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

Definitive IMRT alone with reduced prophylactic nodal irradiation for Early-Stage Oropharyngeal Cancer: JCOG1208.

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

Ventilator Weaning Failure Induced by Oral Beraprost in a Patient after Femoral Endarterectomy: A Case Report.

Annals of vascular diseases·2026
Same author

Mental health stigma and legal responses to defendants with mental health conditions in Bulgaria, Japan, and Norway.

Frontiers in psychology·2026
Same author

Induction chemotherapy plus bevacizumab or radiotherapy in N2 non-squamous non-small cell lung cancer: 5-year results of a randomized phase 2 trial.

JTCVS open·2026
Same author

Robustness Comparison of the Virtual Bolus Method and Robust Optimization in Postmastectomy Radiation Therapy Using Volumetric Modulated Arc Therapy.

Cureus·2026
Same author

Credentialing of small-field dosimetry for the lung SBRT in Japan Clinical Oncology Group clinical trial.

Journal of applied clinical medical physics·2026
Same journal

Immunohistochemistry (IHC) Versus Genomic Profiling in Cancer: Roles in Precision Medicine.

Cureus·2026
Same journal

Pediatric Nasal Tip Reconstruction After a Donkey Bite Using an Expanded Paramedian Forehead Flap With Conchal Cartilage Grafts: A Case Report.

Cureus·2026
Same journal

Splenic Rupture: A Delayed and Rare Complication of Colonoscopy.

Cureus·2026
Same journal

Super-refractory Status Epilepticus in Febrile Infection-Related Epilepsy Syndrome Triggered by Influenza A: A Pediatric Case Report.

Cureus·2026
Same journal

Comparative Evaluation of Serum Peroxiredoxin 2 (PRDX2), Serum Peroxiredoxin 4 (PRDX4), and Plasma Methylated Septin 9 (mSEPT9) Levels Against Conventional Biomarkers for Early Detection of Colorectal Cancer: A Study Protocol.

Cureus·2026
Same journal

Inspiratory Muscle Training for Patients With Chronic Obstructive Pulmonary Disease: A Narrative Review.

Cureus·2026
See all related articles

Related Experiment Video

Updated: May 10, 2025

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

2.6K

Proposal for a Method for Assessing the Quality of an Updated Deep Learning-Based Automatic Segmentation Program.

Fumihiro Tomita1, Ryohei Yamauchi1, Shinobu Akiyama1

  • 1Department of Radiation Oncology, St. Luke's International Hospital, Tokyo, JPN.

Cureus
|April 28, 2025
PubMed
Summary
This summary is machine-generated.

Commercial deep learning segmentation (DLS) methods require reassessment after updates, as contour accuracy can degrade, impacting clinical workflows. A new validation method streamlines this quality assurance process.

Keywords:
auto-segmentationdeep learning (dl)radiation therapy (rt)radiation therapy contouringroi

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.3K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.3K

Related Experiment Videos

Last Updated: May 10, 2025

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

2.6K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.3K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.3K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Radiation Oncology

Background:

  • Deep learning-based automatic segmentation (DLS) methods are increasingly used in radiation oncology.
  • Regular software updates for DLS tools necessitate re-evaluation of their performance and accuracy.
  • Maintaining contour geometric accuracy is critical for effective radiation therapy planning.

Purpose of the Study:

  • To assess the geometric accuracy of contours generated by a commercial DLS method (AI-Rad Companion Organs RT) across different software versions.
  • To propose an efficient validation method for evaluating post-update DLS performance with reduced clinical burden.

Main Methods:

  • Evaluated contours for 28 organs across head and neck, chest, abdomen, and pelvic regions using computed tomography (CT) imaging.
  • Calculated Dice Similarity Coefficient, Hausdorff distance, and Mean Distance to Agreement between AI-delineated and radiation oncologist-defined contours.
  • Compared contour accuracy across AI-Rad Companion Organs RT versions VA30, VA50, and VA60.

Main Results:

  • Nine out of 28 evaluated contours did not meet predefined accuracy criteria.
  • Significant differences in contour accuracy were observed for the brain, rectum, and bladder across AI-Rad Companion Organs RT versions.
  • The rectum contour showed a notable decrease in quality post-update, with an increased Hausdorff distance.

Conclusions:

  • Commercial DLS methods require continuous quality reassessment, especially after software updates, to ensure contour geometric accuracy.
  • The proposed streamlined validation method can effectively evaluate post-update DLS performance while minimizing clinical workflow disruption.