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

A generative model for brain tumor segmentation in multi-modal images.

Bjoern H Menze1, Koen Van Leemput, Danial Lashkari

  • 11 Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, USA.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|October 1, 2010
PubMed
Summary

This study presents a new generative probabilistic model for segmenting tumors in multi-dimensional images. The advanced model improves tumor boundary detection compared to traditional methods, aiding in medical image analysis.

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

Consensus-Level and Cluster-Adjusted Evaluation of a Large Language Model for Diagnostic Extraction from Musculoskeletal Radiology Reports.

Diagnostics (Basel, Switzerland)·2026
Same author

Deep-learning based image reconstruction enables reduced dose CT pulmonary angiography with non-inferior image quality.

Scientific reports·2026
Same author

The Role of Large Language Models in Scientific Research.

RoFo : Fortschritte auf dem Gebiete der Rontgenstrahlen und der Nuklearmedizin·2026
Same author

Prevalence, determinants, and clinical relevance of MRI signs of osteitis pubis in the large population-based cohort SHIP.

European journal of radiology·2026
Same author

A deep-learning framework reveals whole-body perturbations at cell level.

Nature·2026
Same author

[Crossed double patellar tendon as incidental finding in retropatellar arthrosis].

RoFo : Fortschritte auf dem Gebiete der Rontgenstrahlen und der Nuklearmedizin·2026

Area of Science:

  • Medical image analysis
  • Computational pathology
  • Radiomics

Background:

  • Accurate tumor segmentation is crucial for diagnosis and treatment planning.
  • Existing methods struggle with variations in tumor appearance across different imaging modalities.
  • Multi-dimensional image analysis requires sophisticated modeling techniques.

Purpose of the Study:

  • To introduce a novel generative probabilistic model for multi-dimensional tumor segmentation.
  • To enable accurate delineation of tumor boundaries across different imaging channels.
  • To improve upon traditional multivariate tumor segmentation techniques.

Main Methods:

  • Developed a generative probabilistic model incorporating healthy tissue priors and a latent lesion atlas.

Related Experiment Videos

  • Derived an estimation algorithm to extract tumor boundaries and the latent atlas from image data.
  • Augmented probabilistic atlases for enhanced segmentation accuracy.

    • Main Results:

    • The model successfully segmented tumors in multi-dimensional images, accommodating varying tumor appearances per channel.
    • Experiments on 25 glioma patient datasets showed significant improvements over traditional multivariate segmentation.
    • The latent atlas effectively captured tumor characteristics across modalities.

    Conclusions:

    • The proposed generative probabilistic model offers a significant advancement in multi-dimensional tumor segmentation.
    • This approach enhances the accuracy and robustness of tumor boundary detection in medical imaging.
    • The method shows promise for improved clinical applications in oncology and radiology.