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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

YIF1B Mutational Dysregulation Drives Cutaneous Melanoma Progression by Remodeling the TME.

Human mutation·2026
Same author

LncRNA MIR4435-2HG-mediated succinylation of USF1 promotes its protein stability and induces epithelial-mesenchymal transition in HNSCC.

Epigenetics·2026
Same author

ETV7 promotes 5-FU resistance and malignant progression through CXCL1-induced NETs formation in colorectal cancer.

Communications biology·2026
Same author

Functional Characterization of OasiCSP12: A Chemosensory Protein Regulating Olfaction and Phase Change in <i>Oedaleus decorus asiaticus</i>.

Insects·2026
Same author

Case Report: Neurogenic pulmonary edema coupled with myocardial damage following tenecteplase thrombolysis for acute ischemic stroke.

Frontiers in cardiovascular medicine·2026
Same author

Potential mechanisms of Si-Wu-Tang against esophageal squamous cell carcinoma: A machine learning pharmacological study.

Medicine·2026
Same journal

Facial iPPG heatmap patterns based on period-aware autoencoder show association with carotid atherosclerosis towards non-contact hemodynamic assessment.

Computer methods and programs in biomedicine·2026
Same journal

Explainable machine learning models predict liver fibrosis risk and outcome in the general population: Development and multi-cohort external validation.

Computer methods and programs in biomedicine·2026
Same journal

Evaluation of surrogate endpoints for survival outcomes using the surrogate package in R.

Computer methods and programs in biomedicine·2026
Same journal

Relative spectral and frication-based descriptors as numerical indicators of place of articulation shifts in fricatives produced by Polish children.

Computer methods and programs in biomedicine·2026
Same journal

Leaflet resection improves valve expansion and hemodynamic performance in redo TAVI with balloon- and self-expanding transcatheter heart valve configurations.

Computer methods and programs in biomedicine·2026
Same journal

Spectral super-resolution for Parkinson's voice via representation-level methods under mixed-reality acquisition.

Computer methods and programs in biomedicine·2026
See all related articles

Related Experiment Video

Updated: Sep 13, 2025

Models of Bone Metastasis
08:49

Models of Bone Metastasis

Published on: September 4, 2012

42.3K

Dynamic hypergraph representation for bone metastasis analysis.

Yuxuan Chen1, Jiawen Li1, Lianghui Zhu1

  • 1Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, Guangdong, China.

Computer Methods and Programs in Biomedicine
|July 30, 2025
PubMed
Summary
This summary is machine-generated.

A novel dynamic hypergraph neural network (DyHG) improves bone metastasis analysis by capturing complex interactions. This deep learning approach enhances diagnostic accuracy for predicting primary bone cancer origins and subtyping.

Keywords:
Bone metastasisDynamic hypergraph constructionHypergraph convolutional networkMultiple instance learningRegions of interest

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
Multi-modal Imaging of Angiogenesis in a Nude Rat Model of Breast Cancer Bone Metastasis Using Magnetic Resonance Imaging, Volumetric Computed Tomography and Ultrasound
12:23

Multi-modal Imaging of Angiogenesis in a Nude Rat Model of Breast Cancer Bone Metastasis Using Magnetic Resonance Imaging, Volumetric Computed Tomography and Ultrasound

Published on: August 14, 2012

14.4K

Related Experiment Videos

Last Updated: Sep 13, 2025

Models of Bone Metastasis
08:49

Models of Bone Metastasis

Published on: September 4, 2012

42.3K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
Multi-modal Imaging of Angiogenesis in a Nude Rat Model of Breast Cancer Bone Metastasis Using Magnetic Resonance Imaging, Volumetric Computed Tomography and Ultrasound
12:23

Multi-modal Imaging of Angiogenesis in a Nude Rat Model of Breast Cancer Bone Metastasis Using Magnetic Resonance Imaging, Volumetric Computed Tomography and Ultrasound

Published on: August 14, 2012

14.4K

Area of Science:

  • Computational pathology
  • Deep learning in oncology
  • Biomedical image analysis

Background:

  • Bone metastasis analysis is crucial for patient outcomes and treatment.
  • Current methods struggle with complex tissue interactions and high-order biological associations.
  • Whole slide images (WSIs) offer detailed pathology data but require advanced analytical tools.

Purpose of the Study:

  • To develop a deep learning model capable of analyzing complex multivariate interactions in bone metastasis.
  • To overcome limitations of traditional methods like multiple instance learning (MIL) and graph neural networks (GNNs).
  • To enhance the accuracy of predicting primary bone cancer origins and subtyping.

Main Methods:

  • Introduction of a dynamic hypergraph neural network (DyHG) that utilizes hyperedges to connect multiple nodes.
  • Employing nonlinear transformation for a learnable hypergraph structure.
  • Utilizing Gumbel-Softmax sampling for patch distribution optimization and an MIL aggregator for graph-level embedding.

Main Results:

  • DyHG demonstrated superior performance on two large-scale datasets for bone cancer classification.
  • The model outperformed state-of-the-art baselines by up to 1.28% in accuracy.
  • Experimental results validate DyHG's ability to model complex biological interactions.

Conclusions:

  • The proposed DyHG offers a powerful tool for auxiliary diagnostic information in bone metastasis analysis.
  • DyHG shows significant potential for clinical application in pathology.
  • This approach advances deep learning applications in cancer subtyping and origin prediction.