[2603.13432] Spatial Transcriptomics as Images for Large-Scale Pretraining

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.13432 (cs) [Submitted on 13 Mar 2026 (v1), last revised 23 Mar 2026 (this version, v3)] Title:Spatial Transcriptomics as Images for Large-Scale Pretraining Authors:Yishun Zhu, Jiaxin Qi, Jian Wang, Yuhua Zheng, Jianqiang Huang View a PDF of the paper titled Spatial Transcriptomics as Images for Large-Scale Pretraining, by Yishun Zhu and 4 other authors View PDF HTML (experimental) Abstract: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 con...