Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Spatial Analysis for AI-segmented Histopathology Images: Methods and Implementation

Yoolkyu Park, Fangjiang Wu, Xin Feng, Shengjie Yang, Elizabeth H. Wang, Bo Yao, Chul Moon, Guanghua Xiao, Qiwei Li

TL;DR

SASHIMI provides an accessible, reproducible platform for single-cell-level spatial profiling of tumor tissue, enabling interactive visualization and standardized feature extraction without requiring programming expertise.

Abstract

Quantitative characterization of cellular spatial organization is critical for understanding tumor progression and immune response. Recent advances in artificial intelligence (AI) enable large-scale segmentation and classification of nuclei from digitized histopathology slides, producing massive point pattern and marked point pattern data. However, accessible and standardized tools for downstream spatial statistical analysis remain limited. We present SASHIMI (Spatial Analysis for Segmented Histopathology Images using Machine Intelligence), a browser-based platform for real-time spatial analysis of AI-segmented histopathology images. Rather than proposing new spatial methods, SASHIMI systematically organizes and operationalizes 27 widely used spatial summary statistics, areal indices, and topological features within a unified computational framework. The platform computes mathematically grounded descriptors including K-, L-, G-, F-, and J-functions, pair correlation and mark connection functions, spatial autocorrelation measures, similarity indices, and persistent homology-based topological summaries. Outputs include both functional curves and scalar feature tables suitable for downstream statistical modeling. We illustrate the framework using two cancer cohorts: oral potentially malignant disorders and non-small-cell lung cancer. Across datasets, cross-type spatial interactions and topological descriptors show associations with patient survival, demonstrating that complementary spatial features capture distinct aspects of tumor microenvironment architecture. SASHIMI provides an accessible, reproducible platform for single-cell-level spatial profiling of tumor tissue, enabling interactive visualization and standardized feature extraction without requiring programming expertise.

Spatial Analysis for AI-segmented Histopathology Images: Methods and Implementation

TL;DR

SASHIMI provides an accessible, reproducible platform for single-cell-level spatial profiling of tumor tissue, enabling interactive visualization and standardized feature extraction without requiring programming expertise.

Abstract

Quantitative characterization of cellular spatial organization is critical for understanding tumor progression and immune response. Recent advances in artificial intelligence (AI) enable large-scale segmentation and classification of nuclei from digitized histopathology slides, producing massive point pattern and marked point pattern data. However, accessible and standardized tools for downstream spatial statistical analysis remain limited. We present SASHIMI (Spatial Analysis for Segmented Histopathology Images using Machine Intelligence), a browser-based platform for real-time spatial analysis of AI-segmented histopathology images. Rather than proposing new spatial methods, SASHIMI systematically organizes and operationalizes 27 widely used spatial summary statistics, areal indices, and topological features within a unified computational framework. The platform computes mathematically grounded descriptors including K-, L-, G-, F-, and J-functions, pair correlation and mark connection functions, spatial autocorrelation measures, similarity indices, and persistent homology-based topological summaries. Outputs include both functional curves and scalar feature tables suitable for downstream statistical modeling. We illustrate the framework using two cancer cohorts: oral potentially malignant disorders and non-small-cell lung cancer. Across datasets, cross-type spatial interactions and topological descriptors show associations with patient survival, demonstrating that complementary spatial features capture distinct aspects of tumor microenvironment architecture. SASHIMI provides an accessible, reproducible platform for single-cell-level spatial profiling of tumor tissue, enabling interactive visualization and standardized feature extraction without requiring programming expertise.

Paper Structure

This paper contains 31 sections, 41 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Data
  3. Point Pattern Data
  4. Marked Point Pattern Data
  5. Imaging Features
  6. Spatial Summary Statistics
  7. $K$ and $L$-functions
  8. $G$, $F$, and $J$-Functions
  9. Correlation Functions
  10. Areal Data Indices
  11. Spatial Autocorrelation Measures
  12. Similarity Indices
  13. Topological Features
  14. Model-based Spatial Analysis Methods
  15. Bayesian Hidden Potts Mixture Model
  16. ...and 16 more sections

Figures (2)

  • Figure 1: SASHIMI workflow
  • Figure 2: User interface of the SASHIMI web application. (A) Home and overview interface introducing the framework and navigation structure; (B) Online analysis page for uploading point-pattern data and selecting spatial features; (C) Output page displaying areal-level maps and functional results with download options.