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 3, 2026

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

3.6K

Learning a structured graphical model with boosted top-down features for ultrasound image segmentation.

Zhihui Hao1, Qiang Wang1, Xiaotao Wang1

  • 1Medical Imaging Group, China Lab.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|February 8, 2014
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

What affects natural killer cell activity: a cross-sectional study.

Frontiers in immunology·2026
Same author

Association Between Complete Blood Cell Count (CBC)-Derived Inflammatory Markers and Natural Killer Cell Activity: A Cross-Sectional Study.

Journal of inflammation research·2026
Same author

Exploring Age-Related Patterns in Smartphone Keystroke Dynamics Considering Temporal Variability: Cross-Sectional Study With AI-Based Analysis.

JMIR mHealth and uHealth·2025
Same author

Immune-enhanced machine learning approach for early detection of precancerous colorectal neoplasia: Insights from biomarkers in routine health checkups.

European journal of cancer (Oxford, England : 1990)·2025
Same author

Association between resting heart rate and low natural killer cell activity: a cross-sectional study.

Frontiers in immunology·2024
Same author

Application of Deep Neural Networks in the Manufacturing Process of Mesenchymal Stem Cells Therapeutics.

International journal of stem cells·2024

This study introduces a new method for segmenting medical images, effectively combining different data levels for improved ultrasound lesion detection. The approach leverages superpixel graphical models and structured learning for enhanced accuracy.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Machine Learning

Background:

  • Combining diverse knowledge levels is challenging for medical image segmentation.
  • Ultrasound lesion segmentation requires integrating various image cues.

Purpose of the Study:

  • To propose a novel scheme for embedding detected regions into a superpixel-based graphical model.
  • To achieve full leverage of various image cues for ultrasound lesion segmentation.

Main Methods:

  • Embedding detected regions into a superpixel-based graphical model.
  • Mapping region features into a higher-dimensional space via a boosted model.
  • Simultaneously learning parameters for regions, superpixels, and a new affinity term using structured learning.

More Related Videos

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

335

Related Experiment Videos

Last Updated: May 3, 2026

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

3.6K
Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

335

Main Results:

  • The proposed approach effectively segments ultrasound lesions.
  • Demonstrated effectiveness on a breast ultrasound image dataset.
  • Validated the efficacy of two novel modules within the framework.

Conclusions:

  • The novel scheme successfully integrates different-level knowledge for medical image segmentation.
  • The method provides a robust solution for ultrasound lesion segmentation.
  • The structured learning framework enables simultaneous parameter optimization.