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

Ultrasound image segmentation using spectral clustering.

Neculai Archip1, Robert Rohling, Peter Cooperberg

  • 1Harvard Medical School, Brigham and Women's Hospital, Boston, MA 02115, USA. narchip@bwh.harvard.edu

Ultrasound in Medicine & Biology
|November 16, 2005
PubMed
Summary

This study investigates normalized cut (NCut) spectral clustering for automatic ultrasound image segmentation. Results show promise for NCut in segmenting simulated, abdominal, and fetal ultrasound images, warranting further research.

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

Deep transfer learning for detection of placenta-mediated diseases from ultrasound images.

Scientific reports·2026
Same author

Validation of Volumetric Multifrequency Shear Wave Vibro-Elastography With Matrix Array Transducer for the In Vivo Liver.

IEEE transactions on ultrasonics, ferroelectrics, and frequency control·2025
Same author

Development and validation of the placenta-QUS model for the detection of placenta-mediated diseases using quantitative ultrasound measurements: An Ex Vivo proof-of-concept study.

Placenta·2024
Same author

Shape estimation of flexible ultrasound arrays using spatial coherence: A preliminary study.

Ultrasonics·2023
Same author

Multi-Frequency 3D Shear Wave Absolute Vibro-Elastography (S-WAVE) System for the Prostate.

IEEE transactions on medical imaging·2023
Same author

Automatic measurement of kidney dimensions in two-dimensional ultrasonography is comparable to expert sonographers.

Journal of medical imaging (Bellingham, Wash.)·2023

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Signal Processing

Background:

  • Automatic ultrasound image segmentation is crucial for clinical applications but remains challenging.
  • Spectral clustering, particularly normalized cut (NCut), is a promising technique for image analysis.

Purpose of the Study:

  • To evaluate the suitability of the normalized cut (NCut) technique for segmenting ultrasound images.
  • To adapt the NCut algorithm for ultrasound image characteristics.

Main Methods:

  • The normalized cut (NCut) criterion was adapted for ultrasound image segmentation.
  • Segmentation was performed on simulated ultrasound images.
  • Tests were conducted on abdominal and fetal ultrasound images, comparing results to manual segmentation.

Related Experiment Videos

Main Results:

  • The adapted NCut technique demonstrated successful segmentation on simulated ultrasound images.
  • Segmentation results on abdominal and fetal ultrasound images showed good agreement with manual segmentation.

Conclusions:

  • The normalized cut (NCut) technique shows significant potential for automatic ultrasound image segmentation.
  • Further research is recommended to explore and refine NCut-based methods for clinical ultrasound applications.