Search research articles

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

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

Assessing Intronic Variable Number Tandem Repeat (VNTR) Expansions of the HSF1 Gene in Essential Tremor Patients from Eastern China.

Movement disorders : official journal of the Movement Disorder Society·2026

Same author

Global Burden of Encephalitis from 1990 to 2021, Its Attributable Risk Factors, and Projections to 2045.

Neuroepidemiology·2026

Same author

Microbiome preterm birth DREAM challenge: Crowdsourcing machine learning approaches to advance preterm birth research.

Cell reports. Medicine·2025

Same author

Bioinformatic screen with clinical validation for the identification of novel stool based mRNA biomarkers for the detection of colorectal lesions including advanced adenoma.

Scientific reports·2025

Same author

The impact of illness uncertainty on self-efficacy, personal control, and negative emotions in elderly persons with colon cancer.

Geriatric nursing (New York, N.Y.)·2025

Same author

Study on the aggregation patterns of fleas parasitizing the great gerbil (Rhombomys opimus) in the Junggar Basin plague natural focus.

Parasites & vectors·2025

Same journal

Evaluation of an open-face 8-channel transmit 64-channel receive 7T head coil for neuroimaging.

Frontiers in neuroscience·2026

Same journal

Acoustic stimulation in pain management: neurobiological mechanisms and clinical applications-a narrative review.

Frontiers in neuroscience·2026

Same journal

Local brain connectome parameters across the spectrum of clinical cognitive decline.

Frontiers in neuroscience·2026

Same journal

Body mass index affects EEG microstate dynamics through blood viscosity in high-altitude environments.

Frontiers in neuroscience·2026

Same journal

Disrupted glymphatic function and its relationship with sleep and cognitive impairment in ME/CFS assessed via DTI-ALPS.

Frontiers in neuroscience·2026

Same journal

Neuromorphic-inspired multi-view global-local fusion for IR-UWB radar dynamic gesture recognition.

Frontiers in neuroscience·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 14, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Endoscopic image classification algorithm based on Poolformer.

Huiqian Wang^1,2, Kun Wang¹, Tian Yan¹

¹Postdoctoral Research Station, Chongqing Key Laboratory of Photoelectronic Information Sensing and Transmitting Technology, Chongqing University of Posts and Telecommunications, Chongqing, China.

Frontiers in Neuroscience

|October 9, 2023

Summary

This summary is machine-generated.

This study introduces an improved Poolformer model for classifying surgical smoke in endoscopic images. The method enhances accuracy and sensitivity for targeted smoke removal, improving real-time endoscopic video processing.

Keywords:

ConvNeXt Poolformer endoscopic image image classification single-path topology only during inference token mixer

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jul 14, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Medical Imaging
Computer Vision
Surgical Technology

Background:

Surgical smoke obstructs endoscopic views, necessitating effective image processing.
Current smoke removal methods lack frame specificity, increasing computational load and noise.
Efficient classification of smoke-containing endoscopic images is crucial for targeted interventions.

Purpose of the Study:

To develop a robust and efficient algorithm for classifying endoscopic images with surgical smoke.
To improve the real-time processing capabilities of endoscopic image-based smoke removal.
To enhance the scientific accuracy of targeted smoke removal techniques.

Main Methods:

An improved Poolformer model was developed for endoscopic smoke image classification.
The Token Mixer in the encoder was modified into a multi-branch structure similar to ConvNeXt.
A single-path topology was adopted during prediction to increase processing speed.
Experiments utilized a dataset from the Hamlyn Centre Laparoscopic/Endoscopic Video Dataset, augmented with Blender rendering.

Main Results:

The proposed method demonstrated superior performance in accuracy, sensitivity, and inference speed compared to existing models (mobilenet_v3, efficientnet_b7, ViT-B/16).
Compared to Poolformer_s12, the refined model achieved a 2.3% increase in accuracy and an 8.2% increase in sensitivity.
The method maintained a processing speed of 87 frames per second with a minimal reduction.

Conclusions:

The refined Poolformer model significantly improves endoscopic smoke image classification.
This approach offers a lightweight and effective solution for automatic detection of smoke-containing endoscopic images.
The method balances accuracy and real-time processing needs for endoscopic image analysis and targeted desmoking.