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

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

Hypofractionated Proton Reirradiation for Recurrent Glioblastoma: Clinical and Dosimetric Outcomes from a Large Single Institution Series.

International journal of radiation oncology, biology, physics·2026

Same author

FAST-02: Results from the second in-human prospective evaluation of single-fraction proton FLASH for symptomatic thoracic bone metastases.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2026

Same author

Mature Outcomes of 61.2 Gy Concomitant Boost Thoracic Radiation Therapy in Limited-Stage Small Cell Lung Cancer: CALGB 30610 (Alliance)/RTOG 0538.

International journal of radiation oncology, biology, physics·2026

Same author

Computational pathology features of immune architecture predict clinically relevant outcomes in small-cell lung cancer (SCLC).

NPJ precision oncology·2026

Same author

The KRAS-Variant and Cetuximab in HPV-Positive Oropharyngeal Cancer: Results from the NRG/RTOG 1016 Trial.

Cancer research communications·2026

Same author

Changes in Cardiac Function in Patients Receiving Radiation Therapy for Lung Cancer.

Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer·2026

Search research articles

Related Experiment Video

Updated: Dec 29, 2025

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

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

Published on: November 23, 2019

LungRegNet: An unsupervised deformable image registration method for 4D-CT lung.

Yabo Fu¹, Yang Lei¹, Tonghe Wang¹

¹Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA.

Medical Physics

|February 5, 2020

Summary

This summary is machine-generated.

This study introduces LungRegNet, an unsupervised deep learning method for fast and accurate four-dimensional computed tomography (4D-CT) lung image registration. LungRegNet achieves superior accuracy compared to existing deep learning methods for 4D-CT lung image analysis.

Keywords:

4D-CT lung deep learning deformable image registration unsupervised learning

More Related Videos

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

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

Published on: April 12, 2024

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

Related Experiment Videos

Last Updated: Dec 29, 2025

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

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

Published on: November 23, 2019

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

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

Published on: April 12, 2024

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

Area of Science:

Medical imaging
Radiology
Artificial intelligence in medicine

Background:

Four-dimensional computed tomography (4D-CT) is crucial for lung imaging, enabling motion-compensated analysis.
Accurate deformable image registration (DIR) is essential for processing 4D-CT data, but conventional methods can be slow.
Deep learning offers potential for rapid and accurate DIR, particularly for complex lung motion.

Purpose of the Study:

To develop an unsupervised, deep learning-based method for fast and accurate deformable image registration (DIR) of 4D-CT lung images.
To enhance registration accuracy and robustness for lung imaging applications.
To achieve high computational speed in the DIR process.

Main Methods:

Proposed LungRegNet, an unsupervised deep learning model comprising CoarseNet and FineNet subnetworks for multi-scale motion prediction.
Employed a generator-discriminator architecture within each subnetwork to predict the deformation vector field (DVF) and ensure image realism.
Integrated pulmonary vessel enhancement to improve registration accuracy by providing structural priors.

Main Results:

LungRegNet demonstrated superior registration accuracy compared to other deep learning methods on DIRLAB datasets, with a mean Target Registration Error (TRE) of 1.59 ± 1.58 mm.
Achieved comparable accuracy to conventional DIR methods, with TRE below 2 mm on internal datasets (1.00 ± 0.53 mm).
The combination of discriminator and vessel enhancement was critical for achieving high accuracy in 4D-CT lung DIR.

Conclusions:

An unsupervised deep learning method, LungRegNet, was successfully developed for rapid and accurate 4D-CT lung image registration.
LungRegNet outperformed existing deep-learning-based methods in terms of registration accuracy (TRE).
The method shows significant promise for improving lung image analysis workflows.