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

Generative morphodynamic forecasting enables robust zero-shot volumetric medical segmentation.

Medical image analysis·2026
Same author

Glucans from <i>Lentinus edodes</i> Inhibit Myeloid-Derived Suppressor Cell-Induced Regulatory T Cells via the TLR4-TAK1-JNK Signaling Pathway to Scavenge Reactive Oxygen Species.

Journal of agricultural and food chemistry·2026
Same author

Trichoderma modulates Pseudomonas metabolism: Co-inoculation enhances phosphorus acquisition of Pyrus betulifolia in calcareous soil.

Microbiological research·2026
Same author

Modelling the structural evolution, electronic structures and optical properties of Sc<sub>6</sub>Se<sub>n</sub><sup>0/-</sup> (n = 1-12) clusters.

Communications chemistry·2026
Same author

Bidirectional association between edentulism and sarcopenia in Chinese middle-aged and older adults: a nationally representative longitudinal cohort study.

Clinical oral investigations·2026
Same author

AN AUTOMATED CHEMILUMINESCENCE IMMUNOASSAY FOR DETECTION OF GIARDIA DUODENALIS ANTIGENS FROM CANINE SPECIMENS.

The Journal of parasitology·2026

Related Experiment Video

Updated: Oct 12, 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

3.0K

Ms RED: A novel multi-scale residual encoding and decoding network for skin lesion segmentation.

Duwei Dai1, Caixia Dong1, Songhua Xu1

  • 1Institute of Medical Artificial Intelligence, the Second Affiliated Hospital of Xi'an Jiaotong University, Xi'an, 710061, China.

Medical Image Analysis
|November 20, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a new deep learning model, the Multi-scale Residual Encoding and Decoding network (Ms RED), for improved skin lesion segmentation in dermoscopic images. The Ms RED model achieves superior accuracy and efficiency, requiring fewer parameters and less training data for better results.

Keywords:
Feature fusionMulti-scaleResidual encoding/decodingSkin lesion segmentationSoft-pool

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

682
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

2.7K

Related Experiment Videos

Last Updated: Oct 12, 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

3.0K
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

682
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

2.7K

Area of Science:

  • Medical image analysis
  • Deep learning for computer-aided diagnosis
  • Dermatology

Background:

  • Accurate skin lesion segmentation is crucial for computer-aided diagnosis (CAD) of dermatological diseases.
  • Current deep learning models struggle with challenging cases like irregular shapes, low contrast, or blurry boundaries.
  • There is a need for more robust and efficient segmentation methods in dermatoscopic imaging.

Purpose of the Study:

  • To propose a novel Multi-scale Residual Encoding and Decoding network (Ms RED) for accurate and efficient skin lesion segmentation.
  • To enhance feature representation and fusion using novel modules for improved segmentation performance.
  • To validate the proposed Ms RED model against state-of-the-art methods on benchmark datasets.

Main Methods:

  • Developed a novel Multi-scale Residual Encoding and Decoding network (Ms RED).
  • Incorporated multi-scale residual encoding and decoding fusion modules (MsR-EFM and MsR-DFM) for adaptive feature fusion.
  • Introduced a multi-resolution, multi-channel feature fusion module (M²F²) and a novel Soft-pool module for enhanced representation learning and down-sampling.
  • Evaluated the model on ISIC 2016, 2017, 2018, and PH² datasets.

Main Results:

  • The proposed Ms RED model demonstrated significantly superior segmentation performance across five evaluation criteria compared to state-of-the-art methods.
  • The model achieved high accuracy in segmenting challenging skin lesions.
  • Ms RED requires fewer model parameters, reducing the need for labeled samples and leading to faster training convergence.

Conclusions:

  • The Ms RED network offers a highly effective and efficient solution for skin lesion segmentation in dermoscopic images.
  • The novel modules (MsR-EFM, MsR-DFM, M²F², Soft-pool) contribute to improved accuracy and robustness.
  • The model's efficiency in terms of parameters and training time makes it a promising tool for clinical applications.