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

Medical image segmentation using analysis of isolable-contour maps.

S Shiffman1, G D Rubin, S Napel

  • 1Department of Psychiatry, Stanford University, CA 94305, USA.

IEEE Transactions on Medical Imaging
|February 24, 2001
PubMed
Summary

This study introduces intrinsic shape for segmentation (ISeg), a novel automated image segmentation method. ISeg effectively differentiates between closely spaced objects with similar intensities, improving boundary detection in medical imaging.

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

Sales of Electronic Nicotine Delivery Systems (ENDS) and Cigarette Sales in the USA: A Trend Break Analysis.

Journal of consumer policy·2023
Same author

Standardization in Quantitative Imaging: A Multicenter Comparison of Radiomic Features from Different Software Packages on Digital Reference Objects and Patient Data Sets.

Tomography (Ann Arbor, Mich.)·2020
Same author

Radiomics in Brain Tumor: Image Assessment, Quantitative Feature Descriptors, and Machine-Learning Approaches.

AJNR. American journal of neuroradiology·2017
Same author

Public health implications of waterpipe tobacco use in the United States warrant initial steps towards assessing dependence.

Addiction (Abingdon, England)·2016
Same author

Imaging informatics: toward capturing and processing semantic information in radiology images.

Yearbook of medical informatics·2010
Same author

Switching to "lighter" cigarettes and quitting smoking.

Tobacco control·2009

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Image Analysis

Background:

  • Automated image segmentation struggles with differentiating objects of similar intensity and blurred boundaries due to partial-volume effects.
  • Accurate segmentation is crucial for quantitative analysis in medical imaging, particularly in techniques like computed-tomography angiography.

Purpose of the Study:

  • To develop a novel automated image segmentation method that overcomes limitations in differentiating closely spaced objects with similar intensities.
  • To introduce the intrinsic shape for segmentation (ISeg) approach and evaluate its performance against conventional methods.

Main Methods:

  • ISeg analyzes isolabel-contour maps generated through multilevel thresholding with fine intensity partitioning.
  • Object boundaries are detected by comparing the shapes of adjacent isolabel contours within the generated map.

Related Experiment Videos

  • The method does not require prior construction of object-specific shape models, reducing user effort.

    • Main Results:

    • ISeg demonstrated superior robustness compared to conventional thresholding techniques in image segmentation.
    • Segmentation results from ISeg were found to be comparable to those achieved through manual tracing.
    • The method effectively addresses challenges posed by blurred boundaries and similar object intensities.

    Conclusions:

    • Intrinsic shape for segmentation (ISeg) offers a robust and user-friendly approach for automated image segmentation.
    • ISeg provides accurate results, comparable to manual segmentation, for challenging medical imaging datasets.
    • This technique holds potential for improving quantitative analysis in various medical imaging applications.