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: Jun 25, 2026

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

Impact on Cost and Expert Time of Data-Efficient Deep Learning for Medical Image Segmentation.

Astha Jaiswal1, Miriam Rinneburger1, Franziska Meyer1

  • 1Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str 62, 50937 Cologne, Germany.

Radiology. Artificial Intelligence
|June 24, 2026
PubMed

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

Primary hyperoxaluria type 1-current practice in the siRNA era: an ERA Genes & Kidney Working Group survey.

Clinical kidney journal·2026
Same author

Gut decisions based on the liver: prediction of colorectal neoplasia using AI-based liver analysis of routine CT scans.

Frontiers in oncology·2026
Same author

Radiologists' memory as a data protection risk: a worst-case stress test for chest radiograph re-identification.

Insights into imaging·2026
Same author

Hereditary kidney tumor syndromes: structured evaluation of a questionnaire-based approach.

Clinical kidney journal·2026
Same author

An in-depth analysis of the molecular changes induced by short-term calorie restriction before living kidney donation.

npj aging·2026
Same author

The Interplay between Gut Microbiota and Diet-Induced Kidney Protection.

Kidney360·2026
Summary

An expert-guided annotation loop significantly reduces expert time for medical image segmentation, offering substantial cost savings and enabling efficient, high-quality reference standard creation for CT and MRI scans.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Radiology

Background:

  • Accurate medical image segmentation is crucial for diagnosis and treatment planning.
  • Manual segmentation is time-consuming and requires expert radiologist input.
  • Developing efficient annotation strategies is vital for advancing AI in medical imaging.

Purpose of the Study:

  • To develop and evaluate an iterative training approach, the expert-guided annotation loop, for efficient medical image segmentation.
  • To assess two sample-selection strategies (random and active learning) within this loop.
  • To evaluate the real-world clinical implementation and cost-effectiveness of this approach.

Main Methods:

  • A retrospective study involving ten datasets (1948 CT/MRI exams) across five disease areas.
Keywords:
Artificial IntelligenceCTHuman-in-the-Loop Machine LearningMRIMedical Image Segmentation

Related Experiment Videos

Last Updated: Jun 25, 2026

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

  • Iterative training of nnU-Net models using the expert-guided annotation loop with expert correction of presegmentations.
  • Measurement of expert time, model performance (Dice scores), and cost savings estimation.

    • Main Results:

    • Trained 57 segmentation models with Dice scores ranging from 0.64-0.97.
    • Achieved maximum expert time savings of 90.3% for kidney and 48.2% for tumor segmentation.
    • Demonstrated feasibility of no-code implementation and estimated cost savings per examination.

    Conclusions:

    • The expert-guided annotation loop efficiently produces high-quality reference standard medical image segmentations.
    • This approach significantly reduces expert annotation time and offers potential cost savings.
    • The no-code workflow is feasible for clinical implementation in medical imaging.