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

Efficient multilevel brain tumor segmentation with integrated bayesian model classification.

J J Corso1, E Sharon, S Dube

  • 1Department of Radiological Sciences, University of California-Los Angeles, Los Angeles, CA 90095, USA. jcorso@cse.buffalo.edu

IEEE Transactions on Medical Imaging
|May 3, 2008
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

DART (NCI/SWOG S1609): comprehensive final results from dual checkpoint inhibition with CTLA-4 and PD-1 blockade in rare cancers.

Annals of oncology : official journal of the European Society for Medical Oncology·2026
Same author

Canadian Surgery Forum: Abstracts of presentations to the Annual Meetings of the Canadian Association of Bariatric Physicians and Surgeons, Canadian Association of General Surgeons, Canadian Association of Thoracic Surgeons, Canadian Hepato-Pancreato-Biliary Society, Canadian Society of Surgical Oncology, Canadian Society of Colon and Rectal Surgeons, London, Ont. Sept. 15-18, 2011.

Canadian journal of surgery. Journal canadien de chirurgie·2022
Same author

Crizotinib in patients with tumors harboring ALK or ROS1 rearrangements in the NCI-MATCH trial.

NPJ precision oncology·2022
Same author

Corrigendum to 'Ado-trastuzumab emtansine (T-DM1) in patients with HER2-amplified tumors excluding breast and gastric/gastroesophageal junction (GEJ) adenocarcinomas: results from the NCI-MATCH trial (EAY131) subprotocol Q': [Annals of Oncology 30 (2019) 1821-1830].

Annals of oncology : official journal of the European Society for Medical Oncology·2021
Same author

Ado-trastuzumab emtansine (T-DM1) in patients with HER2-amplified tumors excluding breast and gastric/gastroesophageal junction (GEJ) adenocarcinomas: results from the NCI-MATCH trial (EAY131) subprotocol Q.

Annals of oncology : official journal of the European Society for Medical Oncology·2019
Same author

Jet Shapes of Isolated Photon-Tagged Jets in Pb-Pb and pp Collisions at sqrt[s_{NN}]=5.02  TeV.

Physical review letters·2019
Same journal

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026
Same journal

Informed-Exploration Reinforcement Learning for Automated Virtual Coronary Intervention Planning.

IEEE transactions on medical imaging·2026
Same journal

4D Reconstruction of Fetal Left Ventricle from Echocardiography via 2.5D Radial Segmentation and Graph-Fourier Reconstruction.

IEEE transactions on medical imaging·2026
Same journal

Generalised Medical Phrase Grounding.

IEEE transactions on medical imaging·2026
Same journal

EndoLRMGS: Combining Large Reconstruction Modelling and Gaussian Splatting for Complete Endoscopic Scene Reconstruction.

IEEE transactions on medical imaging·2026
Same journal

A Neural-Analytical Fusion Scatter Correction Method for Multi-Source CT Using Equivalent High-Order Scatter.

IEEE transactions on medical imaging·2026
See all related articles

This study introduces a novel Bayesian method for image segmentation, improving brain tumor detection by integrating model assignments into affinity calculations. The approach is significantly faster and yields comparable or better results than existing techniques.

Area of Science:

  • Medical Image Analysis
  • Computational Biology
  • Artificial Intelligence

Background:

  • Automatic image segmentation is crucial for medical diagnosis.
  • Existing methods often fall into either bottom-up or top-down approaches.
  • Bridging the gap between these approaches can enhance segmentation accuracy.

Purpose of the Study:

  • To develop a novel method for automatic segmentation of heterogeneous image data.
  • To bridge the gap between bottom-up affinity-based and top-down generative model-based segmentation.
  • To improve the detection and segmentation of brain tumors and edema.

Main Methods:

  • A Bayesian formulation was developed to incorporate soft model assignments into affinity calculations.
  • Model-aware affinities were integrated into a multilevel segmentation by weighted aggregation algorithm.

Related Experiment Videos

  • The method was applied to multichannel magnetic resonance (MR) volumes for brain tumor analysis.

    • Main Results:

    • The proposed method achieves comparable or improved results compared to state-of-the-art techniques.
    • The computationally efficient method runs orders of magnitude faster than existing methods.
    • Quantitative results demonstrate the benefit of model-aware affinities for glioblastoma multiforme segmentation.

    Conclusions:

    • The novel Bayesian approach effectively integrates model-aware affinities for improved image segmentation.
    • This method offers a computationally efficient and accurate solution for brain tumor detection and segmentation.
    • The technique shows significant promise for analyzing complex medical imaging data.