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: Jun 17, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

Grad-CAM based deep learning analytics for image-level colon disease classification based on graph neural networks

Chaohui Zhen1, Canhua Yao2, Song Li1

  • 1Department of Gastrointestinal Surgery, The First Dongguan Affiliated Hospital, Guangdong Medical University, Dongguan, Guangdong, China.

Frontiers in Physiology
|June 10, 2026
PubMed
Summary

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

BK channel deficiency promotes lipolysis via an AKT-independent activation of the cAMP/PKA/HSL pathway.

Journal of lipid research·2026
Same author

Tetrandrine enhances anti-PD-1 immunotherapeutic efficacy for hepatocellular carcinoma by activating STING/TBK1/IRF3 pathway.

Frontiers in immunology·2026
Same author

Physiological classification of Parkinson's disease severity using multimodal speech biomarkers with a hybrid CNN-Mamba framework.

Frontiers in physiology·2026
Same author

UAV-based tree species classification using DenseNet121 with transfer learning on visible light images.

Scientific reports·2026
Same author

Valence reconstruction driven metal-insulator transition and enhanced anomalous Hall effect in NiCo<sub>2</sub>O<sub>4</sub>epitaxial films induced by CaH<sub>2</sub>reduction.

Journal of physics. Condensed matter : an Institute of Physics journal·2026
Same author

Urological diagnostics based on kidney stone detection in CT imaging using YOLOv8 deep learning framework.

Frontiers in medicine·2026
Same journal

What role does the Notch signaling pathway play in exercise-related metabolic and neurological adaptations? A molecular-to-systems perspective.

Frontiers in physiology·2026
Same journal

Variation in skin barrier function throughout smoltification in Atlantic salmon (<i>Salmo salar</i>).

Frontiers in physiology·2026
Same journal

Correction: What role does the Notch signaling pathway play in exercise-related metabolic and neurological adaptations? A molecular-to-systems perspective.

Frontiers in physiology·2026
Same journal

Effect of high intensity interval Nordic walking and strength training on selected biomarkers of metabolic syndrome in postmenopausal women with abdominal obesity: a quasi-experimental studies.

Frontiers in physiology·2026
Same journal

The interplay between sexual activity, athletic performance, and recovery in athletes: a narrative review.

Frontiers in physiology·2026
Same journal

The alveolar edema equation.

Frontiers in physiology·2026
See all related articles
This summary is machine-generated.

Vision Transformers (ViT) excel in colon disease classification, achieving 94.6% accuracy. Graph neural networks (GNNs) offer competitive performance, demonstrating deep learning

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Accurate colonoscopic image classification is crucial for early colorectal disease detection.
  • Deep learning models, including transformers and graph neural networks (GNNs), offer advanced methods for analyzing image data.
  • These models can capture global context and relational structures vital for disease characterization.

Purpose of the Study:

  • To evaluate transformer-based and graph-based deep learning frameworks for endoscopic colon disease classification.
  • To compare the performance of Vision Transformers (ViT) against CNN-GNN pipelines.
  • To assess the effectiveness of different graph construction strategies within GNNs.

Main Methods:

  • Experiments utilized the Kvasir V2 dataset.
Keywords:
Grad-CAMKvasir V2 datasetcolorectal cancerendoscopygraph neural networks (GNN)interpretabilitymedical image classificationvision transformer (ViT)

Related Experiment Videos

Last Updated: Jun 17, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

  • A Vision Transformer (ViT) was selectively fine-tuned.
  • A CNN-GNN pipeline integrated ViT embeddings with various graph construction methods (cosine similarity, k-NN, epsilon-radius) and GNN architectures.
  • Performance metrics included accuracy, precision, recall, and macro-F1 score; Grad-CAM was used for interpretability.

    • Main Results:

    • The fine-tuned Vision Transformer achieved 94.6% accuracy and a 0.94 macro-F1 score.
    • The optimal graph-based approach, using ViT embeddings with an epsilon graph and GIN aggregation, reached 92% accuracy and a 0.92 macro-F1 score.
    • Both transformer and graph-based methods demonstrated strong classification capabilities.

    Conclusions:

    • Transformer-based models show superior discriminative power for colon disease classification.
    • Graph-based relational modeling provides competitive results when utilizing high-quality image embeddings.
    • These findings highlight the potential of advanced deep learning techniques in improving endoscopic diagnostics.