for ST pretraining consistently improves downstream performance, outperforming conventional pretraining schemes. Ablation studies verify that both spatial patching and channel design are necessary, establishing a unified, practical paradigm for organizing ST data and enabling large-scale pretraining.