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

Multi-atlas pancreas segmentation: Atlas selection based on vessel structure.

Ken'ichi Karasawa1, Masahiro Oda1, Takayuki Kitasaka2

  • 1Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8601, Japan.

Medical Image Analysis
|April 15, 2017
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

Disparate privacy risks from medical AI.

Nature·2026
Same author

Local and global patterns support medical imaging as a biomarker of ageing.

Communications medicine·2026
Same author

Longitudinal Language-Model Reasoning Enables Automated Labeling of Lung Cancer Recurrence from Unstructured Clinical Records.

Research square·2026
Same author

Multiparametric Free-Breathing 3D Whole-Heart Cardiac MR for Anatomical Bright- and Black-Blood Imaging With Co-Registered <math><semantics><mrow><msub><mrow><mi>T</mi></mrow> <mrow><mn>1</mn></mrow></msub> <mo>/</mo> <msub><mrow><mi>T</mi></mrow> <mrow><mn>2</mn></mrow></msub></mrow> <annotation>$$ {T}_1/{T}_2 $$</annotation></semantics></math> Myocardial Tissue Mapping at <math><semantics><mrow><mn>0</mn> <mo>.</mo> <mn>55</mn></mrow> <annotation>$$ 0.55 $$</annotation></semantics></math> T.

NMR in biomedicine·2026
Same author

A Maturity Model for the Enforcement of PETs in Federated Settings.

Studies in health technology and informatics·2026
Same author

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

Nature·2026

This study introduces a novel atlas selection method for segmenting abdominal organs, specifically the pancreas, using surrounding vessel structures in CT scans. This approach improves segmentation accuracy for challenging cases with high inter-patient variability.

Area of Science:

  • Medical Imaging
  • Computational Anatomy
  • Radiology

Background:

  • Automated organ segmentation is crucial for computer-aided diagnosis (CAD) and computer-assisted surgery (CAS).
  • The pancreas presents segmentation challenges in computed tomography (CT) due to its variable position, size, shape, and similar CT intensity to adjacent tissues.
  • Conventional intensity-based atlas selection methods often fail for pancreas segmentation due to anatomical variability.

Purpose of the Study:

  • To develop and evaluate a new multi-atlas segmentation strategy for pancreas segmentation in CT volumes.
  • To improve the accuracy and robustness of pancreas segmentation by utilizing surrounding vessel structures for atlas selection.

Main Methods:

  • A multi-atlas segmentation scheme was employed.
Keywords:
Atlas selectionCT imageMulti-atlasPancreas segmentationVessel structure

Related Experiment Videos

  • A novel atlas selection strategy based on the vessel structure around pancreatic tissue was proposed and investigated.
  • The method was applied to pancreas segmentation in abdominal contrast-enhanced CT volumes.

    • Main Results:

    • The proposed vessel structure-based atlas selection method demonstrated improved pancreas segmentation.
    • Average Jaccard index of 66.3% and Dice overlap coefficient of 78.5% were achieved on 150 CT volumes.
    • The study explored two applications of vessel structure information for atlas selection.

    Conclusions:

    • The novel atlas selection strategy based on vessel structure significantly enhances pancreas segmentation accuracy in CT images.
    • This method offers a more robust solution for segmenting the pancreas, addressing limitations of intensity-based approaches.
    • The findings contribute to advancing automated organ segmentation for clinical applications.