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

Distance Corrections01:15

Distance Corrections

60
To achieve precise distance measurements, especially in surveying and construction, certain corrections must be applied to account for potential sources of error like the standardization errors, temperature variations, and slope adjustments.Standardization error emerges when measurement equipment undergoes changes, such as wear, repairs, or weather impacts. To address this, surveyors compare the equipment’s readings to a standard. This process identifies any deviation that might lead to...
60

You might also read

Related Articles

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

Sort by
Same author

MRI-based gross tumor volume delineation in high-grade glioma using a deep convolutional neural network.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2026
Same author

Evaluating and Mitigating Carbon Dioxide Equivalent Emissions in Stroke Management: A Modeling Study.

Journal of the American Heart Association·2026
Same author

AI-augmented thyroid scintigraphy for robust classification of disease.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2026
Same author

Cycle-dependent variation of tumor absorbed dose rates in<sup>177</sup>Lu-DOTATATE therapies.

Biomedical physics & engineering express·2026
Same author

Beyond the tumor: recurrence-prone radiomics for prognostication in negative PSMA PET/CT scans of prostate cancer.

Biomedical physics & engineering express·2026
Same author

Kernel-based Maximum likelihood reconstruction of attenuation and activity (MLAA) in SPECT imaging for improved attenuation correction and activity quantification: Simulation, phantom and patient validation studies.

Physics in medicine and biology·2026

Related Experiment Video

Updated: Aug 17, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.2K

Decentralized collaborative multi-institutional PET attenuation and scatter correction using federated deep learning.

Isaac Shiri1, Alireza Vafaei Sadr2,3, Azadeh Akhavan1

  • 1Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva 4, Switzerland.

European Journal of Nuclear Medicine and Molecular Imaging
|December 12, 2022
PubMed
Summary
This summary is machine-generated.

Federated learning (FL) enables deep learning (DL) models for PET attenuation correction and scatter compensation (AC/SC) without data sharing. FL models achieved performance comparable to centralized methods, outperforming center-based approaches.

Keywords:
Attenuation correctionDeep learningDistributed learningFederated learningPET

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

2.9K
Highly Multiplexed, Super-resolution Imaging of T Cells Using madSTORM
08:43

Highly Multiplexed, Super-resolution Imaging of T Cells Using madSTORM

Published on: June 24, 2017

7.5K

Related Experiment Videos

Last Updated: Aug 17, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.2K
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

2.9K
Highly Multiplexed, Super-resolution Imaging of T Cells Using madSTORM
08:43

Highly Multiplexed, Super-resolution Imaging of T Cells Using madSTORM

Published on: June 24, 2017

7.5K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare

Background:

  • Quantitative Positron Emission Tomography (PET) imaging relies on accurate attenuation correction and scatter compensation (AC/SC).
  • Deep learning (DL) methods show promise for AC/SC, but require large, diverse datasets, which are challenging to aggregate due to privacy concerns.
  • Federated learning (FL) offers a solution for training DL models across multiple centers without direct data sharing.

Purpose of the Study:

  • To develop and evaluate DL-based AC/SC models using FL in a multicenter setting.
  • To compare the performance of FL models against centralized and center-based training strategies.

Main Methods:

  • Utilized a dataset of 300 patients from 6 centers with varying PET/CT scanner protocols.
  • Employed a modified nested U-Net architecture for AC/SC.
  • Evaluated two FL models (sequential and parallel) against centralized (data pooling) and center-based (local training) approaches.

Main Results:

  • FL models demonstrated excellent agreement with the centralized framework, with lower absolute relative errors (ARE%) compared to center-based models.
  • No significant performance difference was found between centralized and FL-based algorithms (p > 0.05).
  • Voxel-wise comparisons showed similar performance (R² values of 0.93-0.94) for FL and centralized models, significantly outperforming center-based models (R² = 0.74).

Conclusions:

  • FL-based DL models achieve high performance for PET AC/SC, comparable to centralized methods and superior to center-based approaches.
  • The FL framework effectively leverages the generalizability of DL models for AC/SC without necessitating direct data sharing.
  • This study provides strong evidence for the feasibility and effectiveness of FL in multicenter PET imaging research.