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

Imaging Biological Samples with Optical Microscopy01:18

Imaging Biological Samples with Optical Microscopy

7.5K
Optical microscopy uses optic principles to provide detailed images of samples. Antonie van Leeuwenhoek designed the first compound optical microscope in the 17th century to visualize blood cells, bacteria, and yeast cells. In 1830, Joseph Jackson Lister created an essentially modern light microscope. The 20th century saw the development of microscopes with enhanced magnification and resolution.
In optical microscopy, the specimen to be viewed is placed on a glass slide and clipped on the stage...
7.5K

You might also read

Related Articles

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

Sort by
Same author

Correction: Patient Perspectives on Artificial Intelligence in Gastroenterology: A Multicenter Survey of Knowledge, Concerns, and Beliefs.

The American journal of gastroenterology·2026
Same author

Synthetic data generation: challenges and perspectives for gastrointestinal medicine.

Nature reviews. Gastroenterology & hepatology·2026
Same author

When silence is safer: a review and decision-theoretic framework for LLM abstention in healthcare.

NPJ digital medicine·2026
Same author

Seeking gastroenterological services during a pandemic: lessons from a large, national, population-based survey during the COVID-19 pandemic.

Journal of the Canadian Association of Gastroenterology·2026
Same author

REST, Exploring Sleep Patterns and Influencing Factors in Elite Female Football Athletes.

Scientific data·2026
Same author

Investigating discrepancies in accuracy, agreement and interpretability for single-frame embryo classification tasks conducted by embryologists and deep learning models.

Frontiers in reproductive health·2026

Related Experiment Video

Updated: Oct 9, 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

3.0K

Impact of Image Resolution on Deep Learning Performance in Endoscopy Image Classification: An Experimental Study

Vajira Thambawita1,2, Inga Strümke1, Steven A Hicks1,2

  • 1Simula Metropolitan Center for Digital Engineering, 0167 Oslo, Norway.

Diagnostics (Basel, Switzerland)
|December 24, 2021
PubMed
Summary
This summary is machine-generated.

Higher image resolution significantly improves deep convolutional neural network (CNN) performance in endoscopic lesion detection. This study highlights the need for standardized image resolutions for future AI models in gastrointestinal endoscopy.

Keywords:
convolutional neural networksendoscopic imagesimage resolution

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K
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

676

Related Experiment Videos

Last Updated: Oct 9, 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

3.0K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K
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

676

Area of Science:

  • Medical Artificial Intelligence
  • Gastrointestinal Endoscopy
  • Computer Vision

Background:

  • Deep convolutional neural networks (CNNs) show promise for lesion detection in endoscopy.
  • Current studies often use low image resolutions, potentially sacrificing diagnostic detail.
  • Lack of established standards links image resolution to CNN performance in this field.

Purpose of the Study:

  • To investigate the impact of varying image resolutions on CNN performance for endoscopic image classification.
  • To provide insights for establishing future standards for image characteristics in AI-driven gastrointestinal endoscopy.

Main Methods:

  • Two CNN models were evaluated on the HyperKvasir dataset (10,662 images, 23 findings).
  • Image resolutions ranged from 32x32 to 512x512 pixels, with quality distortions considered.
  • Performance was assessed using two-fold cross-validation with F1-score, Matthews correlation coefficient (MCC), precision, and sensitivity.

Main Results:

  • CNN performance consistently increased with higher image resolutions across all findings.
  • Optimal classification performance, indicated by MCC, was achieved at 512x512 pixels.
  • The highest MCC of 0.9002 was obtained when models were trained and tested at the highest resolution.

Conclusions:

  • Image resolution demonstrably influences CNN performance in endoscopic image analysis.
  • Higher resolutions are crucial for detecting subtle endoscopic findings.
  • The findings advocate for the establishment of standardized image resolution requirements for AI in GI endoscopy.