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

Prognostic impact of KMT2A-PTD in acute myeloid leukemia in the NGS era: a multicenter retrospective study.

Annals of hematology·2026
Same author

[Utility of acute-phase cerebral blood flow single photon emission computed tomography (SPECT) for evaluating the pathophysiology of Bickerstaff brainstem encephalitis with decorticate posturing].

Rinsho shinkeigaku = Clinical neurology·2026
Same author

Invasive Aspergillus Sinusitis Masquerading as Hypertrophic Pachymeningitis Complicated by a Ruptured Infectious Internal Carotid Artery Aneurysm.

Internal medicine (Tokyo, Japan)·2026
Same author

Natalizumab Escalation Early in the Disease Course of Pediatric-Onset Multiple Sclerosis: Two Japanese Cases.

Pediatric neurology·2026
Same author

Prospective Clinical Outcomes of Cardiac Stereotactic Body Radiotherapy for Refractory Ventricular Tachycardia　- Insights From Dose Distribution in Survivors.

Circulation journal : official journal of the Japanese Circulation Society·2026
Same author

Combined inhibition of complement C5 and neonatal Fc receptor in refractory generalized myasthenia gravis: A report of two cases.

Journal of neuroimmunology·2026

Related Experiment Video

Updated: Nov 30, 2025

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy
08:17

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy

Published on: June 7, 2015

16.0K

Simulated four-dimensional CT for markerless tumor tracking using a deep learning network with multi-task learning.

Shinichiro Mori1, Ryusuke Hirai2, Yukinobu Sakata2

  • 1Research Center for Charged Particle Therapy, National Institute of Radiological Sciences, Inage-ku, Chiba 263-8555, Japan.

Physica Medica : PM : an International Journal Devoted to the Applications of Physics to Medicine and Biology : Official Journal of the Italian Association of Biomedical Physics (AIFB)
|November 14, 2020
PubMed
Summary

A deep neural network generates simulated 4DCT from 3DCT, enabling accurate markerless tumor tracking when 4DCT is unavailable. This accelerates treatment and improves accuracy for thoracoabdominal procedures.

Keywords:
Computer generatedMachine learningTargeted radiation therapyThree-dimensional imaging

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

8.3K
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

3.2K

Related Experiment Videos

Last Updated: Nov 30, 2025

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy
08:17

Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy

Published on: June 7, 2015

16.0K
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

8.3K
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

3.2K

Area of Science:

  • Medical Imaging
  • Radiotherapy
  • Artificial Intelligence

Background:

  • Markerless tumor tracking algorithms require 4D CT (4DCT) for model training.
  • 4DCT's inaccuracies and radiation dose limit its use in respiratory-gated treatment.
  • A deep neural network (DNN) was developed to generate 4DCT from 3DCT data.

Purpose of the Study:

  • To develop a DNN capable of synthesizing 4DCT data from 3DCT.
  • To evaluate the utility of DNN-generated 4DCT for markerless tumor tracking.
  • To assess the impact of simulated 4DCT on treatment accuracy.

Main Methods:

  • Trained a DNN on 2420 thoracic 4DCT datasets using a 3D convolutional autoencoder and deformable image registration.
  • Generated simulated 4DCT by transforming exhale 3DCT data with predicted deformation vector fields.
  • Compared markerless tumor tracking accuracy using original and simulated 4DCT datasets in 20 patients.

Main Results:

  • Diaphragmatic displacement in simulated 4DCT was comparable to original 4DCT (<1.3 mm difference).
  • Average tracking positional errors for simulated 4DCT were 0.56 mm (X), 0.65 mm (Y), and 0.96 mm (Z).
  • The DNN successfully generated usable simulated 4DCT data.

Conclusions:

  • A DNN can generate simulated 4DCT data suitable for markerless tumor tracking.
  • This approach enhances markerless tumor tracking when original 4DCT is not feasible.
  • The DNN facilitates faster markerless tumor tracking and improved treatment accuracy in thoracoabdominal radiotherapy.