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

Segmenting Small Stroke Lesions with Novel Labeling Strategies.

Machine learning in clinical neuroimaging : 7th international workshop, MLCN 2024, held in conjunction with MICCAI 2024, Marrakesh, Morocco, October 10, 2024, proceedings. MLCN (Workshop) (7th : 2024 : Marrakesh, Morocco)·2026
Same author

STROKE LESION SEGMENTATION USING MULTI-STAGE CROSS-SCALE ATTENTION.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026
Same author

The edge visualization metric: Quantifying the improvement of lung SBRT target definition with 4D CBCT.

Journal of applied clinical medical physics·2025
Same author

Impact of Consensus Guidelines, Clinical Trials, and COVID-19 on Fractionation Practices for Node-negative Intact Breast Cancer.

American journal of clinical oncology·2025
Same author

Fat Suppression in Distal Extremity 3-T MRI Using Spectral Heterogeneity Adaptive Radiofrequency Pulses.

Radiology·2024
Same author

The Role of Axillary Lymph Node Dissection versus Sentinel Lymph Node Dissection in Breast Cancer Patients with Clinical N2b-N3c Disease Who Receive Adjuvant Radiotherapy.

Annals of surgical oncology·2024

Related Experiment Video

Updated: Apr 25, 2026

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

7.5K

Rapid Automated Target Segmentation and Tracking on 4D Data without Initial Contours.

Venkata V Chebrolu1, Daniel Saenz2, Dinesh Tewatia3

  • 1Department of Biomedical Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA ; Department of Human Oncology, University of Wisconsin-Madison, Madison, WI 53792, USA ; Wisconsin Institute of Medical Research, 1111 Highland Avenue, Madison, WI 53705, USA.

Radiology Research and Practice
|August 29, 2014
PubMed
Summary
This summary is machine-generated.

A new algorithm (MPSL) rapidly and automatically outlines gross tumor volumes (GTV) on four-dimensional CT scans for radiotherapy. This method offers comparable accuracy to existing techniques but significantly reduces planning time.

More Related Videos

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

333
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

3.6K

Related Experiment Videos

Last Updated: Apr 25, 2026

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

7.5K
Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

333
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

3.6K

Area of Science:

  • Medical Physics
  • Radiotherapy Technology
  • Image Analysis

Background:

  • Accurate delineation of gross target volume (GTV) is crucial for effective radiotherapy planning.
  • Four-dimensional computed tomography (4D CT) enables visualization of tumor motion during the respiratory cycle.
  • Current autosegmentation methods can be time-consuming, impacting workflow efficiency.

Purpose of the Study:

  • To develop and evaluate a novel Morphological Processing and Successive Localization (MPSL) algorithm for rapid automated GTV delineation.
  • To quantify changes in GTV volume and position using 4D CT for radiotherapy planning.
  • To compare the accuracy and speed of MPSL autosegmentation against state-of-the-art deformable registration methods.

Main Methods:

  • Implementation of novel MPSL algorithms for automated GTV segmentation.
  • Comparison of MPSL-generated contours with manual contours (ground-truth) and contours from deformable registration software (Elastix©, MIMVista).
  • Analysis of segmentation accuracy using Dice similarity coefficient, sensitivity, and positive predictive value (PPV).
  • Tracking of GTV motion using centroids estimated by MPSL and deformable registration methods.

Main Results:

  • MPSL algorithm achieved GTV segmentation in 27.0 ± 11.1 seconds per phase, significantly faster than deformable registration methods (142.3 ± 11.3 seconds per phase).
  • Dice coefficients for MPSL contours against ground-truth were 0.865 ± 0.037.
  • Dice coefficients for deformable registration contours against ground-truth were 0.909 ± 0.051.
  • MPSL accurately tracked target motion, comparable to deformable registration methods.

Conclusions:

  • The MPSL method provides a significant reduction in GTV segmentation time for radiotherapy planning.
  • MPSL demonstrates comparable segmentation accuracy to current state-of-the-art deformable registration techniques.
  • This automated approach enhances efficiency in radiotherapy planning workflows using 4D CT data.