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

Roles of miR-200 family members in lung cancer: more than tumor suppressors.

Future oncology (London, England)·2018
Same author

Alterations and structural resilience of the gut microbiota under dietary fat perturbations.

The Journal of nutritional biochemistry·2018
Same author

Development and Feasibility Testing of an mHealth (Text Message and WeChat) Intervention to Improve the Medication Adherence and Quality of Life of People Living with HIV in China: Pilot Randomized Controlled Trial.

JMIR mHealth and uHealth·2018
Same author

Meta-Analysis of Preclinical Studies of Fibrinolytic Therapy for Acute Lung Injury.

Frontiers in immunology·2018
Same author

Corrigendum to: The calcium sensor TaCBL4 and its interacting protein TaCIPK5 are required for wheat resistance to stripe rust fungus.

Journal of experimental botany·2018
Same author

Transcriptome analysis of Valsa mali reveals its response mechanism to the biocontrol actinomycete Saccharothrix yanglingensis Hhs.015.

BMC microbiology·2018

Related Experiment Video

Updated: Dec 15, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

688

Fully multi-target segmentation for breast ultrasound image based on fully convolutional network.

Yingtao Zhang1, Yan Liu2, Hengda Cheng3

  • 1School of Computer Science and Technology, Harbin Institute of Technology, No. 92, Xidazhi Street, Harbin, 150001, China.

Medical & Biological Engineering & Computing
|July 9, 2020
PubMed
Summary

This study introduces a novel multi-target semantic segmentation method for breast ultrasound images. The approach accurately segments various tissue regions, improving computer-aided diagnosis for breast cancer detection.

Keywords:
Breast ultrasound imageFully convolutional networkSegmentation

More Related Videos

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

3.2K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.2K

Related Experiment Videos

Last Updated: Dec 15, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

688
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

3.2K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.2K

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Biomedical Engineering

Background:

  • Ultrasound image segmentation is crucial for breast cancer diagnosis.
  • Current methods primarily focus on tumor tissue, neglecting valuable reference information from other tissues.
  • Accurate segmentation of diverse tissue regions is essential for comprehensive analysis.

Purpose of the Study:

  • To propose a multi-target semantic segmentation approach for breast ultrasound images using a fully convolutional network.
  • To enhance the segmentation accuracy by addressing challenges like blurry boundaries and improving image detail representation.
  • To optimize network training efficiency for practical application in computer-aided diagnosis.

Main Methods:

  • A multi-target semantic segmentation approach based on a fully convolutional network (FCN).
  • Transformation of AlexNet pixel characteristics into fuzzy decision expressions to handle ambiguous boundaries.
  • Optimization of the FCN structure with a fully connected skip structure and a fully connected conditional random field (CRF) for improved spatial consistency.
  • Development of a data training optimization method to enhance network training efficiency.

Main Results:

  • The proposed method effectively segments breast ultrasound images into distinct target tissue regions.
  • Experimental validation using 325 ultrasound images and four error metrics demonstrated high accuracy and reliability.
  • The approach showed superior performance compared to existing methods in handling complex ultrasound image characteristics.

Conclusions:

  • The developed multi-target semantic segmentation approach is effective and reliable for breast ultrasound image analysis.
  • This method offers a significant advancement in computer-aided diagnosis for breast cancer, providing more comprehensive tissue characterization.
  • The optimized network structure and training methods contribute to improved segmentation accuracy and efficiency.