Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Occurrence and temporal changes of pharmaceuticals in the Warta River in Poland during and after the COVID-19 pandemic.

Scientific reports·2025

Same author

Spatially organized inflammatory myeloid-CD8<sup>+</sup> T cell aggregates linked to Merkel-cell Polyomavirus driven Reorganization of the Tumor Microenvironment.

bioRxiv : the preprint server for biology·2025

Same author

TissueViewer: a web-based multiplexed image viewer.

Bioinformatics (Oxford, England)·2025

Same author

Self-interactive learning: Fusion and evolution of multi-scale histomorphology features for molecular traits prediction in computational pathology.

Medical image analysis·2025

Same author

Tumour purity assessment with deep learning in colorectal cancer and impact on molecular analysis.

The Journal of pathology·2024

Same author

A proinflammatory stem cell niche drives myelofibrosis through a targetable galectin-1 axis.

Science translational medicine·2024

Search research articles

Related Experiment Video

Updated: Oct 13, 2025

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

Self-Organizing Maps for Cellular In Silico Staining and Cell Substate Classification.

Edwin Yuan¹, Magdalena Matusiak², Korsuk Sirinukunwattana^3,4,5,6

¹Department of Applied Physics, Stanford University, Stanford, CA, United States.

Frontiers in Immunology

|November 15, 2021

Summary

Seg-SOM, a novel method, analyzes cell morphology in H&E-stained tissues to reveal cellular composition and architecture. This approach aids in understanding tumor microenvironments and predicting patient outcomes.

Keywords:

cell subtype classification e-pathology in silico staining segmentation self-organization

More Related Videos

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging

Published on: April 30, 2019

Fabrication of a Multiplexed Artificial Cellular MicroEnvironment Array

Fabrication of a Multiplexed Artificial Cellular MicroEnvironment Array

Published on: September 7, 2018

Related Experiment Videos

Last Updated: Oct 13, 2025

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging

Published on: April 30, 2019

Fabrication of a Multiplexed Artificial Cellular MicroEnvironment Array

Fabrication of a Multiplexed Artificial Cellular MicroEnvironment Array

Published on: September 7, 2018

Area of Science:

Computational pathology
Bioinformatics
Artificial intelligence in medicine

Background:

Tissue cellular composition and structure are critical for predicting antitumor responses, patient outcomes, and therapy efficacy.
Understanding cellular heterogeneity and tissue architecture is essential for advancing cancer research and diagnostics.

Purpose of the Study:

To introduce Seg-SOM, a dimensionality reduction method for analyzing cell morphology in H&E-stained tissue images.
To enable systematic cell classification and in silico labeling for detailed tissue analysis.
To provide a framework for utilizing Self-Organizing Maps (SOM) in human pathology for cellular composition resolution.

Main Methods:

Applying a Self-Organizing Map (SOM) artificial neural network to group cells based on morphological features (shape, size).
Utilizing Seg-SOM for cell segmentation, classification, and in silico labeling of H&E-stained tissue images.
Combining Seg-SOM with non-negative matrix factorization to analyze cell subtype interactions.

Main Results:

Clustering of SOM classes identified distinct cell groups (fibroblasts, epithelial cells, lymphocytes) in breast cancer progression images.
Accurate estimation of lymphocytic infiltration by labeling the Lymphocyte SOM class.
Development of highly interpretable features for a histological classifier based on cell subtype interactions.

Conclusions:

Seg-SOM effectively resolves cellular heterogeneity and complex tissue architecture in H&E-stained images.
The method provides a robust framework for analyzing cellular composition in human pathology.
Seg-SOM, with its Python implementation and Docker deployment, facilitates featurization of digitalized tissue for researchers.