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 22, 2026

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Interactive lesion segmentation with shape priors from offline and online learning.

Tony Shepherd1, Simon J D Prince, Daniel C Alexander

  • 1Turku PET Centre and Department of Oncology and Radiotherapy, Turku University Hospital, Turku, Finland. tony.shepherd@tyks.fi

IEEE Transactions on Medical Imaging
|May 2, 2012
PubMed
Summary

This study introduces novel statistical shape models (SSMs) and dynamic contour models (DCMs) for accurate medical image segmentation of tumors and lesions. These advanced models improve accuracy and reduce manual effort in pathological region delineation.

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

Reasoning in machine vision by learning fast and slow thinking.

Nature communications·2026
Same author

Microbiome-behavior coupling shapes infant adaptation to early maternal unpredictability.

Frontiers in microbiology·2026
Same author

InnerEye-HS: a disease-agnostic clinical tool for hippocampal segmentation.

Brain communications·2026
Same author

Towards generalisable foundation models for brain MRI.

Npj imaging·2026
Same author

Real-Time, Inline Quantitative MRI Enabled by Scanner-Integrated Machine Learning: A Proof of Principle With NODDI.

Magnetic resonance in medicine·2026
Same author

Expanded detection of early fibrotic phenotypes using lobar traction bronchiolectasis in lung cancer screening.

American journal of respiratory and critical care medicine·2026

Area of Science:

  • Medical image analysis
  • Computational pathology
  • Machine learning in healthcare

Background:

  • Accurate segmentation of tumors and lesions in medical images is crucial but challenging due to limitations in current automatic methods.
  • Existing shape modeling techniques often exclude pathological regions, hindering the development of robust automatic segmentation.
  • Manual delineation remains a bottleneck, demanding high accuracy and significant user intervention.

Purpose of the Study:

  • To develop novel statistical shape models (SSMs) and dynamic contour models (DCMs) for improved medical image segmentation of pathological regions.
  • To enhance automatic segmentation accuracy by incorporating low-level shape information from boundary fluctuations.
  • To introduce an interactive approach with online learning for refining segmentation models based on user input.

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: May 22, 2026

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Main Methods:

  • Development of two new SSMs combining radial shape parameterization with nonlinear time series analysis.
  • Creation of two DCMs utilizing the new SSMs as shape priors for tumor and lesion segmentation.
  • Implementation of an online learning mechanism within one DCM for adaptive shape prior refinement.

Main Results:

  • The new SSMs effectively learn discriminant low-level shape information from boundary fluctuations.
  • Classification experiments demonstrated superior sensitivity and specificity of the proposed shape priors compared to existing methods.
  • User trials confirmed that the new interactive algorithms significantly improve segmentation accuracy and reduce user demand.

Conclusions:

  • The developed SSMs and DCMs offer a significant advancement in automatic medical image segmentation for pathological regions.
  • The incorporation of low-level shape details and interactive learning enhances segmentation performance and user experience.
  • These findings pave the way for more efficient and accurate clinical diagnostic tools.