Search research articles

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

Human ZBP1 is a potent inducer of cell death through mechanisms divergent from mouse ZBP1.

EMBO reports·2026

Same author

Incorporation of Co-Cyromazine Complexes Onto Halloysite Nanotubes as a Spin-Tip Solid-Phase Extraction Sorbent for Determining Hydrophilic B Vitamins in Functional Foods.

Journal of separation science·2026

Same author

Upcycling shaddock peel waste into a Fe/Fe<sub>3</sub>C@porous carbon sensor for ultrasensitive electrochemical detection of carbendazim.

Analytica chimica acta·2026

Same author

Stage-specific environmental responses and divergent distributional shifts of Antarctic krill under climate change in the Cosmonaut Sea.

Journal of environmental management·2026

Same author

Meat quality assessment at different slaughter weights of broilers sold in the retail market of Dhaka City, Bangladesh: An integrated approach.

Journal of advanced veterinary and animal research·2026

Same author

Correction: Machine learning-based radiomics approach assessing preoperative non-contrast CT for microsatellite instability prediction in colon cancer.

Frontiers in physiology·2026

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

Search research articles

Related Experiment Video

Updated: Jun 30, 2026

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

HiGATE: hierarchical graph attention for multi-scale tissue encoder in computational pathology.

Imam Dad¹, Jianfeng He¹, Tao Shen²

¹Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China.

Frontiers in Oncology

|June 10, 2026

Summary

HiGATE, a novel Hierarchical Graph Attention Tissue Encoder, unifies cell and tissue analysis for improved histopathological diagnosis. This AI framework enhances diagnostic accuracy and clinical trust by integrating multi-scale reasoning.

Keywords:

Explainable AI computational pathology cross-level attention graph attention networks hierarchical graph neural networks histopathological analysis multiscale learning

More Related Videos

Multimodal Hierarchical Imaging of Serial Sections for Finding Specific Cellular Targets within Large Volumes

Multimodal Hierarchical Imaging of Serial Sections for Finding Specific Cellular Targets within Large Volumes

Published on: March 20, 2018

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

Related Experiment Videos

Last Updated: Jun 30, 2026

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

Multimodal Hierarchical Imaging of Serial Sections for Finding Specific Cellular Targets within Large Volumes

Multimodal Hierarchical Imaging of Serial Sections for Finding Specific Cellular Targets within Large Volumes

Published on: March 20, 2018

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

Area of Science:

Computational pathology
Artificial intelligence in medicine
Graph representation learning

Background:

Histopathological diagnosis requires integrating cellular morphology and tissue architecture.
Current computational models analyze cells and tissues separately, limiting diagnostic synergy and clinical trust.

Purpose of the Study:

To introduce HiGATE (Hierarchical Graph Attention Tissue Encoder), a framework unifying cellular and tissue-level analysis.
To enable dynamic, context-aware communication between cellular and tissue representations using bidirectional Cross-Level Attention.
To adaptively capture tissue heterogeneity via learnable, spatially-constrained graph construction.

Main Methods:

Developed a dual-graph architecture with a bidirectional Cross-Level Attention mechanism.
Incorporated differentiable pooling with spatial regularization for adaptive graph construction.
Integrated multi-modal nuclear features including visual semantics (DINOv2), shape descriptors, and morphometrics (StarDist).
Validated across PanNuke, MoNuSeg, DigestPath, and TCGA-BRCA datasets for classification, segmentation, and grading tasks.

Main Results:

Achieved state-of-the-art performance on PanNuke: 91.3% accuracy and 0.896 F1-score for nuclei classification, 85.4% for tissue-type classification.
Demonstrated strong cross-dataset generalization: MoNuSeg (Dice=0.841), DigestPath (accuracy=0.872), TCGA-BRCA (accuracy=0.854).
Reduced false positives by 10.1% compared to HACT-Net at high recall (0.95).
Pathologist study confirmed clinical relevance of multi-scale explanations (mean diagnostic relevance=4.1/5.0).

Conclusions:

HiGATE bridges the gap between AI performance and clinical diagnostics by unifying accuracy with transparent reasoning.
The bidirectional cross-scale attention mechanism offers a general contribution to hierarchical graph representation learning.
HiGATE provides a robust foundation for trustworthy diagnostic AI in personalized medicine.