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

MTPA_Unet: Multi-Scale Transformer-Position Attention Retinal Vessel Segmentation Network Joint Transformer and CNN.

Sensors (Basel, Switzerland)·2022
Same author

Gated Skip-Connection Network with Adaptive Upsampling for Retinal Vessel Segmentation.

Sensors (Basel, Switzerland)·2021
Same author

Effects of long non-coding RNA Opa-interacting protein 5 antisense RNA 1 on colon cancer cell resistance to oxaliplatin and its regulation of microRNA-137.

World journal of gastroenterology·2020
Same author

In-situ synthesis of calcium borate/cellulose acetate-laurate nanocomposite as efficient extreme pressure and anti-wear lubricant additives.

International journal of biological macromolecules·2020
Same author

Sirtuins family as a target in endothelial cell dysfunction: implications for vascular ageing.

Biogerontology·2020
Same author

Distinct optical and kinetic responses from E/Z isomers of caspase probes with aggregation-induced emission characteristics.

Journal of materials chemistry. B·2020

Related Experiment Video

Updated: Aug 28, 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

2.9K

Dermoscopic image segmentation based on Pyramid Residual Attention Module.

Yun Jiang1, Tongtong Cheng1, Jinkun Dong1

  • 1College of Computer Science and Engineering, Lanzhou, Gansu, China.

Plos One
|September 16, 2022
PubMed
Summary
This summary is machine-generated.

We developed a new deep learning model for segmenting dermoscopic images. This Pyramid Residual Attention Network (PRAN) improves skin lesion boundary detection, aiding computer-aided diagnosis.

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.2K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

485

Related Experiment Videos

Last Updated: Aug 28, 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

2.9K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.2K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

485

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Artificial Intelligence

Background:

  • Precise segmentation of dermoscopic images is crucial for computer-aided diagnosis in skin lesion management.
  • Existing methods face challenges in accurately segmenting blurred lesion boundaries.

Purpose of the Study:

  • To propose a novel stacked convolutional neural network with a Pyramid Residual Attention (PRA) module for enhanced dermoscopic image segmentation.
  • To improve the accuracy of skin lesion boundary detection in automated diagnostic systems.

Main Methods:

  • Developed a Pyramid Residual Attention (PRA) module integrating pyramid structures for multi-scale feature extraction, residual connections for training efficiency, and attention mechanisms for feature map screening.
  • Designed a three-level encoder-decoder architecture, the Pyramid Residual Attention Network (PRAN), utilizing the PRA module as its basic component.
  • Evaluated the PRAN model on the ISIC2017 and ISIC2018 dermoscopic image datasets.

Main Results:

  • The proposed PRA module effectively extracts multi-scale features and refines segmentation accuracy, especially for blurred lesion edges.
  • The stacked PRA modules within the PRAN architecture enhance segmentation capabilities for lesion regions.
  • PRAN achieved competitive segmentation performance compared to state-of-the-art deep learning models.

Conclusions:

  • The developed PRAN model demonstrates superior performance in dermoscopic image segmentation.
  • The novel PRA module contributes significantly to accurate boundary delineation, advancing computer-aided skin lesion diagnosis.