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

Commentary: The effects of postponing BCG vaccination on the risk of BCG-related complications among patients with severe combined immunodeficiency disease in Saudi Arabia.

Frontiers in immunology·2026
Same author

Failure of Hepatic Insulin Clearance via CEACAM1-Mediated Endocytosis: The Missing Physiological Link Between Proinsulin Misfolding, Hyperinsulinemia, and Metabolic Complications in Type 2 Diabetes, Obesity, and NAFLD.

Problemy endokrinologii·2026
Same author

Extensive Spontaneous Pneumomediastinum With Suspected Recurrence in a Young Woman: A Case of Hamman Syndrome.

Cureus·2026
Same author

Sulfur-Dependent Disulfide Bond Disruption in Insulin Resistance: A Hypothesis.

Advanced pharmaceutical bulletin·2026
Same author

The 'upside-down' technique in transperitoneal robotic partial nephrectomy: visual standardization and clinical outcomes in 50 consecutive dorsally located renal masses.

Journal of robotic surgery·2026
Same author

Glycohypoxia: a hypothesis linking chronic hyperglycemia to functional hypoxia and diabetic complications in type 2 diabetes.

Medical gas research·2026
Same journal

Peripheral B-cell receptor repertoire predicts immune-related adverse events following immune checkpoint inhibitor therapy in advanced renal cell carcinoma.

Scientific reports·2026
Same journal

Effects of black soldier fly (Hermetia illucens L.) larvae zoocompost on the mineral element content of blue honeysuckle berries.

Scientific reports·2026
Same journal

Investigation on absorption refrigeration performance of R1243zf with imidazolium ionic liquid as the working pairs.

Scientific reports·2026
Same journal

DeepTriage-CN: integrating clinical text with vital signs for emergency department admission prediction in an aging population.

Scientific reports·2026
Same journal

Gold nanoparticles as dual-action antiviral agents: disruption of SARS-CoV-2 viral envelopes and RNA integrity.

Scientific reports·2026
Same journal

Comparison of capillary microsampling and venous blood for multi-pathogen serosurveillance.

Scientific reports·2026
See all related articles

Related Experiment Video

Updated: Jul 5, 2025

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

Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision

Sharib Ali1,2,3, Noha Ghatwary4, Debesh Jha5,6

  • 1School of Computing, Faculty of Engineering and Physical Sciences, University of Leeds, Leeds, LS2 9JT, UK. s.s.ali@leeds.ac.uk.

Scientific Reports
|January 23, 2024
PubMed
Summary
This summary is machine-generated.

Automated polyp detection using machine learning struggles with generalizability across diverse colonoscopy data. Top AI models prioritized accuracy over real-time performance, highlighting the need for improved robustness in clinical settings.

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

542
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

Related Experiment Videos

Last Updated: Jul 5, 2025

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
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

542
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K

Area of Science:

  • Medical imaging
  • Artificial intelligence in healthcare
  • Gastroenterology

Background:

  • Colorectal polyps are precursors to cancer, but their detection during colonoscopy is challenging due to variability in size, appearance, and location.
  • Current colonoscopy surveillance and polyp removal are operator-dependent, leading to high missed detection and incomplete removal rates.
  • Machine learning methods have been developed for automated polyp detection and segmentation, but often lack generalizability to diverse clinical data.

Purpose of the Study:

  • To rigorously test the generalizability of deep learning methods for automated polyp detection and segmentation.
  • To assess the clinical applicability and real-time performance of top-performing AI models in a multi-center dataset.
  • To identify key challenges and propose hypotheses for improving AI robustness in routine colonoscopy procedures.

Main Methods:

  • Curated a multi-center, multi-population dataset from six different colonoscopy systems with expert gastroenterologist input.
  • Organized a crowd-sourcing Endoscopic computer vision challenge to develop automated polyp detection and segmentation methods.
  • Analyzed the performance of top-ranking AI teams, focusing on accuracy and real-time performance metrics.

Main Results:

  • Top-performing AI models for polyp detection and segmentation demonstrated a focus on accuracy at the expense of real-time performance.
  • The study rigorously tested the generalizability of these deep learning methods across diverse datasets and acquisition systems.
  • Analysis revealed limitations in the current AI models' ability to adapt to the variability encountered in routine clinical colonoscopy.

Conclusions:

  • Existing automated polyp detection and segmentation methods require significant improvement in generalizability to be clinically applicable.
  • The diversity inherent in multi-center colonoscopy datasets necessitates the development of more robust AI algorithms.
  • Future research should focus on enhancing AI model performance for real-time, reliable polyp detection in dynamic clinical environments.