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

Mechanism of Buzhong Yiqi decoction for Hashimoto's thyroiditis: insights from gut microbiota and metabolomics.

Journal of traditional Chinese medicine = Chung i tsa chih ying wen pan·2026
Same author

Anatomical structure of pulmonary vessels and bronchi in the right upper lobe based on three-dimensional reconstruction.

BMC surgery·2026
Same author

The impact of mixed exposure to PM<sub>2.5</sub> components before and during pregnancy on renal function in pregnant women.

Frontiers in public health·2026
Same author

Insights into the molecular basis of umami in premium green teas via integrated metabolomics, peptidomics, and in silico molecular docking.

Food chemistry·2026
Same author

Integrating multisequence radiomics and clinical features to predict seizure recurrence after gross total resection of pediatric low-grade epilepsy-associated brain tumors.

Neuroradiology·2026
Same author

Association between PFAS and renal function indicators in cord blood of newborns: modifying effects of newborn sex and maternal factors.

Annals of medicine·2026

Related Experiment Video

Updated: Sep 26, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

533

Multi-scale organs image segmentation method improved by squeeze-and-attention based on partially supervised

Mao Hongdong1, Cao Guogang2, Zhang Shu1

  • 1School of Computer Science and Information Engineering, Shanghai Institute of Technology, Shanghai, China.

International Journal of Computer Assisted Radiology and Surgery
|April 25, 2022
PubMed
Summary

This study introduces an automated 3D U-Net model for precise segmentation of organs at risk (OARs) in head and neck radiotherapy. The method enhances accuracy and significantly reduces processing time, making it suitable for clinical applications.

Keywords:
Image segmentationMulti-scale organsPartially supervised learningSqueeze-and-attention

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

3.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

659

Related Experiment Videos

Last Updated: Sep 26, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

533
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: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

659

Area of Science:

  • Medical Imaging
  • Radiotherapy
  • Artificial Intelligence

Background:

  • Accurate delineation of organs at risk (OARs) is crucial for effective radiotherapy, minimizing damage to healthy tissues.
  • Manual and traditional segmentation methods are time-consuming and labor-intensive, necessitating faster, more precise automated solutions.

Purpose of the Study:

  • To develop a fully automatic segmentation method for multi-organ delineation in head and neck radiotherapy.
  • To improve the speed and accuracy of OAR segmentation compared to existing methods.

Main Methods:

  • A 3D U-Net architecture incorporating squeeze-and-attention blocks for multi-scale context and receptive field blocks for balanced performance.
  • Partially supervised learning utilizing a marginal and exclusion loss function.

Main Results:

  • Achieved an average Dice Similarity Coefficient (DSC) of 0.829, outperforming AnatomyNet, nnU-net, and FocusNet.
  • Demonstrated a 95% Hausdorff distance (95HD) of 2.19.
  • Reduced inference time by 63% and parameter count by 60% compared to FocusNetv2.

Conclusions:

  • The proposed model offers superior accuracy and speed for head and neck OAR segmentation.
  • It provides a better balance between segmentation accuracy and inference time, enhancing clinical applicability.