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

Gegen Qinlian Decoction Mitigates DSS-Induced Acute Colitis and Reinstates Gut Barrier Function in Mice, Correlating with Suppressed IL-33/ST2 Signaling.

Journal of inflammation research·2026
Same author

Biological characterization of Candida parapsilosis haploids induced by voriconazole.

International journal of antimicrobial agents·2026
Same author

Identification of key substances and mechanisms of action for the pleasurable aroma of Shaoxing Huangjiu based on GC-MS, molecular docking, and sensory evaluation.

Food chemistry·2026
Same author

Benzo[a]pyrene carcinogenicity across organs and cancer stages: Molecular mechanisms and interactions with co-exposed chemicals.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Lichang decoction suppresses AOM+DSS-induced colitis-associated cancer via regulating intestinal flora and suppressing the Wnt/β-catenin signaling pathway.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Hypertension management profiles in Chinese adults aged 60 years and older.

Frontiers in public health·2026

Related Experiment Video

Updated: Dec 17, 2025

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

3.2K

ADR-Net: Context extraction network based on M-Net for medical image segmentation.

Lingyu Ji1, Xiaoyan Jiang1, Yongbin Gao1

  • 1School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, 201620, China.

Medical Physics
|July 1, 2020
PubMed
Summary

This study introduces a novel network architecture for enhanced medical image segmentation, particularly for small targets. The new model significantly improves segmentation accuracy and outperforms existing methods.

Keywords:
attention gate mechanismdeep Learningdilation convolutionmedical image segmentationresidualspatial pyramid pooling

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

3.0K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

690

Related Experiment Videos

Last Updated: Dec 17, 2025

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

3.2K
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

3.0K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

690

Area of Science:

  • Medical Image Analysis
  • Deep Learning for Medical Imaging
  • Computer-Aided Diagnosis

Background:

  • Medical image segmentation is crucial for diagnosis and reducing physician fatigue.
  • Existing U-Net based methods show limitations in segmenting small medical objects.
  • There is a need for improved segmentation techniques for small targets.

Purpose of the Study:

  • To propose a novel network architecture for enhanced medical image segmentation.
  • To specifically address the challenge of segmenting small-sized objects in medical images.
  • To improve the accuracy and reliability of medical image analysis.

Main Methods:

  • A joint multi-scale context attention network is proposed.
  • The architecture incorporates dense atrous convolution (DAC) and multi-scale residual pyramid pooling (RMP) modules.
  • Attention gate (AG) blocks are utilized to focus on relevant regions and suppress irrelevant ones.

Main Results:

  • The proposed model significantly outperforms the basic U-Net framework on the DRIVE dataset.
  • Sensitivity (SE) and Intersection-over-Union (IOU) improved by 7.46% and 5.97% respectively.
  • The model demonstrated superior performance compared to state-of-the-art methods across multiple challenging datasets, showing generalizability and transferability.

Conclusions:

  • The novel network architecture effectively enhances medical image segmentation for small targets.
  • Experimental results confirm the proposed model's superiority over existing state-of-the-art methods.
  • The approach shows promise for improving diagnostic accuracy in medical imaging.