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

Autologous and allogeneic haematopoietic cell transplantation in adult patients with Hodgkin lymphoma: recommendations from the EBMT Practice Harmonisation and Guidelines Committee and Lymphoma Working Party.

The Lancet. Haematology·2026
Same author

Hodgkin lymphoma: EHA Clinical Practice Guidelines for diagnosis, treatment, and follow-up.

HemaSphere·2026
Same author

Less is more in primary cutaneous indolent B-cell lymphoma.

Blood·2026
Same author

Threshold Photoelectron Spectroscopy, Dissociative Photoionization, and Pyrolysis of Aziridine.

The journal of physical chemistry. A·2026
Same author

Infections in Patients With Cytokine Release Syndrome/Immune Effector Cell-Associated Neurotoxicity Syndrome Following Chimeric Antigen Receptor T-Cell Therapy.

Open forum infectious diseases·2026
Same author

Heart size on chest CT and its association with acute heart failure in the emergency department.

Danish medical journal·2026

Related Experiment Video

Updated: Oct 13, 2025

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant
05:18

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Published on: October 6, 2023

1.6K

RootPainter3D: Interactive-machine-learning enables rapid and accurate contouring for radiotherapy.

Abraham George Smith1,2, Jens Petersen1,2, Cynthia Terrones-Campos2,3

  • 1Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.

Medical Physics
|November 16, 2021
PubMed
Summary

Interactive-machine-learning significantly speeds up organ-at-risk contouring in radiotherapy. This method trains deep learning models with physician corrections, achieving high accuracy and substantial time savings compared to manual delineation.

Keywords:
X-ray CTdeep-learninginteractive-machine-learningsegmentation

More Related Videos

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.2K
Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
07:57

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

2.9K

Related Experiment Videos

Last Updated: Oct 13, 2025

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant
05:18

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Published on: October 6, 2023

1.6K
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.2K
Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
07:57

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

2.9K

Area of Science:

  • Medical Physics
  • Radiotherapy
  • Artificial Intelligence in Medicine

Background:

  • Organ-at-risk contouring is a critical yet time-consuming step in radiotherapy planning.
  • Existing deep learning methods often struggle with accuracy on diverse clinical data.
  • Interactive-machine-learning offers a potential solution to improve contouring efficiency and accuracy.

Purpose of the Study:

  • To investigate the accuracy and time-efficiency of an interactive-machine-learning approach for organ-at-risk contouring.
  • To evaluate the performance of a corrective-annotation strategy within a deep learning framework.

Main Methods:

  • An open-source interactive-machine-learning software was developed for corrective-annotation of deep learning-generated contours.
  • A physician contoured 933 hearts on X-ray CT images, iteratively correcting model predictions to retrain the assisting model.
  • Contouring time and accuracy were compared against manual delineations in Eclipse software for a subset of cases.

Main Results:

  • The interactive-machine-learning method achieved strong agreement with manual delineations, evidenced by a Dice score of 0.95.
  • Contouring time decreased significantly with increased annotation, reaching an average of 2 min 2 s per heart after 923 images.
  • This represents a substantial time saving compared to the 7 min 1 s required for manual contouring.

Conclusions:

  • Interactive-machine-learning with corrective-annotation offers a rapid and user-friendly method for training deep learning models.
  • This approach enables clinicians to segment structures effectively within routine radiotherapy workflows without extensive computer science expertise.
  • The study demonstrates the clinical viability of interactive-machine-learning for enhancing radiotherapy planning efficiency.