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

Probing Blended-Additive-Regulated Interface Chemistry Based on a Dynamic Competition Mechanism in Lithium Metal Batteries.

Angewandte Chemie (International ed. in English)·2026
Same author

Shexiang Tongxin dropping pill for coronary microvascular disease: rationale and design of a multicenter randomized trial with a cardiopulmonary exercise testing primary endpoint and AI-enhanced myocardial contrast echocardiograph.

Frontiers in cardiovascular medicine·2026
Same author

[Research progress on the mechanism of acupuncture intervention for depression based on oxidative stress].

Zhen ci yan jiu = Acupuncture research·2026
Same author

Integrating <i>In silico</i> perturbation with multilayer omics to decode regulatory networks in cancer immunity: a new frontier in precision oncology.

Frontiers in immunology·2026
Same author

DCPM-ADMET: fusion of dual-component pre-trained model and molecular fingerprints to enhance drug ADMET properties prediction.

Journal of cheminformatics·2026
Same author

Duodenal ulcer perforation presenting as acute appendicitis in a child: a case report and literature review.

Frontiers in surgery·2026

Related Experiment Video

Updated: Apr 4, 2026

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

2.4K

Contrast-Enhanced VM-UNet for Thyroid Nodule Segmentation Based on Wavelet Features and Dual-Branch Edge Learning.

Luoning Bao1, Lu Liang2, Qiongzhu Liu3

  • 1Department of Ultrasonography, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, Guangdong, China.

Journal of Imaging Informatics in Medicine
|April 2, 2026
PubMed
Summary

This study introduces an improved AI model for segmenting thyroid nodules in ultrasound images. The novel approach enhances accuracy by better capturing nodule edges and distinguishing them from surrounding tissue, aiding clinical diagnosis.

Keywords:
Contrastive learningDeep learningDual-branch networkImage segmentationThyroid nodulesWavelet transform

More Related Videos

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
05:41

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

1.2K
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

3.7K

Related Experiment Videos

Last Updated: Apr 4, 2026

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

2.4K
Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis
05:41

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

1.2K
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

3.7K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Accurate thyroid nodule segmentation from ultrasound images is crucial for diagnosis and treatment.
  • Manual segmentation is time-consuming and prone to variability.
  • Existing AI models struggle with capturing fine edge details and differentiating nodule regions.

Purpose of the Study:

  • To develop an advanced AI model for precise thyroid nodule segmentation.
  • To overcome limitations of current models in edge detail and region discrimination.
  • To improve the clinical utility of automated thyroid nodule analysis.

Main Methods:

  • Proposed a contrast-enhanced VM-UNet model for thyroid nodule segmentation.
  • Integrated wavelet transform for frequency-domain feature extraction.
  • Implemented a dual-branch structure (full and edge masks) and contrastive loss for enhanced feature learning.

Main Results:

  • Achieved a Dice Similarity Coefficient (DSC) of 93.61% and mIoU of 88.56% on the TN3k dataset.
  • Demonstrated high performance on an external dataset (DSC 92.87%), outperforming baseline VM-UNet.
  • The combined techniques significantly improved segmentation accuracy and robustness.

Conclusions:

  • The proposed contrast-enhanced VM-UNet offers a robust solution for accurate thyroid nodule segmentation.
  • The integration of wavelet transform, dual-branch edge learning, and contrastive loss enhances clinical applicability.
  • This method supports more reliable clinical decision-making in thyroid cancer diagnosis.