cs.CVNov 18, 2025

3D-Guided Scalable Flow Matching for Generating Volumetric Tissue Spatial Transcriptomics from Serial Histology

Authors: Mohammad Vali Sanian, Arshia Hemmat, Amirhossein Vahidi, Jonas Maaskola, Jimmy Tsz Hang Lee, Martin Prete, Stanislaw Makarchuk, Yeliz Demirci, 

Organizations: Computer Science Department, University of Helsinki · Institute for Molecular Medicine Finland, University of Helsinki · Wellcome Sanger Institute · Computer Science Department, University of Oxford · 

Abstract

A 3D transcriptomic profile of a tissue can give a holistic view of its organization in health and disease, but spatial transcriptomics (ST) is costly, so usually only some serial sections are profiled, while H&E is available for all. Most methods that infer ST from histology treat each section independently and ignore 3D structure, while existing 3D-aware approaches are not generative and do not scale well. We present Holographic Tissue Expression Inpainting and Analysis (HoloTea), a 3D-aware flow-matching framework that imputes spot-level gene expression on an unprofiled section from its H&E and the measured expression of adjacent profiled sections. Our key idea is to take the measured expression at the same registered position on neighboring sections and feed this cross-section context to the flow model through a lightweight ControlNet, so that predictions follow anatomical continuity along z. To capture the discrete, zero-inflated nature of counts, the flow starts from a learned zero-inflated negative binomial (ZINB) prior that, on an unprofiled section, is predicted from the measured expression of the nearest profiled section. A global attention block with a small set of inducing tokens adds whole-slide context at a cost linear in the number of spots, so training and inference scale to large 3D ST datasets. Across three ST datasets spanning different tissue types and resolutions, HoloTea consistently improves 3D expression accuracy and generalization compared to 2D and 3D baselines. We envision HoloTea advancing the creation of accurate 3D virtual tissues, ultimately accelerating biomarker discovery and deepening our understanding of disease. Code is available at https://github.com/Lotfollahi-lab/HoloTea.

Figures & tables

Appendix figures & tables21 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. HoloGene: Learning to Lift Sliced Spatial Transcriptomics to Holistic 3D Gene Fields

    Nov 16, 2026Yumin Zheng, Qingtian Zhu, Ziyan Zhu +3Spatial Gene Expression PredictionSpatial Transcriptomics

  2. Continuous 3D Spatial Transcriptomics Reconstruction via Histology-Informed Implicit Neural Representations

    Nov 10, 2026Kaito Shiku, Ryoma Bise, Ahtisham Fazeel Abbasi +4Spatial TranscriptomicsSpatial Gene Expression Prediction

  3. DriftST: One-Step Generative Inference of Spatial Transcriptomics from H&E Histology

    Jul 6, 2026Yuhang Yang, Yonggan Bu, Shengyuan Zhou +2Computational PathologySpatial Transcriptomics