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

Positron Emission Tomography01:29

Positron Emission Tomography

3.9K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
3.9K

You might also read

Related Articles

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

Sort by
Same author

Impact of deep learning denoising on kinetic modelling for low-dose dynamic PET: application to single- and dual-tracer imaging protocols.

European journal of nuclear medicine and molecular imaging·2025
Same author

Evaluation of cost-effective system designs for long axial field-of-view PET scanners.

Physics in medicine and biology·2023
Same author

Performance evaluation of the PennPET explorer with expanded axial coverage.

Physics in medicine and biology·2023
Same author

Total-body PET: a new paradigm for molecular imaging.

The British journal of radiology·2022
Same author

Time of Flight in Perspective: Instrumental and Computational Aspects of Time Resolution in Positron Emission Tomography.

IEEE transactions on radiation and plasma medical sciences·2021
Same author

PET/MRI for Primary Breast Cancer: A Match Made Better by PET Quantification?

Radiology. Imaging cancer·2021

Related Experiment Video

Updated: May 16, 2025

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking
14:21

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking

Published on: August 6, 2013

18.2K

Depth-of-interaction encoding techniques for pixelated PET detectors enabled by machine learning methods and fast

Bing Dai1, Srilalan Krishnamoorthy1, Emmanuel Morales2

  • 1Department of Radiology, The University of Pennsylvania, Philadelphia, PA 19104, United States of America.

Physics in Medicine and Biology
|April 4, 2025
PubMed
Summary

This study introduces a machine learning method to extract depth-of-interaction (DOI) information from existing positron emission tomography detectors without hardware changes. This technique enhances DOI classification accuracy, improving scanner performance.

Keywords:
depth-of-interaction (DOI)long short-term memory (LSTM)machine learning (ML)waveform sampling (WFS)

More Related Videos

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:31

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

179
High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals
11:09

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals

Published on: December 16, 2022

2.8K

Related Experiment Videos

Last Updated: May 16, 2025

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking
14:21

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking

Published on: August 6, 2013

18.2K
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
05:31

Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph

Published on: February 21, 2025

179
High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals
11:09

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals

Published on: December 16, 2022

2.8K

Area of Science:

  • Medical Imaging
  • Detector Physics

Background:

  • Commercial positron emission tomography (PET) scanners utilize pixelated detectors with single-ended readout, offering good energy and timing resolution but lacking depth-of-interaction (DOI) information.
  • DOI information is crucial for improving PET system performance, particularly in higher resolution and smaller ring diameter configurations.
  • Current methods for obtaining DOI typically require detector modifications, which can be costly and potentially degrade timing performance.

Purpose of the Study:

  • To develop and evaluate a novel technique for multi-level DOI classification in pixelated PET detectors.
  • To achieve DOI information extraction without altering existing detector designs.
  • To assess the impact of machine learning algorithms and waveform features on DOI classification accuracy.

Main Methods:

  • Utilized high-speed waveform sampling electronics (Domino Ring Sampler, DRS4) and machine learning (ML) to analyze scintillation waveforms.
  • Evaluated different multi-level DOI classification schemes by examining DOI positioning profiles and errors.
  • Investigated the influence of various ML algorithms, input features, and crystal configurations on DOI classification accuracy and detector timing performance.

Main Results:

  • 2- or 3-level DOI binning proved effective for 20 mm long crystals, with 2-level models achieving 95% class-wise and 83% overall accuracy.
  • 3-level DOI classification reached up to 90% class-wise accuracy for long and narrow crystals (2 × 2 × 20 mm³).
  • Long short-term memory networks and classical ML algorithms demonstrated comparable accuracy, with classical ML models requiring significantly less training time.

Conclusions:

  • This work presents a viable proof-of-concept for acquiring DOI information from commercial pixelated detectors without design modifications.
  • The developed ML-based approach offers an alternative for multi-level DOI classification, potentially avoiding performance degradation associated with hardware changes.
  • This technique could inspire future PET scanner designs that leverage DOI information for enhanced performance.