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

Loneliness within couples coping with cancer: prevalence, associations with physical and mental health, and potential benefits of dyadic exercise.

Frontiers in aging·2026
Same author

Everything the Light Touches: Radiation Oncology Access and Availability in the State of Oregon.

JCO global oncology·2026
Same author

No Association Between Radiation Dose and Clinical Outcomes in Merkel Cell Carcinoma in the Veteran Population.

Advances in radiation oncology·2026
Same author

Protocol for the internet-based lifestyle intervention to eradicate obese frailty in prostate cancer survivors (iLIVE) randomized controlled trial: a type I hybrid effectiveness implementation trial.

BMC cancer·2026
Same author

Molecular Imaging in Early Skin Cancer Detection: Advances, Limitations, and Future Directions.

Technology in cancer research & treatment·2025
Same author

Quantitative measurement using panretinal optical coherence tomography with three-dimensional curve distortion correction.

Biomedical optics express·2025
Same journal

Comparative treatment planning of photon, proton and carbon ion radiotherapy for sphenoid wing meningiomas.

Physics and imaging in radiation oncology·2026
Same journal

Development and validation of a knowledge-based model for robotic radiosurgery planning for brain lesions.

Physics and imaging in radiation oncology·2026
Same journal

Auto-segmentation of organs-of-interest clinical acceptability & reproducibility framework in head and neck cancer.

Physics and imaging in radiation oncology·2026
Same journal

A component-wise commissioning and validation framework for non-transit electronic portal imaging device patient-specific quality assurance.

Physics and imaging in radiation oncology·2026
Same journal

Optimization of field setup for organs at risk sparing and beam on time in breast radiotherapy planning for a new volumetric modulated arc therapy based treatment technique.

Physics and imaging in radiation oncology·2026
Same journal

An advanced automated pipeline for brain tumour segmentation on magnetic resonance imaging for gamma knife radiosurgery.

Physics and imaging in radiation oncology·2026
See all related articles

Related Experiment Video

Updated: Aug 9, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

472

Stress-testing pelvic autosegmentation algorithms using anatomical edge cases.

Aasheesh Kanwar1, Brandon Merz1, Cheryl Claunch2

  • 1Department of Radiation Medicine, Oregon Health and Sciences University, Portland, OR, United States.

Physics and Imaging in Radiation Oncology
|February 16, 2023
PubMed
Summary
This summary is machine-generated.

Commercial autosegmentation tools struggle with prostate cancer patients who have anatomical variations. These edge cases significantly reduce performance, highlighting a need for improved algorithms in real-world clinical settings.

Keywords:
Anatomical variabilityAutosegmentationDeep learningEdge caseProstate cancer

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
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

9.0K

Related Experiment Videos

Last Updated: Aug 9, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

472
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
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

9.0K

Area of Science:

  • Medical imaging
  • Radiology
  • Computational anatomy

Background:

  • Commercial autosegmentation software is increasingly used in clinical practice.
  • Real-world performance of these tools can be suboptimal, especially in specific patient populations.
  • Anatomical variations in patients may impact the accuracy of automated segmentation.

Purpose of the Study:

  • To evaluate the impact of anatomical variations on the performance of commercial autosegmentation tools for prostate cancer.
  • To compare the performance of different autosegmentation methods in the presence of anatomical edge cases.

Main Methods:

  • Identified 112 prostate cancer patients with anatomical variations (edge cases).
  • Utilized three commercial autosegmentation tools to segment pelvic anatomy.
  • Calculated Dice similarity coefficients (DSC), mean surface distance (MSD), and 95% Hausdorff distance (HD95) against clinician delineations.

Main Results:

  • Deep learning-based autosegmentation methods demonstrated superior performance compared to atlas-based and model-based approaches.
  • Autosegmentation performance was significantly reduced in patients with anatomical variations, showing a mean DSC reduction of 0.12 compared to a normal cohort.
  • All evaluated commercial tools experienced performance degradation with anatomical edge cases.

Conclusions:

  • Anatomical variations pose a significant challenge to the clinical utility of current commercial autosegmentation software.
  • Further development is needed to enhance the robustness of autosegmentation algorithms for diverse patient anatomies in prostate cancer treatment planning.