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

Automatic tumor segmentation using knowledge-based techniques

M C Clark1, L O Hall, D B Goldgof

  • 1Department of Computer Science and Engineering, University of South Florida, Tampa 33620, USA.

IEEE Transactions on Medical Imaging
|August 4, 1998
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

Lumbar disc nomenclature: version 2.0.

AJNR. American journal of neuroradiology·2014
Same author

Reply to letter to the editor.

Journal of pediatric surgery·2013
Same author

Laparoscopic-assisted removal of gastric trichobezoar; a novel technique to reduce operative complications and time.

Journal of pediatric surgery·2013
Same author

Tension pneumocephalus: a case report of spontaneous decompression into the ventricular system.

Journal of neuroradiology = Journal de neuroradiologie·2013
Same author

Automatic section thickness determination using an absolute gradient focus function.

Journal of microscopy·2012
Same author

Ipilimumab-induced hypophysitis: MR imaging findings.

AJNR. American journal of neuroradiology·2009
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 presents an automated system for segmenting and labeling glioblastoma tumors in brain MRIs. The knowledge-based system integrates multispectral analysis for accurate tumor identification and tracking during treatment.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Neuro-oncology

Background:

  • Accurate segmentation of glioblastoma tumors in MRI is crucial for diagnosis and treatment monitoring.
  • Manual segmentation is time-consuming and subject to inter-observer variability.
  • Developing automated systems can improve efficiency and consistency in glioblastoma analysis.

Purpose of the Study:

  • To develop and evaluate an automated system for segmenting and labeling glioblastoma-multiforme tumors in brain MRIs.
  • To integrate knowledge-based techniques with multispectral analysis for enhanced tumor detection.
  • To assess the system's performance against radiologist-labeled ground truth and other automated methods.

Main Methods:

  • The system utilizes T1-weighted, proton density, and T2-weighted MRI sequences.

Related Experiment Videos

  • It employs unsupervised clustering for initial segmentation, followed by a rule-based expert system for intracranial region extraction.
  • Multispectral histogram analysis and region analysis are used for final tumor labeling.

    • Main Results:

    • The system was trained on three datasets and tested on thirteen unseen datasets.
    • Knowledge-based tumor segmentation demonstrated good correspondence with radiologist-labeled ground truth.
    • The system effectively tracked total tumor volume changes over time during treatment.

    Conclusions:

    • The developed automated system shows promise for accurate glioblastoma segmentation and labeling in MRI.
    • This approach offers a reliable method for monitoring tumor volume dynamics, aiding in treatment assessment.
    • Further validation on diverse datasets could enhance its clinical applicability.