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

Search research articles

Related Experiment Video

Updated: Jun 5, 2026

Radiosynthesis, Quality Control, and Small Animal Positron Emission Tomography Imaging of 68Ga-Labelled Nano Molecules

Radiosynthesis, Quality Control, and Small Animal Positron Emission Tomography Imaging of ⁶⁸Ga-Labelled Nano Molecules

Published on: October 4, 2024

A novel peak-searching method for multiple radioisotopes based on deep learning.

Dajian Liang¹, Pin Gong², Zeyu Wang¹

¹Department of Nuclear Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, China.

Applied Radiation and Isotopes : Including Data, Instrumentation and Methods for Use in Agriculture, Industry and Medicine

|June 3, 2026

Summary

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

The relationship between perfectionism, neuroticism, and exercise addiction risk: a latent profile analysis and the mediating role of social physique anxiety.

Frontiers in psychology·2026

Same author

Circulating Antinephrin Antibodies in Adult Chinese Patients With IgAN and Nephrotic-Range Proteinuria.

Kidney international reports·2026

Same author

Structures of the endophytic microbiota during heart rot development in <i>Abies georgei</i> var. <i>smithii</i>.

Microbiology spectrum·2026

Same author

Controlled encapsulation and droplet size prediction in two-step microfluidic double emulsions.

Lab on a chip·2026

Same author

Time poverty and access-based consumption: Convenience gains and risk blindness.

British journal of psychology (London, England : 1953)·2026

Same author

High-specificity kilobase-level multiplex PCR enabled by graphene oxide-dendrimer-encapsulated gold nanoparticles.

Journal of materials chemistry. B·2026

This study introduces an automated deep learning framework for radionuclide identification using gamma-ray spectroscopy. Convolutional Neural Networks (CNNs) offer balanced performance for real-time detection in complex environments.

Area of Science:

Nuclear physics
Data science
Spectroscopy

Background:

Traditional radionuclide identification struggles with large data and complex environments in mobile detection.
Automated methods are needed for nuclear security, arms control, and emergency response.

Purpose of the Study:

To develop and evaluate an automated deep learning-based peak-searching framework for radionuclide identification.
To compare the performance of Convolutional Neural Networks (CNNs), Residual Networks (ResNets), and Transformers for this task.

Main Methods:

A deep learning framework was developed to identify photopeak channel coordinates from gamma-ray spectra.
Three architectures (CNN, ResNet, Transformer) were trained and compared.
Performance was evaluated using precision, recall, and F1-score under strict and tolerant channel-matching criteria.

Keywords:

Deep learning Gamma spectroscopy Multi-nuclide identification NaI(Tl) detector Numerical simulation Peak localization

More Related Videos

A Novel Technique for Raman Analysis of Highly Radioactive Samples Using Any Standard Micro-Raman Spectrometer

A Novel Technique for Raman Analysis of Highly Radioactive Samples Using Any Standard Micro-Raman Spectrometer

Published on: April 12, 2017

Related Experiment Videos

Last Updated: Jun 5, 2026

Radiosynthesis, Quality Control, and Small Animal Positron Emission Tomography Imaging of 68Ga-Labelled Nano Molecules

Radiosynthesis, Quality Control, and Small Animal Positron Emission Tomography Imaging of ⁶⁸Ga-Labelled Nano Molecules

Published on: October 4, 2024

A Novel Technique for Raman Analysis of Highly Radioactive Samples Using Any Standard Micro-Raman Spectrometer

A Novel Technique for Raman Analysis of Highly Radioactive Samples Using Any Standard Micro-Raman Spectrometer

Published on: April 12, 2017

Main Results:

The CNN model demonstrated balanced performance, achieving high precision and recall.
The Transformer model showed poor localization precision under strict matching but performed comparably to CNNs under tolerance.
ResNets achieved the highest recall but with a higher false-positive rate.

Conclusions:

The proposed CNN-based framework provides a robust foundation for automated, real-time radionuclide identification.
Deep learning architectures offer potential for improved detection in complex radiological environments.
Model selection depends on the specific requirements for precision, recall, and localization accuracy.