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

Search research articles

Related Experiment Video

Updated: Feb 19, 2026

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

Endoscopic Image Classification and Retrieval using Clustered Convolutional Features.

Jamil Ahmad¹, Khan Muhammad¹, Mi Young Lee¹

¹Digital Contents Research Institute, Sejong University, Seoul, Republic of Korea.

Journal of Medical Systems

|November 1, 2017

Summary

This summary is machine-generated.

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

Impact of a foodservice establishment manager's willingness to perform duties on hygiene management levels and the mediating effects of extrinsic motivations: a cross-sectional study.

Korean journal of community nutrition·2026

Same author

Three-dimensional evaluation of soft tissue contour changes after premolar extraction with and without alveolar ridge preservation: A prospective observational study.

PloS one·2026

Same author

Bangpungtongsung-san alleviates depressive-like behavior and metabolic disturbances in high-fat diet-induced obesity: mechanisms involving inflammation, CREB/BDNF signaling, and NMDA receptor modulation.

Frontiers in pharmacology·2025

Same author

CRTSC: Channel-Wise Recalibration and Texture-Structural Consistency Constraint for Anomaly Detection in Medical Chest Images.

Sensors (Basel, Switzerland)·2025

Same author

Bilateral collaborative streams with multi-modal attention network for accurate polyp segmentation.

Scientific reports·2025

Same author

Effect of <i>Pinus koraiensis</i> leaf extract on fatigue reduction and exercise performance: study protocol for a randomized, double-blind, placebo-controlled clinical trial.

Frontiers in medicine·2025

Same journal

Starmate: A Lightweight AI Assistant for Autism Caregivers Developed and Evaluated Through a User-Centered Mixed-Methods Framework.

Journal of medical systems·2026

Same journal

Predicting the Predictor: Unresolved Validity Threats in LLM-Based ASA Classification.

Journal of medical systems·2026

Same journal

Development and Internal Validation of a Vectorcardiography-Augmented Model for 12-Month Major Adverse Cardiovascular Events in Chronic Heart Failure.

Journal of medical systems·2026

Same journal

Development and Validation of an Automated Acute Kidney Injury E-Alert System Integrated with Clinical Decision Support for Hospitalized Patients.

Journal of medical systems·2026

Same journal

Calibration of Self-Reported Confidence and Accuracy of Large Language Models in Medical Question Answering.

Journal of medical systems·2026

Same journal

Throughput Benchmarking and Throughput Variance Analysis to Evaluate the Efficiency of an Outpatient Endoscopy Unit.

Journal of medical systems·2026

See all related articles

This study introduces a novel method for creating compact visual features from endoscopic images using clustered convolutional neural network (CNN) features. This approach enhances content retrieval and classification in large endoscopic video archives.

Area of Science:

Medical Imaging
Computer Vision
Artificial Intelligence

Background:

Minimally invasive surgery generates vast endoscopic video archives.
Efficient indexing and retrieval require compact and discriminative visual features.
Existing methods may not fully capture the complexity of endoscopic imagery.

Purpose of the Study:

To develop an effective method for representing endoscopic images using salient convolutional features.
To improve the efficiency of content indexing and matching in large endoscopic video archives.
To extract compact and discriminative visual features that outperform existing approaches.

Main Methods:

Clustering convolutional kernels from a pre-trained Convolutional Neural Network (CNN) based on color and texture sensitivity.

Keywords:

Classification Convolution Endoscopy Features extraction Image retrieval Spatial pooling

Related Experiment Videos

Last Updated: Feb 19, 2026

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

Employing spatial maximal activator pooling (SMAP) to create layout-preserving feature maps.

Utilizing a moving window based structured pooling method to capture spatial layout and global shape information.

Combining individual feature histograms into a comprehensive histogram.

Main Results:

The proposed method extracts color and texture features with varying strengths.
The SMAP approach effectively selects dominant and discriminative features.
The generated features are compact and demonstrate superior performance in retrieval and classification tasks compared to existing methods on an endoscopy dataset.

Conclusions:

Clustering convolutional features provides a robust way to represent endoscopic images.
The developed feature extraction method is efficient and effective for large-scale endoscopic video analysis.
This technique offers significant improvements for content-based retrieval and classification in medical imaging applications.