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

Reasons for introducing self-intermittent urinary catheterization and long-term outcomes in individuals with multiple sclerosis: a retrospective study.

World journal of urology·2026
Same author

Do Uniform Fasting Instructions Lead to Reproducible Stomach Volumes in Patients Being Treated With Radiation to the Pancreas?

Practical radiation oncology·2026
Same author

Reduction of CT number location dependency using photon-counting detector CT and virtual monoenergetic imaging.

Physics in medicine and biology·2026
Same author

Inter-fraction monitoring of brain metastases resection cavities during fractionated stereotactic radiosurgery on the 0.35 T MRI-Linac.

Journal of radiosurgery and SBRT·2026
Same author

Prior information-based subtraction radiography for enhanced tumor visibility in image-guided radiotherapy.

Frontiers in oncology·2026
Same author

Polar-to-Radical Crossover in Catalyst-Free Olefin Halo-Hydroxylamination: A Direct Route to Multifunctional Electrophilic Hydroxylamines.

JACS Au·2026

Related Experiment Video

Updated: Mar 22, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.6K

A comparative study of automatic image segmentation algorithms for target tracking in MR-IGRT.

Yuan Feng1, Iwan Kawrakow, Jeff Olsen

  • 1Soochow University; Washington University School of Medicine; University of Texas at Austin. fengyuan@suda.edu.cn.

Journal of Applied Clinical Medical Physics
|April 14, 2016
PubMed
Summary

Accurate segmentation of organs and tumors is vital for MR-guided radiation therapy. Different algorithms show varying performance based on image contrast, with a combined approach recommended for optimal results.

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.6K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.8K

Related Experiment Videos

Last Updated: Mar 22, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.6K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.6K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.8K

Area of Science:

  • Medical Imaging
  • Radiation Oncology
  • Image Processing

Background:

  • On-board magnetic resonance (MR) image guidance enhances radiation therapy accuracy.
  • Real-time segmentation and tracking of regions of interest (ROIs) are critical for utilizing MR image guidance.
  • Evaluating segmentation algorithm performance is essential for advancing MR-guided radiotherapy (MR-IGRT).

Purpose of the Study:

  • To evaluate the performance of various segmentation algorithms on motion images acquired during MR-IGRT.
  • To compare automatic segmentation methods against manual contours for accuracy and efficiency.

Main Methods:

  • Motion images (4 frames/sec) from an MR-IGRT system were used.
  • Manual segmentation by an expert served as ground truth for kidney, bladder, duodenum, and liver tumor.
  • Algorithms evaluated: thresholding, fuzzy k-means (FKM), k-harmonic means (KHM), reaction-diffusion level set evolution (RD-LSE), and ViewRay treatment planning and delivery system (VR-TPDS).
  • Performance metrics included Dice coefficient and target registration error (TRE).

Main Results:

  • All methods successfully segmented bladder and kidney.
  • FKM, KHM, and VR-TPDS segmented liver tumor and duodenum.
  • Algorithm performance degraded with decreased image contrast, except for VR-TPDS.
  • Thresholding offered the fastest segmentation (<1 ms) for high-contrast images (kidney) with good accuracy (Dice=0.95).
  • VR-TPDS provided the best automatic contouring for low-contrast images.

Conclusions:

  • Image quality assessment prior to segmentation is recommended.
  • Combining different segmentation methods may optimize performance with on-board MR-IGRT systems.
  • Algorithm choice should consider image contrast and specific anatomical targets.