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

Community-based tuberculosis screening with computer-aided detection technology alone and in combination with point-of-care C-reactive protein testing: a paired screen-positive trial.

The Lancet. Infectious diseases·2026
Same author

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026
Same author

Organ masks applied in feature space improve weakly supervised scan-level CT classification.

Scientific reports·2026
Same author

Assessment of modifications to a blind-sweep ultrasound protocol for improved lower-uterus imaging by novice operators.

Scientific reports·2026
Same author

From AI-based image analysis to surgical decision support in prostate cancer: interdisciplinary application of the international radiomics platform.

Frontiers in oncology·2026
Same author

A longitudinal whole-body CT dataset with manually annotated tumor lesions.

Scientific data·2026

Related Experiment Video

Updated: Oct 30, 2025

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

767

CNN-based lung CT registration with multiple anatomical constraints.

Alessa Hering1, Stephanie Häger2, Jan Moltz3

  • 1Fraunhofer Institute for Digital Medicine MEVIS, Maria-Goeppert-Str 3, Lübeck 23562, Germany; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, The Netherlands.

Medical Image Analysis
|July 3, 2021
PubMed
Summary

This study introduces a deep learning lung registration method that overcomes limitations of existing approaches. It achieves state-of-the-art accuracy and speed for medical image analysis.

Keywords:
Deep learningImage registrationKeypointsLung CTMultilevelVolume change control

More Related Videos

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.2K
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

1.4K

Related Experiment Videos

Last Updated: Oct 30, 2025

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

767
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.2K
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

1.4K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computational Anatomy

Background:

  • Deep learning registration offers speed but struggles with complex deformations and plausibility.
  • Conventional methods are accurate but slow, limiting clinical application.
  • Existing deep learning models often fail with large/small deformation superposition, producing artifacts.

Purpose of the Study:

  • To develop a deep learning lung registration method that matches conventional accuracy while improving speed.
  • To address limitations of existing deep learning registration, specifically handling complex deformations and ensuring plausible results.
  • To provide a robust and transferable deep learning solution for CT lung registration.

Main Methods:

  • A Gaussian-pyramid-based multilevel framework for coarse-to-fine optimization.
  • Incorporation of volume change penalty and curvature regularization to prevent foldings and ensure physiological validity.
  • Integration of keypoint correspondences to enhance alignment of smaller anatomical structures.

Main Results:

  • Achieved state-of-the-art results on the COPDGene dataset, outperforming conventional methods in accuracy and speed.
  • Demonstrated substantial improvements on DIRLab exhale-to-inhale lung registration, with TRE below 1.2 mm.
  • Validated accuracy, robustness, deformation field plausibility, and transferability through extensive evaluation.

Conclusions:

  • The developed deep learning method offers a fast and accurate alternative for CT lung registration.
  • The approach successfully handles complex deformations and ensures physiologically plausible results.
  • This method represents a significant advancement in medical image registration, with potential for clinical impact.