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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Ofatumumab therapy modulates the meningeal lymphatic draining function in patients with multiple sclerosis: a pilot study.

Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology·2026
Same author

Development of a High-Throughput LC-MS/MS Method for Simultaneous Quantification of Four Therapeutic Monoclonal Antibodies in Human Serum: Application in Clinical Therapeutic Drug Monitoring.

Biomedical chromatography : BMC·2026
Same author

Cedrol ameliorates ulcerative colitis <i>via</i> myeloid differentiation factor 2-mediated inflammation suppression, with barrier restoration and microbiota modulation.

World journal of gastroenterology·2026
Same author

Artificial intelligence-assisted diagnosis of rectal neuroendocrine tumors during white-light endoscopy.

World journal of gastroenterology·2026
Same author

Bridging the gap: Computer-aided detection and Yamada classification system matches expert performance.

World journal of gastroenterology·2025
Same author

Treatment strategy for myasthenia gravis with GAD65-IgG associated neurological disorders: A case report.

Journal of neuroimmunology·2025

Related Experiment Video

Updated: Jul 4, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K

Automatic detection of small bowel lesions with different bleeding risks based on deep learning models.

Rui-Ya Zhang1, Peng-Peng Qiang2, Ling-Jun Cai1

  • 1Department of Gastroenterology, The Fifth Clinical Medical College of Shanxi Medical University, Taiyuan 030012, Shanxi Province, China.

World Journal of Gastroenterology
|February 5, 2024
PubMed
Summary

This study introduces a deep learning model for small bowel capsule endoscopy that accurately identifies lesions and bleeding risks, significantly improving diagnostic efficiency and physician accuracy in detecting high-risk bleeding cases.

Keywords:
Artificial intelligenceBleeding riskCapsule endoscopyDeep learningImage classificationObject detection

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
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

2.8K

Related Experiment Videos

Last Updated: Jul 4, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
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

2.8K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Gastroenterology

Background:

  • Deep learning offers efficient automatic image recognition for small bowel (SB) capsule endoscopy (CE).
  • Existing deep learning models face challenges in accurately diagnosing SB lesions and assessing bleeding risks.
  • Physician diagnostic efficiency can be enhanced with advanced AI tools.

Purpose of the Study:

  • To develop a novel deep learning model for classifying and detecting SB lesions from CE images.
  • To accurately assess the bleeding risk associated with identified SB lesions.
  • To improve diagnostic efficiency and the identification of high-risk bleeding patients.

Main Methods:

  • A two-stage deep learning approach combining image classification and object detection was employed.
  • An improved ResNet-50 model classified images (lesion, normal, invalid).
  • An improved YOLO-V5 model detected lesion type, bleeding risk, and location, with performance compared to human endoscopists.

Main Results:

  • The model achieved 98.96% accuracy, outperforming single-module systems.
  • Model-assisted reading demonstrated high sensitivity (99.17%), specificity (99.92%), and accuracy (99.86%).
  • The model processed images significantly faster (48 ms/image) than physicians (0.40 ± 0.24 s/image).

Conclusions:

  • A combined deep learning model for classification and detection effectively diagnoses SB lesions and bleeding risks in CE.
  • This approach enhances physician diagnostic efficiency and the ability to identify high-risk bleeding groups.
  • The model shows significant potential for improving patient care in gastroenterology.