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

Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity

Wei Wu1, Albert Y C Chen, Liang Zhao

  • 1Department of Computer Science and Engineering, SUNY at Buffalo, Buffalo, NY, USA, hustwuwei@gmail.com.

International Journal of Computer Assisted Radiology and Surgery
|July 18, 2013
PubMed
Summary

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

Measuring Physical Plausibility of 3D Human Poses Using Physics Simulation.

BMVC : proceedings of the British Machine Vision Conference. British Machine Vision Conference·2026
Same author

Learning to Estimate External Forces of Human Motion in Video.

Proceedings of the ... ACM International Conference on Multimedia, with co-located Symposium & Workshops. ACM International Conference on Multimedia·2026
Same author

Temporally guided articulated hand pose tracking in surgical videos.

International journal of computer assisted radiology and surgery·2022
Same author

Slimming Neural Networks Using Adaptive Connectivity Scores.

IEEE transactions on neural networks and learning systems·2022
Same author

Novel Assessments of Technical and Nontechnical Cardiac Surgery Quality: Protocol for a Mixed Methods Study.

JMIR research protocols·2021
Same author

A Temporally-Aware Interpolation Network for Video Frame Inpainting.

IEEE transactions on pattern analysis and machine intelligence·2019

A novel method accurately segments brain tumors like glioblastoma multiforme (GBM) in MRI scans. This approach improves upon existing techniques, offering robust tumor detection and segmentation for better analysis.

Area of Science:

  • Medical Imaging
  • Computational Biology
  • Artificial Intelligence

Background:

  • Glioblastoma multiforme (GBM) segmentation in MRI is challenging due to heterogeneous signal characteristics.
  • Traditional methods like thresholding and statistical approaches struggle with GBM's complex features (enhancement, necrosis, edema).
  • Existing model-based methods face limitations in small sample learning and transferability.

Purpose of the Study:

  • To develop and test a robust segmentation method for brain tumor MRI scans.
  • To overcome the limitations of existing segmentation techniques for GBM.
  • To achieve accurate detection and segmentation of brain tumors in MR images.

Main Methods:

  • Multimodal MR images segmented into superpixels to improve sample representativeness.

Related Experiment Videos

  • Feature extraction from superpixels using multi-level Gabor wavelet filters.
  • Training of Support Vector Machine (SVM) and affinity metric models, followed by conditional random fields for segmentation.
  • Removal of labeling noise using structural knowledge (symmetry, continuity).

    • Main Results:

    • The system was evaluated on 20 GBM cases and the BraTS challenge dataset.
    • Dice coefficients demonstrated high consistency with established benchmarks (Zikic et al., 2012).

    Conclusions:

    • A novel brain tumor segmentation method utilizing model-aware affinity was developed.
    • The proposed method shows performance comparable to state-of-the-art algorithms.
    • This approach offers a robust solution for challenging brain tumor segmentation tasks.