Jove
Visualize
Contact Us

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

An international study of factors affecting variability of dosimetry calculations, part 5: impact of segmentation methods.

EJNMMI physics·2026
Same author

Mitochondrial diseases: from molecular mechanisms to therapeutic advances.

Signal transduction and targeted therapy·2025
Same author

Social isolation and depressive symptoms among chinese older adults: Serial mediating roles of social support and resilience.

Geriatric nursing (New York, N.Y.)·2025
Same author

Mitochondria-Targeting Virus-Like Gold Nanoparticles Enhance Chemophototherapeutic Efficacy Against Pancreatic Cancer in a Xenograft Mouse Model.

International journal of nanomedicine·2025
Same author

Non-surgery strategy versus hepatectomy in hepatocellular carcinoma patients with complete response after conversion therapy: a meta-analysis.

World journal of surgical oncology·2024
Same author

Epigenome-Wide and Methylation Risk Score Analysis of Body Mass Index Among People with HIV.

Epigenomes·2024
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 Experiment Video

Updated: Dec 5, 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

1.6K

Generating anthropomorphic phantoms using fully unsupervised deformable image registration with convolutional neural

Junyu Chen1,2, Ye Li1,2, Yong Du2

  • 1Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, 21287, USA.

Medical Physics
|October 20, 2020
PubMed
Summary

This study introduces a new deep learning method to create highly detailed computerized phantoms for medical imaging. The novel approach significantly improves phantom realism and similarity to patient scans.

Keywords:
computerized Phantomconvolutional Neural Networksdeep Neural Networksimage Registrationmedical Image Simulation

More Related Videos

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

894
Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
07:34

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

17.8K

Related Experiment Videos

Last Updated: Dec 5, 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

1.6K
Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

894
Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
07:34

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

17.8K

Area of Science:

  • Medical Imaging
  • Computational Anatomy
  • Artificial Intelligence in Medicine

Background:

  • Computerized phantoms are essential for nuclear medicine imaging system optimization and validation.
  • Existing phantoms lack the anatomical detail and variation found in human patients.
  • Accurate phantoms are crucial for advancing medical imaging research and applications.

Purpose of the Study:

  • To develop a novel registration-based method for generating highly anatomically detailed computerized phantoms.
  • To improve the anatomical accuracy and realism of digital phantoms for medical imaging simulations.
  • To enhance the similarity between generated phantoms and patient-specific anatomy.

Main Methods:

  • A deep-learning-based unsupervised registration method was proposed to warp an existing phantom (XCAT) to a patient CT scan.
  • The method utilized a novel SSIM-based unsupervised objective function and analyzed the tradeoff between image similarity and deformation regularization.
  • Ablation studies compared the proposed method against state-of-the-art unsupervised registration techniques.

Main Results:

  • The proposed method achieved superior performance compared to state-of-the-art methods (SyN, VoxelMorph) in terms of image similarity (SSIM) and mean squared error (MSE).
  • Generated phantoms exhibited high anatomical detail, closely resembling patient images.
  • Quantitative improvements included over 8% higher SSIM and less than 30% lower MSE.

Conclusions:

  • A novel deep learning method effectively creates highly realistic anthropomorphic phantoms with anatomical labels.
  • These phantoms can serve as a basis for modeling organ properties and realistic medical imaging simulations.
  • The developed method holds significant potential for various applications in medical imaging research and development.