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 Experiment Video

Updated: Dec 12, 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

3.2K

Variability and reproducibility in deep learning for medical image segmentation.

Félix Renard1,2, Soulaimane Guedria3,4, Noel De Palma3

  • 1Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG, 38000, Grenoble, France. felix.renard@univ-grenoble-alpes.fr.

Scientific Reports
|August 15, 2020
PubMed
Summary

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

Patient self-assessment and virtual visit-based treatment decisions in rheumatoid arthritis: results from the multicentre Telemedicine in Rheumatoid Arthritis trial.

EULAR rheumatology open·2026
Same author

An Information-Driven Approach for the Early Health Technology Sustainability Assessment and the Frugal Design of the Internet of Medical Things: An Exploratory Study of Wearable Activity Monitoring Devices.

JMIR mHealth and uHealth·2026
Same author

Impact of personalized coaching on the use of digital health interventions for movement therapy in rheumatology: a randomized controlled trial.

Scientific reports·2026
Same author

Whole body analysis of functional communities and topological features of gait with different speeds in Parkinson's disease.

Journal of neurology·2026
Same author

Association Between Freezing of Gait and Sleep Quality in People with Parkinson's Disease.

Brain sciences·2026
Same author

The Digital Exposome: A Life Course Framework for Health in the Digital Age.

Journal of medical Internet research·2026

Deep learning for medical image segmentation offers high accuracy but faces reproducibility challenges. This review identifies variability sources and proposes recommendations for reliable deep learning frameworks in clinical applications.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Medical image segmentation is crucial for clinical diagnosis, oncology, and surgery.
  • Deep learning algorithms surpass classical methods in segmentation accuracy.
  • Variability in deep learning techniques raises concerns about result reproducibility.

Purpose of the Study:

  • To provide an overview of variability sources in deep learning for medical image segmentation.
  • To understand the challenges and issues of reproducibility in this field.
  • To propose recommendations for enhancing the reliability of deep learning models.

Main Methods:

  • Literature review of deep learning for medical image segmentation.
  • Analysis of variability sources impacting reproducibility.

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

3.5K

Related Experiment Videos

Last Updated: Dec 12, 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

3.2K
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

3.5K
  • Development of recommendations for framework description, variability analysis, and result evaluation.

    • Main Results:

    • Identified key sources of variability in deep learning segmentation frameworks.
    • Highlighted the challenges in achieving reproducible results.
    • Proposed three core recommendations for improving reproducibility.

    Conclusions:

    • Addressing variability is essential for reliable deep learning in medical imaging.
    • Standardized frameworks, thorough analysis, and robust evaluation systems are needed.
    • Implementing these recommendations will enhance the clinical utility of deep learning segmentation.