INST-Align: Implicit Neural Alignment for Spatial Transcriptomics via Canonical Expression Fields

TL;DR

INST-Align is an unsupervised neural framework that jointly aligns and reconstructs spatial transcriptomics data, effectively handling large deformations and batch effects to produce accurate spatial embeddings and 3D reconstructions.

Contribution

It introduces a novel joint alignment and reconstruction method using implicit neural representations and a two-phase training strategy for spatial transcriptomics.

Findings

Achieves state-of-the-art accuracy metrics across nine datasets.

Reduces Chamfer distance by up to 94.9% on large-deformation sections.

Produces biologically meaningful spatial embeddings and coherent 3D tissue reconstructions.

Abstract

Spatial transcriptomics (ST) measures mRNA expression while preserving spatial organization, but multi-slice analysis faces two coupled difficulties: large non-rigid deformations across slices and inter-slice batch effects when alignment and integration are treated independently. We present INST-Align, an unsupervised pairwise framework that couples a coordinate-based deformation network with a shared Canonical Expression Field, an implicit neural representation mapping spatial coordinates to expression embeddings, for joint alignment and reconstruction. A two-phase training strategy first establishes a stable canonical embedding space and then jointly optimizes deformation and spatial-feature matching, enabling mutually constrained alignment and representation learning. Cross-slice parameter sharing of the canonical field regularizes ambiguous correspondences and absorbs batch variation. Across nine datasets, INST-Align achieves state-of-the-art mean OT Accuracy (0.702), NN Accuracy (0.719), and Chamfer distance, with Chamfer reductions of up to 94.9\% on large-deformation sections relative to the strongest baseline. The framework also yields biologically meaningful spatial embeddings and coherent 3D tissue reconstruction. The code will be released after review phase.