Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adaptive Spatial Transcriptomics Interpolation via Cross-modal Cross-slice Modeling

NingFeng Que, Xiaofei Wang, Jingjing Chen, Yixuan Jiang, Chao Li

TL;DR

The paper addresses the challenge of interpolating missing ST slices at arbitrary intermediate positions to enable 3D spatial transcriptomics with fewer experiments. It introduces C2-STi, a framework that combines cross-modal alignment between ST and H&E images, a pyramid gene co-expression graph, and distance-aware local structural modulation to model cross-slice deformations and gene co-expression. Extensive experiments on the OpenST HNSCC dataset show clear improvements over state-of-the-art methods for both single- and multi-slice interpolation, with ablations confirming the value of each module. The approach reduces cost and enables robust multi-slice ST reconstruction, and code is publicly available at the provided GitHub repository.

Abstract

Spatial transcriptomics (ST) is a promising technique that characterizes the spatial gene profiling patterns within the tissue context. Comprehensive ST analysis depends on consecutive slices for 3D spatial insights, whereas the missing intermediate tissue sections and high costs limit the practical feasibility of generating multi-slice ST. In this paper, we propose C2-STi, the first attempt for interpolating missing ST slices at arbitrary intermediate positions between adjacent ST slices. Despite intuitive, effective ST interpolation presents significant challenges, including 1) limited continuity across heterogeneous tissue sections, 2) complex intrinsic correlation across genes, and 3) intricate cellular structures and biological semantics within each tissue section. To mitigate these challenges, in C2-STi, we design 1) a distance-aware local structural modulation module to adaptively capture cross-slice deformations and enhance positional correlations between ST slices, 2) a pyramid gene co-expression correlation module to capture multi-scale biological associations among genes, and 3) a cross-modal alignment module that integrates the ST-paired hematoxylin and eosin (H&E)-stained images to filter and align the essential cellular features across ST and H\&E images. Extensive experiments on the public dataset demonstrate our superiority over state-of-the-art approaches on both single-slice and multi-slice ST interpolation. Codes are available at https://github.com/XiaofeiWang2018/C2-STi.

Adaptive Spatial Transcriptomics Interpolation via Cross-modal Cross-slice Modeling

TL;DR

The paper addresses the challenge of interpolating missing ST slices at arbitrary intermediate positions to enable 3D spatial transcriptomics with fewer experiments. It introduces C2-STi, a framework that combines cross-modal alignment between ST and H&E images, a pyramid gene co-expression graph, and distance-aware local structural modulation to model cross-slice deformations and gene co-expression. Extensive experiments on the OpenST HNSCC dataset show clear improvements over state-of-the-art methods for both single- and multi-slice interpolation, with ablations confirming the value of each module. The approach reduces cost and enables robust multi-slice ST reconstruction, and code is publicly available at the provided GitHub repository.

Abstract

Spatial transcriptomics (ST) is a promising technique that characterizes the spatial gene profiling patterns within the tissue context. Comprehensive ST analysis depends on consecutive slices for 3D spatial insights, whereas the missing intermediate tissue sections and high costs limit the practical feasibility of generating multi-slice ST. In this paper, we propose C2-STi, the first attempt for interpolating missing ST slices at arbitrary intermediate positions between adjacent ST slices. Despite intuitive, effective ST interpolation presents significant challenges, including 1) limited continuity across heterogeneous tissue sections, 2) complex intrinsic correlation across genes, and 3) intricate cellular structures and biological semantics within each tissue section. To mitigate these challenges, in C2-STi, we design 1) a distance-aware local structural modulation module to adaptively capture cross-slice deformations and enhance positional correlations between ST slices, 2) a pyramid gene co-expression correlation module to capture multi-scale biological associations among genes, and 3) a cross-modal alignment module that integrates the ST-paired hematoxylin and eosin (H&E)-stained images to filter and align the essential cellular features across ST and H\&E images. Extensive experiments on the public dataset demonstrate our superiority over state-of-the-art approaches on both single-slice and multi-slice ST interpolation. Codes are available at https://github.com/XiaofeiWang2018/C2-STi.
Paper Structure (10 sections, 5 equations, 2 figures, 2 tables)

This paper contains 10 sections, 5 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Cross-modal alignment between H&E and ST
  4. Pyramid gene co-expression correlation
  5. Distance-aware local structural modulation across ST slices
  6. Loss function
  7. Experiments & Results
  8. Performance evaluation
  9. Ablation Experiments
  10. Conclusion

Figures (2)

  • Figure 1: Framework of the C2-STi, including three modules of cross-modal alignment, pyramid gene co-expression correlation and distance-aware local structural modulation.
  • Figure 2: Visual comparisons for single slice interpolation result. Note that IGKC, MT-CO2, MT-CO3, and MT-ND2 denote different genes.