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 22, 2026

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
03:05

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

1.6K

Gastric precancerous diseases classification using CNN with a concise model.

Xu Zhang1,2, Weiling Hu3,4, Fei Chen4,5

  • 1College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou, China.

Plos One
|September 27, 2017
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

Long-text caption generation for surgical image with a concept retrieval augmented large multimodal model.

PloS one·2026
Same author

Generalized Few-Shot MM-Former For Surgical Scene Panoptic Segmentation.

Healthcare technology letters·2025
Same author

Real-time gastric polyp detection using convolutional neural networks.

PloS one·2019
Same author

Optical imaging. Expansion microscopy.

Science (New York, N.Y.)·2015
Same author

Erratum for kang et Al., flexibility and symmetry of prokaryotic genome rearrangement reveal lineage-associated core-gene-defined genome organizational frameworks.

mBio·2015
Same author

Pretreatment with intravenous levetiracetam in the rhesus monkey Coriaria lactone-induced status epilepticus model.

Journal of the neurological sciences·2015
This summary is machine-generated.

Accurate and rapid identification of gastric precancerous diseases (GPD) is crucial. A new Gastric Precancerous Disease Network (GPDNet) utilizing iterative reinforced learning (IRL) achieved 88.90% accuracy in classifying GPD.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Gastroenterology

Background:

  • Gastric precancerous diseases (GPD) pose a risk of progressing to early gastric cancer if misdiagnosed.
  • Accurate and timely recognition of GPD is essential for effective clinical management.

Purpose of the Study:

  • To develop a concise and efficient deep learning model for classifying three types of GPD: polyp, erosion, and ulcer.
  • To enhance classification accuracy and speed for clinical applications.

Main Methods:

  • Utilized convolutional neural networks (CNN) to create the Gastric Precancerous Disease Network (GPDNet).
  • Incorporated fire modules from SqueezeNet to reduce model size and parameters.
  • Applied iterative reinforced learning (IRL) to fine-tune model parameters and improve accuracy.

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

774

Related Experiment Videos

Last Updated: Feb 22, 2026

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
03:05

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

1.6K
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

774

Main Results:

  • GPDNet achieved a 10-fold reduction in model size and parameters compared to standard models.
  • Iterative reinforced learning (IRL) improved classification accuracy by approximately 9% after 6 iterations.
  • The final GPDNet model demonstrated a classification accuracy of 88.90%.

Conclusions:

  • The GPDNet model offers a promising solution for rapid and accurate clinical recognition of GPD.
  • The integration of IRL enhances the performance of concise CNN models for medical image classification.
  • This approach supports improved diagnostic capabilities in gastroenterology.