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

X-ray Imaging01:24

X-ray Imaging

5.7K
German physicist Wilhelm Röntgen (1845–1923) was experimenting with electrical current when he discovered that a mysterious and invisible "ray" would pass through his flesh but leave an outline of his bones on a screen coated with a metal compound. In 1895, Röntgen made the first durable record of the internal parts of a living human: an "X-ray" image (as it came to be called) of his wife’s hand. Scientists worldwide quickly began their own experiments with...
5.7K
Imaging Studies for Cardiovascular System III: X-Ray01:20

Imaging Studies for Cardiovascular System III: X-Ray

220
The most common cardiovascular diagnostic test is an X-ray. It produces images of the heart, blood vessels, and adjacent structures.
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
220

You might also read

Related Articles

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

Sort by
Same author

Non-Destructive Testing and Evaluation of Hybrid and Advanced Structures: A Comprehensive Review of Methods, Applications, and Emerging Trends.

Sensors (Basel, Switzerland)·2025
Same author

Advancements in and Research on Coplanar Capacitive Sensing Techniques for Non-Destructive Testing and Evaluation: A State-of-the-Art Review.

Sensors (Basel, Switzerland)·2024
Same author

A Complementary Fusion-Based Multimodal Non-Destructive Testing and Evaluation Using Phased-Array Ultrasonic and Pulsed Thermography on a Composite Structure.

Materials (Basel, Switzerland)·2024
Same author

Advanced Image Stitching Method for Dual-Sensor Inspection.

Sensors (Basel, Switzerland)·2024
Same author

Robust Multi-Modal Image Registration for Image Fusion Enhancement in Infrastructure Inspection.

Sensors (Basel, Switzerland)·2024
Same author

Automatic Detection and Identification of Defects by Deep Learning Algorithms from Pulsed Thermography Data.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Jul 30, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K

Deep Learning Neural Network Performance on NDT Digital X-ray Radiography Images: Analyzing the Impact of Image

Bata Hena1,2, Ziang Wei1,2,3,4, Clemente Ibarra Castanedo1,2

  • 1Department of Electrical and Computer Engineering, Université Laval, Quebec City, QC G1V 0A6, Canada.

Sensors (Basel, Switzerland)
|May 13, 2023
PubMed
Summary

Optimizing image quality is crucial for automated defect detection in industrial radiography. This study shows that high contrast-to-noise ratio (CNR) in training data significantly improves deep learning model performance for non-destructive testing (NDT).

Keywords:
automated defect recognition (ADR)deep learningdigital X-ray radiographynon-destructive testingsemantic segmentation

More Related Videos

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
3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography
07:01

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

9.9K

Related Experiment Videos

Last Updated: Jul 30, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
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
3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography
07:01

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

9.9K

Area of Science:

  • Industrial Nondestructive Testing (NDT)
  • Digital Radiography
  • Deep Learning in Image Analysis

Background:

  • Process automation in manufacturing drives demand for automated inspection using non-destructive testing (NDT).
  • Deep learning models are increasingly used for defect identification in digital X-ray radiography images.
  • Understanding the impact of image quality on deep learning performance is essential for reliable automated inspection.

Purpose of the Study:

  • To investigate the influence of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) on a U-net deep learning model for defect detection.
  • To evaluate how varying radiographic image quality affects the performance of semantic segmentation models.
  • To determine the optimal image quality parameters for training deep learning models in NDT applications.

Main Methods:

  • Acquired digital X-ray radiography images with varied exposure factors to alter image quality.
  • Calculated signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) for image datasets.
  • Trained a U-net deep learning model five times, each with a dataset categorized by specific SNR and CNR values.
  • Evaluated model performance using the intersection-over-union (IoU) metric.

Main Results:

  • Training a U-net model with high CNR values resulted in an IoU of 0.9594 on similar test data.
  • Model performance significantly dropped to an IoU of 0.5875 when tested on data with lower CNR.
  • Image quality parameters, particularly CNR, have a substantial impact on the accuracy of deep learning-based defect detection.

Conclusions:

  • A balanced training dataset reflecting specific image quality parameters is vital for enhancing deep learning model performance.
  • Achieving optimal SNR and CNR is critical for reliable automated defect identification in NDT digital X-ray radiography.
  • This research highlights the need to carefully manage image acquisition parameters for effective deep learning applications in industrial inspection.