Halo: a pretrained model for whole-cell segmentation from nuclei images in spatial transcriptomics.

Abstract

Spatial transcriptomics (ST) enables measurement of gene expression while preserving spatial organization within tissues. Accurate reconstruction of single-cell transcriptomes requires precise whole-cell segmentation, yet many ST experiments provide only nuclear staining images, making reliable inference of cell boundaries difficult. Here we introduce Halo, a pretrained segmentation model that reconstructs whole-cell boundaries by integrating nuclear morphology with the spatial distribution of RNA transcripts. Halo converts transcript coordinates into molecular density maps that are processed jointly with DAPI images using a Cellpose-SAM segmentation architecture. Halo is pretrained on multimodal Xenium data from 12 tissue types and can be directly applied to new datasets without additional training, providing a ready-to-use alternative to supervised approaches that require dataset-specific fitting. Across diverse tissues, Halo achieves substantially higher agreement with the 10$\times$ multimodal reference segmentation than existing methods, in terms of both cell boundaries and RNA-to-cell assignments, while requiring only DAPI staining and transcript spatial information. Improved segmentation leads to more reliable cell-type identification and more accurate estimation of cell morphological features. By providing a pretrained, generalizable model for whole-cell reconstruction, Halo enables scalable and reproducible cell segmentation for image-based ST.