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

3-D breast ultrasound segmentation using active contour model.

Dar-Ren Chen1, Ruey-Feng Chang, Wen-Jie Wu

  • 1Department of General Surgery, China Medical College & Hospital, Taichung, Taiwan. dlchen88@ms13.hinet.net

Ultrasound in Medicine & Biology
|July 25, 2003
PubMed
Summary

This study introduces an automated method using active contours for precise breast tumor segmentation in ultrasound images. The technique improves accuracy by incorporating edge information and can be extended to 3D tumor volume calculation.

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

2025 Update of the Taiwan Expert Consensus on Hormone Receptor-Positive Metastatic Breast Cancer Management.

Journal of breast cancer·2026
Same author

Dual-Phase Computed Tomography-Based Deep Learning Architecture for Three-Year Survival Prediction in Hepatocellular Carcinoma.

Journal of imaging informatics in medicine·2026
Same author

An adaptor protein CRK mediates antiviral immunity against white spot syndrome virus via JAK/STAT signaling pathway in Cherax quadricarinatus.

Fish & shellfish immunology·2026
Same author

Preoperative Chemoimmunotherapy Followed by Salvage Surgery and Adjuvant Tislelizumab for Previously Irradiated Recurrent HNSCC: A Prospective Phase II Trial.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same author

Long-term oncologic outcomes of minimal access (endoscopic or Robotic Assisted) nipple-sparing mastectomy compared with conventional approach in breast cancer - a propensity score matching analysis.

International journal of surgery (London, England)·2025
Same author

Structural Symmetry and Mixed-anion Engineering in Halopnictides for Extraordinary Second-Harmonic Generation.

Angewandte Chemie (International ed. in English)·2025

Area of Science:

  • Medical imaging
  • Image processing
  • Computational biology

Background:

  • Ultrasound (US) imaging is crucial for breast tumor detection but suffers from speckle, noise, and texture artifacts.
  • Accurate segmentation of breast tumors is essential for diagnosis and treatment planning.
  • Manual delineation of tumor boundaries is time-consuming and subjective.

Purpose of the Study:

  • To develop an automated method for precise breast tumor segmentation in ultrasound images.
  • To overcome limitations of manual contour initialization in active contour models.
  • To improve the accuracy of tumor boundary detection and enable 3D volume estimation.

Main Methods:

  • Utilized a discrete active contour model (snake-deformation) for tumor segmentation.

Related Experiment Videos

  • Developed an automatic initial contour-finding method to maintain tumor shape and proximity to the boundary.
  • Incorporated edge information as an external force to prevent false contour positioning due to image artifacts.
  • Extended the 2D segmentation method for 3D tumor volume calculation.

    • Main Results:

    • The proposed method accurately segments breast tumors by overcoming US image properties like speckle and noise.
    • Automatic contour initialization significantly reduces the time required compared to manual methods.
    • Inclusion of edge information enhances the robustness of the snake-deformation process.
    • The method demonstrates good performance and satisfactory results for 3D tumor volume estimation.

    Conclusions:

    • The automated active contour model provides precise breast tumor segmentation in ultrasound images.
    • The developed method is efficient, accurate, and robust against common ultrasound image artifacts.
    • The approach is extendable to 3D, enabling accurate tumor volume quantification for clinical applications.