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

Adaptive, Privacy-Preserving Small Language Models for Multi-Task Clinical Assistance.

Journal of imaging informatics in medicine·2026
Same author

Pearls & Oy-sters: Using Susceptibility-Based Imaging in Highly Active Late-Onset Multiple Sclerosis.

Neurology·2026
Same author

Dynamic MRI of Fluid and Solute Transportation across the Arachnoid Barrier in the Human Meninges.

Radiology·2026
Same author

Prostate cancer molecular subtypes in systematic versus MRI-targeted biopsy cores at active surveillance: association of PTEN and ERG status with extreme grade reclassification.

Histopathology·2025
Same author

Best Practices for the Safe Use of Large Language Models and Other Generative AI in Radiology.

Radiology·2025
Same author

Family History of Prostate, Breast, Ovarian, and/or Pancreatic Cancer and Associations with Grade Reclassification in a Large Prostate Cancer Active Surveillance Cohort.

European urology oncology·2025

Related Experiment Video

Updated: Sep 29, 2025

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

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

7.4K

Tumor Connectomics: Mapping the Intra-Tumoral Complex Interaction Network Using Machine Learning.

Vishwa S Parekh1,2, Jay J Pillai1,3, Katarzyna J Macura1,4

  • 1The Russell H. Morgan Department of Radiology and Radiological Science, School of Medicine, The Johns Hopkins University, Baltimore, MD 21205, USA.

Cancers
|March 25, 2022
PubMed
Summary
This summary is machine-generated.

We developed a tumor connectomics framework (TCF) using graph theory and machine learning to map complex tumor networks. This novel approach enhances understanding of tumor microenvironment interactions and aids in characterization.

Keywords:
brainbreastcancercomplex networksgraph theorymultiparametric MRIprostatetumor connectomics

More Related Videos

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors
06:32

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

2.3K
Visualization, Quantification, and Mapping of Immune Cell Populations in the Tumor Microenvironment
11:00

Visualization, Quantification, and Mapping of Immune Cell Populations in the Tumor Microenvironment

Published on: March 25, 2020

17.3K

Related Experiment Videos

Last Updated: Sep 29, 2025

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

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

7.4K
Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors
06:32

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

2.3K
Visualization, Quantification, and Mapping of Immune Cell Populations in the Tumor Microenvironment
11:00

Visualization, Quantification, and Mapping of Immune Cell Populations in the Tumor Microenvironment

Published on: March 25, 2020

17.3K

Area of Science:

  • Medical Imaging
  • Computational Biology
  • Graph Theory

Background:

  • Understanding complex tumor networks and their interactions with surrounding tissues is challenging.
  • Existing imaging methods offer limited insight into the intricate tumoral microenvironment.

Purpose of the Study:

  • To develop and validate a novel tumor connectomics framework (TCF) for modeling and characterizing tumor networks.
  • To utilize machine learning and graph theory on multiparametric MRI data for improved tumor analysis.

Main Methods:

  • Developed a TCF using graph theory and machine learning (IsoSVM) to model tumor microenvironment interactions.
  • Analyzed network connections using graph metrics: centrality, average path length (APL), and clustering.
  • Validated TCF performance on independent breast, brain, and prostate cancer datasets using MCC, AUC-ROC, and AUC-PR metrics.

Main Results:

  • TCF achieved high classification performance for breast (AUC-PR 0.86, MCC 0.63) and brain tumors (AUC-PR 0.85, MCC 0.65).
  • TCF identified distinct network properties for benign vs. malignant breast lesions and different grades of brain tumors.
  • Gleason 7 prostate lesions showed altered network metrics (betweenness centrality, APL) compared to Gleason 6, with high classification accuracy (AUC-PR 0.90-0.99, MCC 0.73-0.87).

Conclusions:

  • The TCF provides a novel method for tumor characterization and visualization.
  • This framework enhances the understanding of global and regional connections within tumors and surrounding tissues.
  • TCF demonstrates significant potential for improving diagnostic accuracy and treatment planning in oncology.