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

Accurate Protein-Protein Interaction Prediction: Based on Multiview Heterogeneous Graph Autoencoders and Random Masking.

IEEE transactions on neural networks and learning systems·2025
Same author

Pre-trained language models for protein and molecular design.

Physical chemistry chemical physics : PCCP·2025
Same author

Multi-objective drug design with a scaffold-aware variational autoencoder.

Chemical science·2025
Same author

A framework reforming personalized Internet of Things by federated meta-learning.

Nature communications·2025
Same author

Meta-MolNet: A Cross-Domain Benchmark for Few Examples Drug Discovery.

IEEE transactions on neural networks and learning systems·2025
Same author

Dual modality feature fused neural network integrating binding site information for drug target affinity prediction.

NPJ digital medicine·2025

Related Experiment Video

Updated: Jul 9, 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

2.8K

LDCNet: Lightweight dynamic convolution network for laparoscopic procedures image segmentation.

Yiyang Yin1, Shuangling Luo2, Jun Zhou1

  • 1Artificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, 518107, Guangdong, China.

Neural Networks : the Official Journal of the International Neural Network Society
|December 1, 2023
PubMed
Summary
This summary is machine-generated.

A new lightweight dynamic convolution network (LDCNet) achieves state-of-the-art medical image segmentation performance for Transanal Total Mesorectal Excision (TaTME) procedures. This innovation offers high accuracy with efficient computational speed, aiding surgical planning and reducing risks.

Keywords:
AttentionColonoscopyDeep learningLightweight networkMedical image segmentation

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

8.8K
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

3.8K

Related Experiment Videos

Last Updated: Jul 9, 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

2.8K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

3.8K

Area of Science:

  • Medical Imaging and Computer-Aided Diagnosis
  • Surgical Technology and Robotics
  • Artificial Intelligence in Healthcare

Background:

  • Medical image segmentation is crucial for surgical risk reduction and treatment planning in healthcare.
  • Transanal Total Mesorectal Excision (TaTME) is a key laparoscopic technique for colorectal cancer treatment.
  • Real-time instance segmentation of surgical images during TaTME can significantly assist surgeons.

Purpose of the Study:

  • To address the challenges of accurate and computationally efficient instance segmentation in TaTME images.
  • To develop a deep learning model that matches state-of-the-art (SOTA) segmentation performance with lightweight complexity.
  • To introduce the Lightweight Dynamic Convolution Network (LDCNet) for enhanced intraoperative surgical assistance.

Main Methods:

  • Proposed a novel Lightweight Dynamic Convolution Network (LDCNet) architecture.
  • Focused on achieving high accuracy in medical image segmentation for TaTME procedures.
  • Emphasized maintaining manageable computational complexity for real-time applications.

Main Results:

  • LDCNet demonstrated superior segmentation performance compared to existing SOTA medical image segmentation networks.
  • The proposed network achieved segmentation accuracy comparable to SOTA models while operating at high speeds.
  • Experimental results confirmed the promising performance and efficiency of LDCNet on TaTME data.

Conclusions:

  • LDCNet effectively overcomes the limitations of current models in segmenting TaTME images.
  • The network provides a viable solution for real-time surgical assistance, enhancing safety and precision in TaTME.
  • The developed model offers a balance of high segmentation accuracy and computational efficiency for clinical application.