Yang, Y.; Luo, Y.; Zhang, K.; Bu, Y.; Xia, Z.; Peng, H.; Yan, R.; Liu, Q.; Chen, Y.; Shen, L.; Chen, E.

Capturing the three-dimensional (3D) organization of cells is essential for deciphering complex biological processes, yet comprehensive 3D spatial omics is severely hindered by the destructive nature of physical sectioning and the depth limitations of intact tissue imaging. Current computational methods rely on 2.5D stacking of discrete slices, which inherently disrupts tissue topology and fails to resolve continuous depth-dependent molecular gradients. To bridge this gap, we introduce DeepSpatial, an Optimal Transport flow matching framework that models tissue evolution as a continuous dynamic vector field. By solving the underlying probability flow ODEs, DeepSpatial enables the direct extraction of uninterrupted, infinitely resolvable tissue states at arbitrary spatial depths. Using Deep STAR/RIBOmap 3D technologies, we demonstrate that DeepSpatial achieves improved 3D reconstruction fidelity relative to 2.5D approaches, yielding structures that more closely recapitulate native tissue microenvironments in real-world datasets. Across diverse spatial omics modalities, including spatial proteomics using imaging mass cytometry in human breast cancer and spatial transcriptomics using openST in head and neck squamous cell carcinoma metastatic lymph nodes, DeepSpatial produces biologically interpretable and high-fidelity reconstructions across datasets. We evaluated the scalability and robustness of DeepSpatial on a large-scale mouse brain dataset, reconstructing a continuous 3D cellular atlas comprising 39 million cells within 41.6 hours. Systematic downstream characterization validated its ability to recapitulate consistent spatial architectures, cell-type distributions, transcriptomic patterns, and microenvironmental structures across brain regions. Collectively, these results demonstrate DeepSpatial as a generalizable and efficient solution for true 3D spatial reconstruction across scales and modalities.