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 31, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

364

Dynamic spectrum-driven hierarchical learning network for polyp segmentation.

Haolin Wang1, Kai-Ni Wang1, Jie Hua2

  • 1School of Biological Science and Medical Engineering, Southeast University, Nanjing, China; Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing, China.

Medical Image Analysis
|January 23, 2025
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

Effects of Hydrogen-Rich Water on Juvenile Largemouth Bass (<i>Micropterus salmoides</i>) Under Acute Low-Temperature Stress.

Antioxidants (Basel, Switzerland)·2026
Same author

Cell-type and spatiotemporal transcriptional signatures of white matter morphometric similarity network alterations in major depressive disorder.

Psychological medicine·2026
Same author

Association between birth memory and postpartum psychological distress: The mediating role of sleep quality.

Midwifery·2026
Same author

DSTED: decoupling temporal stabilization and discriminative enhancement for surgical workflow recognition.

International journal of computer assisted radiology and surgery·2026
Same author

Tracking of volatile organic compound emissions from unsaturated polyester resin-based artificial stone using automated static headspace-gas chromatography-mass spectrometry.

Journal of chromatography. A·2026
Same author

A Topology-Enhanced Dual-stream Attention Model for Parasternal Long-Axis View Identification in Echocardiography.

IEEE journal of biomedical and health informatics·2026
Same journal

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026
Same journal

MedP-CLIP: Medical CLIP with region-aware prompt integration.

Medical image analysis·2026
Same journal

Multi-organ guided diagnosis of mild cognitive impairment via hierarchical alignment and knowledge distillation.

Medical image analysis·2026
Same journal

SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis.

Medical image analysis·2026
Same journal

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026
Same journal

Annotation-efficient medical image segmentation via cross-latent graphs and vector-quantized memory.

Medical image analysis·2026
See all related articles
This summary is machine-generated.

This study introduces a new dynamic spectrum-driven hierarchical learning model (DSHNet) for precise polyp segmentation in colonoscopy. The model effectively handles polyp variations and lighting conditions, improving colorectal cancer prevention.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Accurate polyp segmentation is vital for colorectal cancer prevention.
  • Challenges include polyp heterogeneity and varying illumination/visibility conditions.
  • Existing methods struggle with consistent segmentation across diverse cases.

Purpose of the Study:

  • To propose a novel dynamic spectrum-driven hierarchical learning model (DSHNet) for precise automatic polyp segmentation.
  • To leverage image frequency domain information for enhanced region-level salience analysis.
  • To address challenges posed by polyp heterogeneity and illumination variations.

Main Methods:

  • Developed a novel spectral decoupler to separate low-frequency and high-frequency image components.
Keywords:
Dynamic ConvolutionFrequency LearningPolyp SegmentationRegion-level Saliency Modeling

More Related Videos

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

456
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K

Related Experiment Videos

Last Updated: May 31, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

364
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

456
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K
  • Implemented low-frequency driven region-level saliency modeling with dynamic convolution kernels.
  • Integrated a high-frequency attention module to preserve detailed spatial information.
  • Utilized a hierarchy of labels for supervision to adapt to variations.

    • Main Results:

    • The proposed DSHNet model achieved superior performance compared to state-of-the-art polyp segmentation methods.
    • Demonstrated robust and accurate segmentation results across five diverse datasets.
    • Effectively adapted to polyp heterogeneity and illumination variations simultaneously.

    Conclusions:

    • DSHNet is the first model to utilize frequency domain information for polyp segmentation.
    • The model's dynamic spectrum-driven hierarchical approach enhances segmentation accuracy and robustness.
    • This advancement contributes to more reliable polyp detection and improved colorectal cancer screening.