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

Tumor-Associated Macrophage Infiltration and PD-L1 Expression in Gastric Cancer According to a Modified TCGA-Based Classification.

Journal of gastric cancer·2026

Same author

Cell strain-stiffening drives cell breakout from embedded spheroids.

ArXiv·2026

Same author

Multimodal Approach for Identification and Validation of Hepatocellular Carcinoma Targets for Radiotheranostics.

bioRxiv : the preprint server for biology·2025

Same author

Evaluating the robustness of slide-level AI predictions on out-of-focus whole slide images: A retrospective observational study.

Journal of pathology informatics·2025

Same author

Correction: Colorectal cancers with a residual adenoma component: Clinicopathologic features and KRAS mutation.

PloS one·2025

Same author

A robust artificial intelligence system for predicting EBV status in gastric cancer biopsy and resection specimens.

Scientific reports·2025

Search research articles

Related Experiment Video

Updated: Jul 17, 2025

Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

Published on: June 2, 2023

Multi-cell type and multi-level graph aggregation network for cancer grading in pathology images.

Syed Farhan Abbas¹, Trinh Thi Le Vuong¹, Kyungeun Kim²

¹School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea.

Medical Image Analysis

|September 3, 2023

Summary

A new deep learning model, MMGA-Net, improves cancer grading by analyzing cell types and interactions within pathology images. This approach enhances automated cancer diagnosis by integrating cellular composition with tissue context.

Keywords:

Cancer grading Cell graphs Graph aggregation Graph neural network

More Related Videos

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

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

Related Experiment Videos

Last Updated: Jul 17, 2025

Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

Published on: June 2, 2023

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

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

Area of Science:

Computational pathology
Artificial intelligence in medicine
Oncology imaging analysis

Background:

Cancer grading is essential for patient management and treatment decisions.
Deep learning, particularly Convolutional Neural Networks (CNNs), shows promise for automated cancer diagnosis.
Existing CNN methods often overlook explicit tissue/cellular composition, limiting the integration of pathological knowledge.

Purpose of the Study:

To introduce a novel Multi-cell type and Multi-level Graph Aggregation Network (MMGA-Net) for automated cancer grading.
To develop a method that explicitly incorporates intra- and inter-cell type relationships and interactions.
To fuse cellular and tissue information for more accurate cancer grade prediction.

Main Methods:

MMGA-Net constructs multiple cell graphs at various levels to capture complex cell-to-cell interactions.
The network represents relationships between different cell types and analyzes global/local cellular interactions.
Tissue contextual information is extracted using a CNN, and then fused with cellular graph data.

Main Results:

MMGA-Net demonstrated superior performance on two cancer datasets compared to existing models.
The model effectively integrates multi-level, multi-cell type information through graph aggregation.
Experimental results validate the effectiveness of fusing cellular composition and tissue context for improved cancer grading.

Conclusions:

MMGA-Net offers a significant advancement in automated cancer grading by leveraging detailed cellular and tissue information.
The fusion of multiple cell types and interaction levels via graph networks is crucial for enhancing pathology image analysis.
This approach holds potential for improving the accuracy and reliability of cancer diagnosis and patient management.