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 Videos

Tumor feature visualization with unsupervised learning.

Tim W Nattkemper1, Axel Wismüller

  • 1Applied Neuroinformatics Group, Faculty of Technology, Bielefeld University, P.O. Box 100131, D-33501 Bielefeld, Germany. tnattkem@techfak.uni-bielefeld.de

Medical Image Analysis
|May 24, 2005
PubMed
Summary
This summary is machine-generated.

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

Multimodal contrastive prognostication framework for early neurological outcome prediction in post-cardiac arrest patients.

Scientific reports·2026
Same author

Inferring causal relations from multivariate data using Large-Scale Augmented Granger Causality (lsAGC).

NeuroImage·2025
Same author

Out of sight, but not out of mind: Key issues regarding seafloor macrolitter monitoring.

Marine pollution bulletin·2025
Same author

Scaling down annotation needs: The capacity of self-supervised learning on diatom classification.

iScience·2025
Same author

A data science approach for multi-sensor marine observatory data monitoring cold water corals (Paragorgia arborea) in two campaigns.

PloS one·2023
Same author

Improving deep learning-based segmentation of diatoms in gigapixel-sized virtual slides by object-based tile positioning and object integrity constraint.

PloS one·2023
Same journal

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026
Same journal

MedP-CLIP: Medical CLIP with region-aware prompt integration.

Medical image analysis·2026
Same journal

Multi-organ guided diagnosis of mild cognitive impairment via hierarchical alignment and knowledge distillation.

Medical image analysis·2026
Same journal

SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis.

Medical image analysis·2026
Same journal

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026
Same journal

Annotation-efficient medical image segmentation via cross-latent graphs and vector-quantized memory.

Medical image analysis·2026
See all related articles

Self-organizing maps (SOM) can visualize hidden structures in dynamic contrast-enhanced MRI data for breast cancer. This method aids in identifying benign versus malignant lesions by analyzing voxel signal kinetics.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background:

  • Dynamic contrast-enhanced magnetic resonance imaging (DCE MRI) is crucial for breast cancer diagnosis and therapy monitoring.
  • Lesion malignancy is assessed via signal kinetics within regions of interest (ROI), offering high sensitivity but variable specificity.
  • Computer-aided diagnosis (CAD) systems aim to analyze DCE MRI time-curve data from selected ROIs.

Purpose of the Study:

  • To apply the self-organizing map (SOM) technique to DCE MRI data for improved breast cancer lesion characterization.
  • To visualize the complex, high-dimensional signal space of voxel time-curve data in a two-dimensional map.
  • To evaluate the potential of SOM for identifying benign versus malignant lesions and deriving new visualization parameters.

Main Methods:

Related Experiment Videos

  • The self-organizing map (SOM) algorithm was applied to feature vectors of single voxels from seven benign and seven malignant breast lesions.
  • Time-curve values for each voxel were projected onto a two-dimensional SOM map.
  • The trained SOM was used to classify voxels and visualize lesion cross-sections using pseudo-colors.

Main Results:

  • The SOM successfully visualized the underlying two-dimensional structure within the six-dimensional signal space of DCE MRI data.
  • The technique enabled the identification of voxels exhibiting benign or malignant signal characteristics.
  • Pseudo-color visualization of lesion cross-sections based on SOM classification was achieved.

Conclusions:

  • The self-organizing map (SOM) demonstrates significant potential for analyzing and visualizing DCE MRI data in breast cancer.
  • SOM offers a novel approach to identifying lesion characteristics, potentially improving diagnostic accuracy.
  • This method shows promise for deriving new visualization parameters compared to the established three time points method.