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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Computed Tomography-Based Artificial Intelligence Analysis of Myosteatosis and Its Effect on Survival in Fournier Gangrene.

The world journal of men's health·2026
Same author

Age-Related Testosterone Decline and Metabolic Determinants in 27,687 Korean Men Aged ≥40 Years: A Nationwide Population-Based Study.

The world journal of men's health·2026
Same author

Why Sex/Gender-Specific Medicine Matters in Men's Health Research: An Editorial Call to Action.

The world journal of men's health·2026
Same author

Real Practice Confirmatory Study of Adjustable Initial Injection Volume and Necessity of Retouch and Reinjection in Penile Girth Enhancement with Hyaluronic Acid Gel.

The world journal of men's health·2026
Same author

Analysis of uroflowmetry results in community-dwelling adult males: Results of 24 years of Korean population-based screening data.

Investigative and clinical urology·2026
Same author

Combined therapy with dutasteride and tadalafil vs dutasteride or tadalafil monotherapy in benign prostatic hyperplasia: a randomised phase III trial.

BJU international·2026

Related Experiment Video

Updated: Oct 9, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Intelligent Automatic Segmentation of Wrist Ganglion Cysts Using DBSCAN and Fuzzy C-Means.

Kwang Baek Kim1, Doo Heon Song2, Hyun Jun Park3

  • 1Department of Artificial Intelligence, Silla University, Busan 46958, Korea.

Diagnostics (Basel, Switzerland)
|December 24, 2021
PubMed
Summary

This study introduces an AI-driven method for automatically segmenting ganglion cysts in ultrasound images. The approach improves accuracy, especially for small, hypoechoic cysts, reducing operator subjectivity in diagnosis.

Keywords:
DBSCANfuzzy C-meansganglion cystmachine learningpixel clustering

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.0K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.1K

Related Experiment Videos

Last Updated: Oct 9, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.0K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.1K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Diagnostic Ultrasound

Background:

  • Ganglion cysts are frequent soft tissue masses in the hand and wrist.
  • Small ganglion cysts often appear hypoechoic, posing identification challenges in ultrasonography.
  • Current diagnostic methods can be subjective and dependent on examiner experience.

Purpose of the Study:

  • To develop an automated segmentation method for ganglion cysts using artificial intelligence.
  • To improve the accuracy and reliability of ganglion cyst identification, particularly for small or low-quality ultrasound images.
  • To reduce operator subjectivity in the interpretation of ultrasound findings.

Main Methods:

  • A two-stage artificial intelligence approach was employed, combining DBSCAN and Fuzzy C-Means (FCM) clustering.
  • Density-Based Spatial Clustering of Applications with Noise (DBSCAN) was used as a front-end to determine cluster numbers for FCM.
  • Fuzzy C-Means (FCM) clustering was then applied for the quantification and segmentation of ganglion cyst objects.

Main Results:

  • The proposed automated method achieved a high extraction rate of 89.2% in experiments with 120 images.
  • The method demonstrated a lower false positive rate compared to standard FCM when validated against human expert decisions.
  • Improved performance was noted for small ganglion cysts, where ultrasound image quality is often suboptimal.

Conclusions:

  • The developed AI-based method offers a reliable and automatic approach for ganglion cyst segmentation from ultrasound images.
  • This technique mitigates operator subjectivity, enhancing diagnostic consistency and reliability.
  • The automated segmentation shows particular promise for challenging cases involving small or poorly visualized cysts.