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

Dosimetric analysis of post-radiotherapy sexual dysfunction in patients receiving definitive stereotactic body radiotherapy (SBRT) for prostate cancer: a secondary analysis of MIRAGE.

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

Computed Tomography-Guided and Magnetic Resonance-Guided Adaptive Radiotherapy for Gynecological Stereotactic Body Radiotherapy Treatments: A Dosimetry and Workflow Analysis.

Cureus·2026
Same author

Automated Assessment of Nondosimetric Aspects of Prostate Radiation Therapy Treatment Quality in a Large Plan Database.

Advances in radiation oncology·2026
Same author

Direct-to-Unit Stereotactic Magnetic Resonance Imaging-Guided Adaptive Radiation Therapy for Spine Metastasis.

International journal of radiation oncology, biology, physics·2025
Same author

Enhancing cyberattack resiliency through the radiotherapy backup and recovery dashboard tool.

Journal of applied clinical medical physics·2025
Same author

Stereotactic Intensity-modulated Radiotherapy After Radical Prostatectomy (SCIMITAR): 4-Year Outcomes of a Phase 2 Clinical Trial.

European urology·2025

Related Experiment Video

Updated: Oct 13, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

558

Machine-assisted interpolation algorithm for semi-automated segmentation of highly deformable organs.

Dishane C Luximon1, Yasin Abdulkadir1, Phillip E Chow1

  • 1Department of Radiation Oncology, David Geffen School of Medicine, University of California, Los Angeles, California, USA.

Medical Physics
|November 16, 2021
PubMed
Summary

Machine-assisted interpolation (MAI) improves auto-segmentation of deformable organs like the stomach and bowel in medical imaging. This method enhances accuracy and speed for radiotherapy workflows.

Keywords:
deep learningradiation therapysegmentation

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.1K
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.6K

Related Experiment Videos

Last Updated: Oct 13, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

558
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.1K
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.6K

Area of Science:

  • Medical Imaging
  • Radiotherapy
  • Computational Anatomy

Background:

  • Accurate auto-segmentation of highly deformable organs (HDOs) like the stomach and bowel is challenging due to anatomical variations.
  • Manual segmentation is time-consuming, posing a challenge for modern radiotherapy techniques.
  • Need for rapid and accurate HDO segmentation in image-guided radiation therapy.

Purpose of the Study:

  • To propose and evaluate a machine-assisted interpolation (MAI) algorithm for rapid and accurate segmentation of the stomach and bowel.
  • To utilize sparse manual delineations as prior information to guide segmentation.
  • To compare MAI performance against linear interpolation (LI) and fully automated segmentation (FAS).

Main Methods:

  • Developed a two-channel patch-based convolutional neural network (CNN) with a Dense-UNet architecture for boundary localization and organ segmentation.
  • Trained MAI algorithm separately for stomach (MRI) and bowel (CT) segmentation using sparse manual contours.
  • Compared MAI against LI and FAS using Dice Similarity Coefficient (DSC) and mean surface distance (MSD) metrics.

Main Results:

  • MAI achieved higher mean DSC (stomach: 0.91, bowel: 0.90) and lower average MSD (stomach: 0.77 mm, bowel: 0.93 mm) compared to LI and FAS.
  • MAI demonstrated superior robustness, with fewer predictions below DSC < 0.8 for both stomach (7%) and bowel (16%) segmentation.
  • All performance improvements of MAI over baseline methods were statistically significant (p < 0.001).

Conclusions:

  • The MAI algorithm significantly outperforms LI and FAS in accuracy and robustness for stomach and bowel segmentation.
  • MAI has the potential to expedite HDO delineation in radiation therapy workflows.
  • Current fully automated segmentation methods for HDOs still require substantial manual correction.