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: Feb 20, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.4K

Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification.

Younghak Shin, Ilangko Balasingham

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |October 25, 2017
    PubMed
    Summary

    This study compares two polyp detection methods for colonoscopy screening. A deep learning approach using convolutional neural networks (CNNs) significantly outperformed traditional feature-based methods in classifying polyps.

    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

    Advancing Survival Analysis with Large Language Models: A Solution to Data Scarcity and Missing Information in Healthcare.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
    Same author

    Decoding Blood Volume Loss: Can Non-Invasive Signals Match the Gold Standard?

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
    Same author

    Sonication Tuning in Focused Ultrasound Multi-Target Brain Tumor Therapy.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
    Same author

    Recording and modeling of pinched hysteresis loops, the fingerprint of a memristor, in neurons.

    Scientific reports·2025
    Same author

    Empirical Model of Focused Ultrasound-Mediated Treatment for Chemotherapy Delivery to Brain Tumors.

    Ultrasound in medicine & biology·2025
    Same author

    Multimodal deep learning improves recurrence risk prediction in pediatric low-grade gliomas.

    Neuro-oncology·2024

    Area of Science:

    • Medical imaging
    • Artificial intelligence in healthcare
    • Gastroenterology

    Background:

    • Colonoscopy is a key screening tool for colorectal cancer, but miss-detected polyps pose a risk.
    • Automated polyp classification can improve screening accuracy and efficiency.

    Purpose of the Study:

    • To compare the performance of a hand-craft feature method versus a deep learning (convolutional neural network - CNN) approach for automatic polyp classification.
    • To evaluate the effectiveness of these methods in identifying polyps during colonoscopy.

    Main Methods:

    • Hand-craft feature method: Combined shape and color features with Support Vector Machine (SVM) classification.
    • Deep learning method: Utilized a three-convolution and pooling-based CNN framework for polyp classification.

    Related Experiment Videos

    Last Updated: Feb 20, 2026

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    2.4K
  • Evaluation: Both methods were tested on three public polyp databases.

    • Main Results:

    • The CNN-based deep learning framework demonstrated superior classification performance compared to the hand-craft feature method.
    • The CNN approach achieved over 90% accuracy, sensitivity, specificity, and precision in polyp classification.
    • This indicates a significant advancement in automated polyp detection.

    Conclusions:

    • Convolutional neural networks offer a highly effective approach for automatic polyp classification in colonoscopy.
    • Deep learning methods show promise in enhancing the accuracy and reliability of colorectal cancer screening.
    • Further development of AI-powered tools can aid physicians in reducing miss-detected polyps.