Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Cobaloxime-catalysed regiodivergent hydrogen atom transfer for alkenyl and allylic carbamoylation with branched alkenes.

Nature communications·2026

Same author

Effects of local heat on metabolic health, frailty risk, and exercise adaptations in pre-diabetic older adults: Protocol for the Heat and Exercise in Aging as Therapy (HEAT) clinical trial.

PloS one·2026

Same author

Sensitive Spectral and Temporal-Spatial Characteristic Analysis of Leaf SPAD in Maize Under Variety and Nitrogen Coupling Effects.

Food science & nutrition·2026

Same author

A preclinical investigation into the potential associations of geraniin with ulcerative colitis alleviation through integrated multi-omics and <i>in vivo</i> analysis.

Frontiers in medicine·2026

Same author

Incidence and risk factors of vaccination hesitancy among early-stage lung cancer patients: a cross-sectional study.

Journal of thoracic disease·2026

Same author

Synergistic engineering of a GRAS-certified strain: Transforming Bacillus subtilis 168 into a high-performance nicotine scavenger.

Journal of hazardous materials·2026

Same journal

Rapid personalisation of cardiovascular models using invasively measured right ventricular pressure.

Computers in biology and medicine·2026

Same journal

Biologically inspired mechanisms for enhancing robustness in EEG signal modeling: Challenges, opportunities, and perspectives.

Computers in biology and medicine·2026

Same journal

Machine learning-based detection of missed inspiratory efforts using esophageal pressure during noisy pressure support ventilation.

Computers in biology and medicine·2026

Same journal

A computational model of chemically- and mechanically-induced thrombus formation in cerebral aneurysms.

Computers in biology and medicine·2026

Same journal

An improved catch fish optimization based deep learning model for Parkinson disease classification using EEG signal.

Computers in biology and medicine·2026

Same journal

Assessing the robustness of evaluation metrics for synthetic ECG signal quality.

Computers in biology and medicine·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 25, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

HSNet: A hybrid semantic network for polyp segmentation.

Wenchao Zhang¹, Chong Fu², Yu Zheng³

¹School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China.

Computers in Biology and Medicine

|October 18, 2022

Summary

This summary is machine-generated.

This study introduces a hybrid semantic network (HSNet) for improved automatic polyp segmentation in colonoscopy images. The novel HSNet effectively addresses challenges like varying polyp appearance and detail loss, enhancing diagnostic accuracy.

Keywords:

Dual-branch Hybrid semantic Local details Long-range dependencies Polyp segmentation

More Related Videos

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

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

Published on: April 14, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Aug 25, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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

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

Published on: April 14, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Medical Imaging
Computer Vision
Artificial Intelligence

Background:

Automatic polyp segmentation aids physicians in identifying polyps during colonoscopies.
Existing methods struggle with polyp variations (scale, illumination) and overlook fine details, impacting accuracy.
Decoder-encoder networks often miss crucial appearance details for small polyps.

Purpose of the Study:

To develop an improved automatic polyp segmentation method using a hybrid semantic network (HSNet).
To address limitations in current segmentation techniques, specifically concerning polyp variability and detail preservation.
To enhance the accuracy and reliability of polyp detection in colonoscopy images.

Main Methods:

Proposed a hybrid semantic network (HSNet) integrating Transformer and Convolutional Neural Network (CNN) advantages.
Introduced a cross-semantic attention (CSA) module to bridge low-level and high-level features.
Designed a hybrid semantic complementary (HSC) module for capturing long-range dependencies and local details.
Implemented a multi-scale prediction (MSP) module for fusing decoder prediction masks.

Main Results:

HSNet demonstrated superior performance compared to 10 state-of-the-art methods across 5 benchmark datasets.
Achieved high accuracy metrics, including 0.926/0.877 mDic/mIoU on Kvasir-SEG and 0.948/0.905 mDic/mIoU on ClinicDB.
Significantly improved segmentation accuracy by effectively handling polyp appearance variations and preserving fine details.

Conclusions:

The proposed HSNet effectively overcomes key challenges in automatic polyp segmentation.
The hybrid approach combining Transformer and CNN architectures offers enhanced feature representation.
HSNet shows significant potential for improving polyp detection in clinical colonoscopy screening.