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

DRI-Net: segmentation of polyp in colonoscopy images using dense residual-inception network.

Frontiers in physiology·2023
Same author

Decoding the microbiome: advances in genetic manipulation for gut bacteria.

Trends in microbiology·2023
Same author

Tumor-produced and aging-associated oncometabolite methylmalonic acid promotes cancer-associated fibroblast activation to drive metastatic progression.

Nature communications·2022
Same author

Bioinformatics-guided connection of a biosynthetic gene cluster to the antitumor antibiotic gilvusmycin.

Acta biochimica et biophysica Sinica·2018

Related Experiment Video

Updated: Jun 10, 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

2.7K

Multi-scale input layers and dense decoder aggregation network for COVID-19 lesion segmentation from CT scans.

Xiaoke Lan1, Wenbing Jin2

  • 1College of Internet of Things Technology, Hangzhou Polytechnic, Hangzhou, 311402, China. lxk@mail.hzpt.edu.cn.

Scientific Reports
|October 10, 2024
PubMed
Summary

A new deep learning model, MD-Net, accurately segments COVID-19 lesions in CT scans. This advanced network improves diagnostic precision by effectively analyzing complex image details and enhancing lesion identification.

Keywords:
COVID-19Dense decoder aggregationMulti-scale input layersSE-ConvSegmentationU-Net

More Related Videos

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.1K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

376

Related Experiment Videos

Last Updated: Jun 10, 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

2.7K
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.1K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

376

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Accurate segmentation of COVID-19 lesions in medical images is crucial for diagnosis and treatment.
  • Challenges include complex lesion characteristics, subtle tissue differences, and image noise in CT scans.

Purpose of the Study:

  • To design a novel deep learning architecture, MD-Net, for precise COVID-19 lesion segmentation.
  • To improve segmentation accuracy by addressing the complexities of medical image analysis.

Main Methods:

  • Developed MD-Net, a U-shaped deep learning network featuring multi-scale input layers (MIL) and a dense decoder aggregation (DDA) module.
  • Incorporated an SE-Conv module in the encoder for enhanced feature identification and noise suppression.

Main Results:

  • MD-Net demonstrated superior performance in segmenting COVID-19 lesions on Vid-QU-EX and QaTa-COV19-v2 datasets.
  • Achieved higher scores for Dice value, Matthews correlation coefficient (Mcc), and Jaccard index compared to existing methods.

Conclusions:

  • MD-Net offers a robust and versatile solution for COVID-19 lesion segmentation.
  • The proposed architecture effectively handles complex image features, leading to improved diagnostic accuracy.