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: Feb 22, 2026

Whole-body PET/MRI of Pediatric Patients: The Details That Matter

Whole-body PET/MRI of Pediatric Patients: The Details That Matter

Published on: December 19, 2017

Deep Learning MR Imaging-based Attenuation Correction for PET/MR Imaging.

Fang Liu¹, Hyungseok Jang¹, Richard Kijowski¹

¹From the Department of Radiology, University of Wisconsin School of Medicine and Public Health, 600 Highland Ave, Madison, WI 53705-2275.

|September 20, 2017

Summary

This summary is machine-generated.

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

Mapping Fatty Acid Composition in the Human Knee: Short-Term Repeatability at 3T.

Journal of magnetic resonance imaging : JMRI·2026

Same author

The Potential Expertise Paradox in AI-Assisted Radiology.

Radiology·2026

Same author

Robust disease prognosis via diagnostic knowledge preservation: A sequential learning approach.

PloS one·2026

Same author

High-Resolution 2D versus 3D Lumbar Spine MRI Optimized with a Deep Learning Reconstruction Algorithm and Prototype Conformal Coil.

AJNR. American journal of neuroradiology·2026

Same author

Radiomics-based Differentiation of Recurrent Brain Metastases from Treatment Effects: A Multi-Institutional Comparative Study with Advanced Imaging.

Radiology. Imaging cancer·2026

Same author

ConTEXTual Net 3D: Vision-Language Modeling in PET/CT for Visual Grounding of Positive Findings.

Journal of imaging informatics in medicine·2026

Same journal

Erratum for: Prediction of Lobar Emphysema Progression with a CT-Based Foundational Model.

Radiology·2026

Same journal

Erratum for: Associations of MRI-derived Paraspinal IMAT and LMM with Cardiometabolic Risk Factors: Results from a German Cohort.

Radiology·2026

Same journal

Erratum for: Blue Rubber Bleb Nevus Syndrome.

Radiology·2026

Same journal

Redefining the Clinical Role of MRI in Endometrial Cancer Staging.

Radiology·2026

Same journal

To Ablate or Not to Ablate: The Colorectal Liver Metastasis Question.

Radiology·2026

Same journal

The Limits of Radiologic Categorization in Pulmonary Nonsolid Nodules.

Radiology·2026

See all related articles

Deep learning for magnetic resonance imaging-based attenuation correction (AC) in PET/MR imaging generates accurate pseudo CT scans. This deep MRAC approach significantly reduces PET reconstruction errors in brain imaging compared to existing methods.

Area of Science:

Medical Imaging
Artificial Intelligence
Radiology

Background:

Accurate attenuation correction (AC) is crucial for quantitative positron emission tomography (PET) imaging.
Traditional AC in PET/MR relies on CT scans, limiting simultaneous acquisition.
Deep learning offers a potential solution for MR-only AC.

Purpose of the Study:

To develop and assess a deep learning method for MR imaging-based AC in brain PET/MR.
To generate pseudo CT scans from MR images for AC using deep learning (deep MRAC).

Main Methods:

A deep convolutional auto-encoder network was trained on MR images to identify air, bone, and soft tissue.
The model was trained using retrospective PET/MR data coregistered with CT scans.
Prospective simultaneous PET/MR imaging was performed to evaluate the deep MRAC approach.

More Related Videos

MRI and PET in Mouse Models of Myocardial Infarction

MRI and PET in Mouse Models of Myocardial Infarction

Published on: December 19, 2013

Noninvasive In Vivo Small Animal MRI and MRS: Basic Experimental Procedures

Noninvasive In Vivo Small Animal MRI and MRS: Basic Experimental Procedures

Published on: October 20, 2009

Related Experiment Videos

Last Updated: Feb 22, 2026

Whole-body PET/MRI of Pediatric Patients: The Details That Matter

Whole-body PET/MRI of Pediatric Patients: The Details That Matter

Published on: December 19, 2017

MRI and PET in Mouse Models of Myocardial Infarction

MRI and PET in Mouse Models of Myocardial Infarction

Published on: December 19, 2013

Noninvasive In Vivo Small Animal MRI and MRS: Basic Experimental Procedures

Noninvasive In Vivo Small Animal MRI and MRS: Basic Experimental Procedures

Published on: October 20, 2009

Main Results:

Deep MRAC accurately generated pseudo CT scans with high Dice coefficients for air, soft tissue, and bone.
PET reconstruction errors were less than 1% in most brain regions using deep MRAC.
Deep MRAC demonstrated significantly lower PET reconstruction errors compared to Dixon-based and CT-template methods.

Conclusions:

An automated deep learning approach (deep MRAC) was developed to create pseudo CT scans from MR images for PET/MR AC.
Deep MRAC provides accurate AC and reduces PET reconstruction errors in brain imaging.
This deep learning-based MRAC is a promising alternative to CT-based AC in PET/MR studies.