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 Video

Updated: May 28, 2026

Extracting Metrics for Three-dimensional Root Systems: Volume and Surface Analysis from In-soil X-ray Computed Tomography Data
09:37

Extracting Metrics for Three-dimensional Root Systems: Volume and Surface Analysis from In-soil X-ray Computed Tomography Data

Published on: April 26, 2016

3-D graph cut segmentation with Riemannian metrics to avoid the shrinking problem.

Shouhei Hanaoka1, Karl Fritscher, Martin Welk

  • 1The Institute of Biomedical Image Analysis, The Health and Life Sciences University (UMIT), Eduard-Wallnöfer-Zentrum 1, Hall in Tirol, Austria. hanaoka-tky@umin.ac.jp

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|October 19, 2011
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

Honeycomb-Like Mucinous Carcinoma of the Pancreas, Mimicking Serous Cystadenoma.

Journal of clinical ultrasound : JCU·2026
Same author

Synthesis of Amyloid Images Using a Generative Adversarial Network from 2-Dimensional <sup>18</sup>F-FDG Images and Evaluation for Clinical Use.

Journal of nuclear medicine technology·2026
Same author

What are you looking at? Modality contribution in multimodal medical deep learning.

International journal of computer assisted radiology and surgery·2025
Same author

Evaluation of amyloid PET positivity using machine learning on <sup>18</sup>F-FDG PET images.

Japanese journal of radiology·2025
Same author

Super-resolution deep learning reconstruction to evaluate lumbar spinal stenosis status on magnetic resonance myelography.

Japanese journal of radiology·2025
Same author

Head and Neck Tumor Segmentation on MRIs with Fast and Resource-Efficient Staged nnU-Nets.

Head and Neck Tumor Segmentation for MR-Guided Applications : First MICCAI Challenge, HNTS-MRG 2024, held in conjunction with MICCAI 2024, Marrakesh, Morocco, October 17, 2024, proceedings·2025

This study introduces a new graph cut segmentation method using Riemannian metrics to solve the "shrinking problem" in medical imaging. The novel approach effectively segments thin, elongated structures like vertebral bones in CT scans.

Area of Science:

  • Medical Image Analysis
  • Computer Vision
  • Computational Geometry

Background:

  • Graph cut segmentation is a common technique but struggles with thin, elongated structures due to the "shrinking problem."
  • Many medical imaging targets, such as vertebral bones, possess these challenging thin structures.
  • Conventional graph cut methods are thus unsuitable for segmenting such anatomical features.

Purpose of the Study:

  • To develop an improved graph cut segmentation method capable of accurately segmenting thin, elongated structures.
  • To address the "shrinking problem" inherent in traditional graph cut algorithms.
  • To enhance the applicability of graph cut segmentation in medical image analysis.

Main Methods:

  • Developed a novel graph cut segmentation method incorporating Riemannian metrics.

More Related Videos

Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality
06:18

Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality

Published on: April 5, 2024

Related Experiment Videos

Last Updated: May 28, 2026

Extracting Metrics for Three-dimensional Root Systems: Volume and Surface Analysis from In-soil X-ray Computed Tomography Data
09:37

Extracting Metrics for Three-dimensional Root Systems: Volume and Surface Analysis from In-soil X-ray Computed Tomography Data

Published on: April 26, 2016

Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality
06:18

Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality

Published on: April 5, 2024

  • Riemannian metrics are derived from an initial contour, ensuring consistent surface area in Riemannian space.
  • This metric design prevents the "shrinking problem" for shapes similar to the initial contour.

    • Main Results:

    • The proposed method demonstrated effectiveness in segmenting thin, elongated structures.
    • Evaluation on clinical CT datasets showed fair results in segmenting vertebral bones.
    • The novel Riemannian metrics successfully mitigated the "shrinking problem" observed in conventional methods.

    Conclusions:

    • The developed graph cut segmentation method with Riemannian metrics offers a viable solution for segmenting thin, elongated structures in medical images.
    • This approach enhances the utility of graph cut segmentation for challenging targets like vertebral bones.
    • The method shows promise for improving medical image analysis accuracy and efficiency.