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

You might also read

Related Articles

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

Sort by
Same author

Imaging foundation model for universal enhancement of non-ideal measurement CT.

Nature communications·2026
Same author

Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same author

Recent Advancements of Transcranial Direct Current Stimulation and Machine Learning: Methods, Challenges, and Opportunities.

Transactions on artificial intelligence·2026
Same author

Deep learning-based generation of synthetic multiphasic MRI in hepatocellular carcinoma and cirrhosis.

JHEP reports : innovation in hepatology·2026
Same author

Hematopoietic stem cells activate a latent differentiation pathway to facilitate recovery after 5-fluorouracil-induced myeloablation.

Developmental cell·2026
Same author

Hematopoietic stem cells activate a latent differentiation pathway to facilitate recovery after 5-fluorouracil-induced myeloablation.

Developmental cell·2026

Related Experiment Video

Updated: Dec 25, 2025

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin
09:36

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin

Published on: March 14, 2018

9.7K

Deep Learning Based High-Resolution Reconstruction of Trabecular Bone Microstructures from Low-Resolution CT Scans

Indranil Guha1, Syed Ahmed Nadeem1, Chenyu You2

  • 1Department of Electrical and Computer Engineering, College of Engineering, University of Iowa, Iowa City, IA 52242.

Proceedings of Spie--The International Society for Optical Engineering
|March 24, 2020
PubMed
Summary

This study introduces a deep learning method to enhance low-resolution CT scans for better osteoporosis assessment. The AI model improves trabecular bone microstructure imaging, aiding in fracture risk evaluation.

Keywords:
GAN-CIRCLEdeep learninghigh-resolution reconstructionmicrostructureosteoporosistrabecular bone

More Related Videos

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects
08:39

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Published on: June 24, 2025

477
A Sectioning, Coring, and Image Processing Guide for High-Throughput Cortical Bone Sample Procurement and Analysis for Synchrotron Micro-CT
07:10

A Sectioning, Coring, and Image Processing Guide for High-Throughput Cortical Bone Sample Procurement and Analysis for Synchrotron Micro-CT

Published on: June 12, 2020

5.4K

Related Experiment Videos

Last Updated: Dec 25, 2025

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin
09:36

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin

Published on: March 14, 2018

9.7K
Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects
08:39

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Published on: June 24, 2025

477
A Sectioning, Coring, and Image Processing Guide for High-Throughput Cortical Bone Sample Procurement and Analysis for Synchrotron Micro-CT
07:10

A Sectioning, Coring, and Image Processing Guide for High-Throughput Cortical Bone Sample Procurement and Analysis for Synchrotron Micro-CT

Published on: June 12, 2020

5.4K

Area of Science:

  • Biomedical Imaging
  • Osteoporosis Research
  • Artificial Intelligence in Medicine

Background:

  • Osteoporosis is a prevalent age-related condition marked by decreased bone density and increased fracture risk.
  • Trabecular bone (Tb) microstructural quality is crucial for bone strength and fracture prediction.
  • High-resolution CT scanners allow in vivo measurement of Tb microstructure, but resolution discrepancies necessitate data harmonization.

Purpose of the Study:

  • To present a deep learning-based method for reconstructing high-resolution trabecular bone microstructures from low-resolution CT scans.
  • To evaluate the effectiveness of the GAN-CIRCLE network in improving the accuracy of microstructural measures for osteoporosis assessment.
  • To address the challenge of resolution-dependence and scanner variability in CT-based bone studies.

Main Methods:

  • A deep learning network, GAN-CIRCLE, was developed for high-resolution reconstruction of trabecular bone microstructures.
  • The network was trained and validated using 9,000 low- and high-resolution CT scan patches from 10 volunteers.
  • Evaluation involved 5,000 patches from 9 different volunteers, comparing predicted high-resolution scans with true high-resolution scans.

Main Results:

  • The deep learning method significantly improved the structural similarity index between predicted and true high-resolution scans (p < 0.01).
  • Trabecular bone thickness and network area measures from predicted images showed higher agreement with true high-resolution CT values (CCC = [0.95, 0.91]) compared to low-resolution data (CCC = [0.72, 0.88]).
  • The method effectively enhanced the quantitative assessment of trabecular bone microstructural parameters.

Conclusions:

  • Deep learning-based high-resolution reconstruction of trabecular bone microstructures is feasible and effective.
  • This approach can harmonize data across different CT scanner resolutions, improving osteoporosis diagnosis and fracture risk assessment.
  • The GAN-CIRCLE method offers a promising solution for accurate in vivo analysis of bone microarchitecture.