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

Imaging Studies III: Computed Tomography01:27

Imaging Studies III: Computed Tomography

DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...

You might also read

Related Articles

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

Sort by
Same author

Towards a general-purpose foundation model for functional MRI analysis.

Nature biomedical engineering·2026
Same author

Correction: NK-92 cells labeled with Fe<sub>3</sub>O<sub>4</sub>-PEG-CD56/Avastin@Ce6 nanoprobes for the targeted treatment and noninvasive therapeutic evaluation of breast cancer.

Journal of nanobiotechnology·2026
Same author

An <sup>124</sup>I-radiolabeled exosome-based treatment platform for enhanced boron neutron capture therapy: precise delivery and real-time PET tracking of boron.

Nanoscale·2026
Same author

Neural network-aided unsupervised input function estimation for dual-time-window PET Patlak analysis.

EJNMMI physics·2025
Same author

Design and Performance Assessment of a High-Resolution Small-Animal PET System.

Bioengineering (Basel, Switzerland)·2025
Same author

A Radiofluorinated Nanobody PET Tracer to Dynamically Visualize Differential Nectin4 Expression <i>In Vivo</i>.

Journal of medicinal chemistry·2025

Related Experiment Video

Updated: May 27, 2026

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

3.3K

Modality-projection universal model for comprehensive full-body medical imaging segmentation.

Yixin Chen1, Lin Gao2, Yajuan Gao3,4

  • 1Institute of Medical Technology, Peking University Health Science Center, Peking University, Beijing, China.

Nature Communications
|October 24, 2025
PubMed
Summary
This summary is machine-generated.

A new universal deep learning model, the Modality Projection Universal Model (MPUM), adapts to various medical imaging types for advanced organ segmentation and analysis. This framework enhances diagnostic speed and uncovers crucial brain-body metabolic links.

More Related Videos

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
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.5K

Related Experiment Videos

Last Updated: May 27, 2026

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

3.3K
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
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.5K

Area of Science:

  • Artificial Intelligence in Medicine
  • Medical Imaging Analysis
  • Computational Biology

Background:

  • Deep learning significantly advances medical imaging but struggles with multi-modality variability.
  • Universal models are needed to overcome inter-modality differences in medical imaging.

Purpose of the Study:

  • To introduce the Modality Projection Universal Model (MPUM) for adaptable, multi-modal medical image analysis.
  • To achieve state-of-the-art whole-body organ segmentation and explore brain-body metabolic correlations.

Main Methods:

  • Developed MPUM using a modality-projection strategy trained on 861 subjects.
  • Implemented a controller-based convolutional layer for saliency map visualization.
  • Applied the model for whole-body organ segmentation and metabolic correlation analysis.

Main Results:

  • MPUM achieved state-of-the-art whole-body organ segmentation, aiding computer-aided diagnosis.
  • The model demonstrated enhanced interpretability through saliency maps.
  • MPUM revealed metabolic correlations along the brain-body axis and within brain regions.

Conclusions:

  • MPUM offers a universal framework for accelerating diagnosis and large-scale imaging analysis.
  • The model bridges anatomical and metabolic information for integrative brain-body research.
  • MPUM facilitates the discovery of cross-organ disease mechanisms.