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 Experiment Video

Updated: May 17, 2026

Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System
15:49

Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System

Published on: October 16, 2013

Computer-aided colorectal tumor classification in NBI endoscopy using local features.

Toru Tamaki1, Junki Yoshimuta, Misato Kawakami

  • 1Department of Information Engineering, Graduate School of Engineering, Hiroshima University, 1-4-1 Kagamiyama, Higashi-hiroshima, Hiroshima 739-8527, Japan. tamaki@hiroshima-u.ac.jp

Medical Image Analysis
|October 23, 2012
PubMed
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

Contactless Respiratory Waveform Estimation Using a Depth Camera and AI-Based Body Detection.

Sensors (Basel, Switzerland)·2026
Same author

Long-term local recurrence and survival after colorectal endoscopic submucosal dissection: a prospective multicenter real-world cohort study.

Endoscopy·2026
Same author

Self-assembling peptide hydrogel prevents esophageal stenosis after endoscopic submucosal dissection for esophageal squamous cell carcinoma: Multicenter prospective study.

Endoscopy international open·2026
Same author

Long-Term Outcomes After Endoscopic Submucosal Dissection for T1 Colorectal Cancer: A Multicenter Prospective Study.

Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association·2026
Same author

Predicting mucosal healing in patients with ulcerative colitis in clinical remission using biomarkers: A single-center prospective pilot study.

Medicine·2026
Same author

Resection Depth of Underwater Versus Conventional Endoscopic Mucosal Resection for Intermediate-Sized Colorectal Tumors.

The American journal of gastroenterology·2026

This study introduces a computer-aided system for classifying colorectal tumors using Narrow Band Imaging (NBI) during colonoscopy. The system achieves high accuracy in identifying tumor types, aiding early cancer detection.

Area of Science:

  • Medical Imaging
  • Computational Pathology
  • Gastroenterology

Background:

  • Early detection of colorectal cancer via colonoscopy is crucial for patient outcomes.
  • Narrow Band Imaging (NBI) with zoom-videoendoscopy aids visual inspection of colorectal tumors.
  • Histological diagnosis often relies on classification schemes for NBI magnification findings.

Purpose of the Study:

  • To develop and evaluate a computer-aided recognition system for classifying NBI images of colorectal tumors.
  • To classify NBI images into three types (A, B, and C3) based on NBI magnification findings.
  • To explore local feature-based recognition methods, specifically bag-of-visual-words (BoW), for this classification task.

Main Methods:

  • A prototype system combining bag-of-visual-words (BoW) representation of local features with Support Vector Machine (SVM) classifiers was developed.

More Related Videos

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

Related Experiment Videos

Last Updated: May 17, 2026

Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System
15:49

Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System

Published on: October 16, 2013

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

  • Local features were extracted using Difference-of-Gaussians and grid sampling schemes.
  • Extensive experiments were conducted, varying parameters like sampling strategy, feature histogram representation, and SVM kernel types.

    • Main Results:

    • The proposed system achieved a 96% recognition rate using 10-fold cross-validation on a dataset of 908 NBI images.
    • A separate test dataset yielded a recognition rate of 93%.
    • Performance was evaluated using recognition rates, precision/recall, and F-measure across different numbers of visual words.

    Conclusions:

    • The developed computer-aided system demonstrates high performance in classifying NBI images of colorectal tumors.
    • This approach shows promise for enhancing the accuracy and efficiency of early colorectal cancer detection.
    • Further optimization and validation of the system could significantly impact clinical diagnosis.