Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Leaky Scanning

Leaky Scanning

During most eukaryotic translation processes, the small 40S ribosome subunit scans an mRNA from its 5' end until it encounters the first start AUG codon. The large 60S ribosomal subunit then joins the smaller one to initiate protein synthesis. The location of the translation initiation is largely determined by the nucleotides near the start codon as there may be multiple translation initiation sites present on the mRNA. Marilyn Kozak discovered that the sequence RCCAUGG (where R...

Types of Errors: Detection and Minimization

Types of Errors: Detection and Minimization

Error is the deviation of the obtained result from the true, expected value or the estimated central value. Errors are expressed in absolute or relative terms.
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...

You might also read

Related Articles

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

Sort by

Same author

Estimating the properties of bone phantom cylinders through the inversion of axially transmitted low-frequency ultrasonic guided waves.

Ultrasonics·2025

Same author

Visualization of specular reflections with phase coherence imaging using sub-apertures.

Ultrasonics·2025

Same author

Cortical bone plate properties assessment using inversion of axially transmitted low frequency ultrasonic guided waves.

The Journal of the Acoustical Society of America·2024

Same author

Surface breaking crack sizing method using pulse-echo Rayleigh waves.

Ultrasonics·2024

Same author

An alternative Rayleigh wave excitation method using an ultrasonic phased array.

Ultrasonics·2023

Same author

Ultrasonic imaging using conditional generative adversarial networks.

Ultrasonics·2023

Same journal

MUnet: A model-based unrolled reconstruction framework for computational photoacoustic imaging.

Ultrasonics·2026

Same journal

Uncovering the mechanism of ultrasonic cavitation-induced deagglomeration of 7-ADCA agglomerates.

Ultrasonics·2026

Same journal

Identifiability limits in ultrasonic microstructure characterisation using attenuation and velocity features: Canonical analysis and stochastic surrogate modelling.

Ultrasonics·2026

Same journal

A methodology to estimate the ultrasonic p-wave velocity of coarse aggregates in concrete.

Ultrasonics·2026

Same journal

Ultrasonic guided wave damage imaging using the time difference coefficient between direct and scattered waves.

Ultrasonics·2026

Same journal

Axial acoustic radiation force on a sphere embedded in a gel phantom within a focused ultrasound field: simulation and measurement.

Ultrasonics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 3, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Automatic flaw detection in sectoral scans using machine learning.

Hugo Hervé-Côte¹, Frédéric Dupont-Marillia², Pierre Bélanger¹

¹PULÉTS, École de technologie supérieure, 1100 Notre-Dame Ouest, Montréal QC H3C 1K3, Canada.

|May 16, 2024

Summary

This summary is machine-generated.

Artificial intelligence (AI) can now detect defects in phased array ultrasonic testing (PAUT) with high accuracy. A new machine learning model trained on a large dataset demonstrates robust defect detection, even in noisy conditions.

Keywords:

Convolutional Neural Network Flaw detection Full Matrix Capture Phased Array Ultrasonic Testing Total Focusing Method Ultrasonic testing

More Related Videos

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Related Experiment Videos

Last Updated: May 3, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Area of Science:

Non-destructive testing
Artificial Intelligence
Machine Learning
Ultrasonic Testing

Background:

Phased array ultrasonic testing (PAUT) image analysis relies heavily on inspector expertise, which can lead to variability and errors.
Current machine learning applications in PAUT are limited by the scarcity of large, labeled inspection datasets due to data confidentiality.
Existing methods require significant training and experience for accurate defect identification.

Purpose of the Study:

To develop and evaluate a machine learning model for automated defect detection in PAUT sectoral scans.
To address the challenge of limited labeled data in PAUT by generating a comprehensive dataset.
To improve the accuracy and reliability of PAUT defect analysis.

Main Methods:

Generated a large database of hundreds of thousands of sectoral scans from Full Matrix Capture (FMC) data using mock-ups.
Trained a machine learning model on this comprehensive dataset, incorporating data from various probes and frequencies.
Utilized post-processing of FMC data to compute sectoral scans from focal laws.

Main Results:

The trained machine learning model achieved robust defect detection in PAUT sectoral scans.
The model demonstrated generalization capabilities, successfully identifying defect types not present in the training data.
Consistent detection performance was observed even under high noise conditions with low Contrast-to-Noise Ratio (CNR).

Conclusions:

A novel approach using AI and a large, generated dataset significantly enhances PAUT defect detection.
The developed model offers a reliable and accurate alternative to manual interpretation, reducing human error.
This advancement holds potential for wider adoption of computer vision in PAUT inspections.