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

Force Classification01:22

Force Classification

1.9K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.9K
Convolution Properties II01:17

Convolution Properties II

339
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
339

You might also read

Related Articles

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

Sort by
Same author

Redefining text-to-SQL metrics by incorporating semantic and structural similarity.

Scientific reports·2025
Same author

Deep learning-based object detection algorithms in medical imaging: Systematic review.

Heliyon·2025
Same author

Comparing SMILES and SELFIES tokenization for enhanced chemical language modeling.

Scientific reports·2024
Same author

Comparing Stacking Ensemble Techniques to Improve Musculoskeletal Fracture Image Classification.

Journal of imaging·2024
Same author

Multiparametric MRI dataset for susceptibility-based radiomic feature extraction and analysis.

Scientific data·2024
Same author

Assessing robustness of quantitative susceptibility-based MRI radiomic features in patients with multiple sclerosis.

Scientific reports·2023
Same journal

Multi-dimensional alignment framework with geometric intraoral constraints for precise occlusal registration.

Health information science and systems·2026
Same journal

SPSGL: uncovering psychiatric network mechanisms via structural-prior guided synaptic graph learning.

Health information science and systems·2026
Same journal

A noval 4D graph temporal brain network model for EEG-based depression detection.

Health information science and systems·2026
Same journal

PLETHSOMNet: automated identification of insomnia using deep neural network technique with photoplethysmography (PPG) signals.

Health information science and systems·2026
Same journal

Self-supervised fusion of clinical expertise and interpersonal skills for enhanced physician recommendation.

Health information science and systems·2026
Same journal

Construction and application of a traditional Chinese medicine syndrome differentiation and treatment model grounded in knowledge distillation and reinforcement learning.

Health information science and systems·2026
See all related articles

Related Experiment Video

Updated: Oct 25, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.1K

Improving convolutional neural networks performance for image classification using test time augmentation: a case

Ibrahem Kandel1, Mauro Castelli1

  • 1Nova Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, 1070-312 Lisboa, Portugal.

Health Information Science and Systems
|August 5, 2021
PubMed
Summary
This summary is machine-generated.

Test time augmentation (TTA) significantly improves X-ray fracture detection accuracy. This AI technique enhances deep learning models, especially those initially performing poorly, by using image transformations during testing.

Keywords:
Convolutional neural networksDeep learningEnsemble learningImage classificationTest time augmentationTransfer learning

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

9.5K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

621

Related Experiment Videos

Last Updated: Oct 25, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

621

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Bone fractures are a common emergency room (ER) diagnosis requiring X-ray imaging.
  • Expert radiologists are not always available in ERs, leading to potential diagnostic delays or errors.
  • Automatic X-ray classifiers can provide crucial second opinions for emergency physicians.

Purpose of the Study:

  • To investigate the impact of Test Time Augmentation (TTA) on the performance of deep learning models for X-ray image classification.
  • To evaluate the effectiveness of various image augmentation techniques during the testing phase.
  • To assess ensemble methods in conjunction with TTA for improved fracture detection.

Main Methods:

  • Utilized the MURA dataset for evaluating bone fracture classification.
  • Applied nine different image augmentation techniques during the testing phase.
  • Implemented two ensemble techniques: majority vote and average vote.

Main Results:

  • Test Time Augmentation (TTA) led to a significant increase in classification performance.
  • The performance enhancement was particularly notable for deep learning models with lower initial scores.
  • Ensemble methods further contributed to improved accuracy when combined with TTA.

Conclusions:

  • TTA is a valuable technique for enhancing the accuracy of AI-based X-ray fracture detection systems.
  • Implementing TTA can improve diagnostic reliability in ER settings, even with less performant models.
  • The findings support the integration of TTA into AI diagnostic tools for medical imaging.