Search research articles

Related Concept Videos

Protein Networks

Protein Networks

An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Reliability of the In Silico Prediction Approach to In Vitro Evaluation of Bacterial Toxicity.

Sensors (Basel, Switzerland)·2022

Same author

Protective Effect of Polymethoxyflavones Isolated from <i>Kaempferia parviflora</i> against TNF-α-Induced Human Dermal Fibroblast Damage.

Antioxidants (Basel, Switzerland)·2021

Same author

Generalized Parking Occupancy Analysis Based on Dilated Convolutional Neural Network.

Sensors (Basel, Switzerland)·2019

Same author

Robust Powerline Equipment Inspection System Based on a Convolutional Neural Network.

Sensors (Basel, Switzerland)·2018

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 25, 2026

Automated Image-Based Quantification of Neutrophil Extracellular Traps Using NETQUANT

Automated Image-Based Quantification of Neutrophil Extracellular Traps Using NETQUANT

Published on: November 27, 2019

MMNet: A Mixing Module Network for Polyp Segmentation.

Raman Ghimire¹, Sang-Woong Lee²

¹Pattern Recognition and Machine Learning Lab, Department of IT Convergence Engineering, Gachon University, Seongnam 13557, Republic of Korea.

Sensors (Basel, Switzerland)

|August 26, 2023

Summary

This study introduces a hybrid transformer and convolutional mixing network (MMNet) for improved polyp segmentation. MMNet effectively captures long-range dependencies while reducing computational costs, outperforming existing methods.

Keywords:

computational complexity depth-wise and 1 × 1 convolution mixing module polyp segmentation transformer

More Related Videos

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Jun 25, 2026

Automated Image-Based Quantification of Neutrophil Extracellular Traps Using NETQUANT

Automated Image-Based Quantification of Neutrophil Extracellular Traps Using NETQUANT

Published on: November 27, 2019

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Medical Image Analysis
Computer Vision
Artificial Intelligence

Background:

Traditional encoder-decoder networks (e.g., U-Net) struggle with long-range dependencies in polyp segmentation, prioritizing local patterns over global context.
Transformer networks excel at capturing long-range dependencies via self-attention but face computational challenges due to quadratic complexity with image size.
Existing transformer approaches lack inductive bias, hindering generalization to local contexts due to limited low-level feature extraction.

Purpose of the Study:

To develop a novel hybrid network that addresses the limitations of existing methods for polyp segmentation.
To improve the modeling of long-range dependencies while mitigating computational costs associated with transformer architectures.
To enhance the generalization capabilities of segmentation models by integrating convolutional inductive biases.

Main Methods:

Introduced a hybrid transformer combined with a convolutional mixing network (MMNet).
Utilized a pretrained transformer as a feature-extracting encoder.
Developed a mixing module network (MMNet) employing depth-wise and 1x1 convolutions for efficient long-range dependency modeling (spatial and cross-channel correlations).

Main Results:

The proposed MMNet effectively captures long-range dependencies with reduced computational overhead.
Qualitative and quantitative evaluations on five polyp datasets demonstrated superior performance.
MMNet outperformed previous state-of-the-art polyp segmentation methods across six metrics.

Conclusions:

The hybrid MMNet architecture offers an effective solution for polyp segmentation, balancing long-range dependency modeling with computational efficiency.
This approach overcomes the limitations of purely convolutional or transformer-based methods.
MMNet represents a significant advancement in automated polyp segmentation for medical imaging applications.