Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Apr 30, 2026

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

23.3K

Graph adiabatic diffusion neural networks for distribution-shift breast tumor image classification.

Haoquan Lu1, Zhihui Lai1, Heng Kong2

  • 1College of Computer Science and Software Engineering, Shenzhen University, Nanshan, Shenzhen, 518060, Guangdong, China.

Neural Networks : the Official Journal of the International Neural Network Society
|February 18, 2026
PubMed
Summary

Related Concept Videos

Assessment of Diffusion and Perfusion01:17

Assessment of Diffusion and Perfusion

2.0K
Understanding and evaluating diffusion and perfusion is critical in assessing a patient's respiratory and circulatory health. These processes play key roles in maintaining the body's internal environment, ensuring that tissues receive adequate oxygen while waste products are efficiently removed.
The Role of Diffusion in Respiration
Diffusion is the process by which molecules move from an area of higher concentration to an area of lower concentration. In the respiratory system, this...
2.0K

You might also read

Related Articles

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

Sort by
Same author

Mammary tumors-derived exosomes induce striatal NF-κB signaling, microglial reactivity, and anxiety/depression-like behaviors.

Brain, behavior, and immunity·2026
Same author

Structural-Functional Connectome Generation via Diffusion-Guided Graph Transformer for Alzheimer's Disease Analysis.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
Same author

Gecko-Like Multi-Directional High-Power Magneto-Mechano-Electric Energy Harvesters for Self-Powered, Hundred-Meter-Scale LoRa Communication.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

NPSVC++: A Representation Learning Framework for Nonparallel Classifiers.

IEEE transactions on neural networks and learning systems·2026
Same author

Interpretable facial landmark detection by multi-expert collaborative uncertainty-aware deep networks.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Adaptive Dispersal and Collaborative Clustering for Few-Shot Unsupervised Domain Adaptation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025

Breast tumor image analysis faces challenges due to low similarity and distribution shifts. Graph Adiabatic Diffusion Neural Networks (GradiNet) improve classification by learning graph structures and simulating distribution shifts for better generalization.

Area of Science:

  • Medical Imaging
  • Machine Learning
  • Graph Neural Networks

Background:

  • Breast tumor images exhibit low intra-class similarity and distribution shift, complicating recognition.
  • High costs of expert annotation limit labeled data availability for training.
  • Semi-supervised learning, particularly Graph Neural Networks (GNNs), offers a promising approach to reduce annotation costs and improve breast tumor classification.

Purpose of the Study:

  • To propose Graph Adiabatic Diffusion Neural Networks (GradiNet) for enhanced breast tumor image classification.
  • To jointly learn discriminative graph structures and simulate distribution shift environments.
  • To improve the generalization ability of models on both in-distribution (ID) and out-of-distribution (OOD) data.

Main Methods:

Keywords:
Breast tumor classificationDiscriminabilityGraph neural diffusionOut-Of-Distribution

Related Experiment Videos

Last Updated: Apr 30, 2026

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

23.3K
  • Developed GradiNet, a novel GNN architecture for breast tumor recognition.
  • Modeled discriminative graph structure using a graph-learning objective function.
  • Introduced a GNN feature propagation mechanism based on the Fourier heat diffusion equation with adiabatic boundary conditions to simulate distribution shifts.

    • Main Results:

    • Demonstrated the effectiveness of the learned graph structure theoretically and empirically.
    • Showcased the adaptive simulation of distribution shifts and enhanced generalization.
    • Achieved state-of-the-art performance on public and private breast tumor ultrasound image datasets across multiple metrics.

    Conclusions:

    • GradiNet effectively addresses challenges in breast tumor image analysis, including low intra-class similarity and distribution shift.
    • The proposed method reduces reliance on extensive labeled data through semi-supervised learning.
    • GradiNet significantly improves classification performance and generalization for breast tumor detection.