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

Short term complications and risk factors of unilateral biportal endoscopic cervical spine surgery in patients with cervical radiculopathy and myelopathy: a single center retrospective study.

Frontiers in medicine·2026
Same author

Dynamic evolution of higher alcohols from CO<sub>2</sub> on Fe<sub>3</sub>O<sub>4</sub>-Fe<sub>5</sub>C<sub>2</sub>-Cu catalytic interfaces with amorphous Ti layout.

Nature communications·2026
Same author

Acupuncture and Moxibustion Therapy Attenuates Inflammation in CCI-Induced Sciatica by Inhibiting the NF-κB Pathway.

Journal of pharmacopuncture·2026
Same author

Advance Care Planning Documentation Completeness and End-of-Life Care: Trends and Associations Using HRS 2010-2022 Data.

The American journal of hospice & palliative care·2026
Same author

First molecular evidence of Rickettsia spp. in Triatoma rubrofasciata: implications for vector ecology and zoonotic transmission.

Parasites & vectors·2026
Same author

Awareness and misconceptions of palliative care among paid, unpaid, and non-caregivers in the U.S.

BMC palliative care·2026

Related Experiment Video

Updated: Mar 29, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

861

Waveformer: Dual-Branch Adaptive Network with Wavelet-Guided Cross-Context Decoding for Colorectal Polyp

Liming Liang, Ting Kang, Yulin Li

    IEEE Journal of Biomedical and Health Informatics
    |March 27, 2026
    PubMed
    Summary

    Waveformer, a novel deep learning network, enhances polyp segmentation in endoscopic images by combining local and global feature extraction. This approach improves accuracy in challenging conditions, outperforming existing methods.

    More Related Videos

    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

    3.4K
    Automated Analysis of C. elegans Fluorescence Images using SegElegans
    06:27

    Automated Analysis of C. elegans Fluorescence Images using SegElegans

    Published on: October 10, 2025

    760

    Related Experiment Videos

    Last Updated: Mar 29, 2026

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    861
    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

    3.4K
    Automated Analysis of C. elegans Fluorescence Images using SegElegans
    06:27

    Automated Analysis of C. elegans Fluorescence Images using SegElegans

    Published on: October 10, 2025

    760

    Area of Science:

    • Medical Imaging
    • Computer Vision
    • Artificial Intelligence

    Background:

    • Deep learning has advanced polyp segmentation in endoscopic images.
    • Clinical polyps present challenges like variable morphology, blurred boundaries, low contrast, and poor lighting, leading to misdetections.

    Purpose of the Study:

    • To introduce Waveformer, a local-global co-modeling network, for improved polyp segmentation accuracy.
    • To address limitations in current computer-aided diagnosis systems for endoscopic imaging.

    Main Methods:

    • The proposed Waveformer network utilizes parallel CNN-Transformer branches in its encoder for synergistic feature extraction.
    • The decoder incorporates a wavelet-based frequency decomposition unit (WFDU), a camouflage identification module (CIM), and an information fusion layer (IFL).

    Main Results:

    • Waveformer achieved Dice Similarity Coefficients (DSC) of 95.60% on CVC-ClinicDB and 94.11% on Kvasir-SEG.
    • The model outperformed fourteen state-of-the-art methods in polyp segmentation.
    • Cross-dataset evaluations demonstrated strong generalization with DSC scores of 81.0% and 79.2%.

    Conclusions:

    • Waveformer significantly improves polyp segmentation accuracy and boundary delineation in endoscopic images.
    • The network's local-global co-modeling and specialized decoder modules enhance performance in complex clinical scenarios.
    • Waveformer shows robust generalization capabilities across different datasets.