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

Manual Segmentation of the Human Choroid Plexus Using Brain MRI
04:25

Manual Segmentation of the Human Choroid Plexus Using Brain MRI

Published on: December 15, 2023

Evaluation of uterine cervix segmentations using ground truth from multiple experts.

Shiri Gordon1, Shelly Lotenberg, Rodney Long

  • 1Biomedical Engineering Department, Faculty of Engineering, Tel Aviv University, Tel-Aviv 69978, Israel.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|February 17, 2009
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

Mitigating hallucinations in synthesized clinical texts to improve multimodal deep learning for dermatology.

Journal of biomedical informatics·2026
Same author

Multimodal Learning with Privileged Report Supervision for Generalizable Tuberculosis Detection on Chest Radiographs.

Journal of medical systems·2026
Same author

Oral Cancer Detection By Using Tabular Data Synthesis and Classification.

Proceedings ... ICDM workshops. IEEE International Conference on Data Mining·2026
Same author

Assessment of Abdominal Adiposity in OSA Using Combined PET Imaging and MRI: Impact of Short-Term CPAP.

Chest·2026
Same author

Artificial Intelligence-Based Diagnosis of Kaposi Sarcoma Using Digital Photographs in Dark-Skinned Patients in Uganda.

JCO global oncology·2026
Same author

Topical treatment for high-risk human papillomavirus: evidence gap persists.

International journal of gynecological cancer : official journal of the International Gynecological Cancer Society·2026

This study generated a reliable ground truth (GT) segmentation for cervigrams using expert data. This GT map helps assess segmentation complexity and evaluate automated algorithm performance.

Area of Science:

  • Medical Imaging Analysis
  • Computational Pathology
  • Digital Health

Background:

  • The National Cancer Institute (NCI) collected a large dataset of digital cervigrams.
  • Manual segmentation of medical images by multiple experts is crucial for establishing ground truth.
  • Assessing segmentation complexity and algorithm performance requires a reliable ground truth.

Purpose of the Study:

  • To automatically generate a multi-expert ground truth (GT) segmentation map for cervigrams.
  • To define and utilize a measure of segmentation complexity based on inter-observer variability.
  • To develop and apply an accuracy measure for evaluating automated segmentation algorithms.

Main Methods:

  • Utilized the STAPLE (Simultaneous Truth and Performance Level Estimation) algorithm to generate a multi-expert GT segmentation map from 939 cervigrams.

More Related Videos

Laparoscopic Extracorporeal Knot-Tying for Uterine Vessel Occlusion during Hysterectomy with Cervical Cerclage in Large Uteri
05:21

Laparoscopic Extracorporeal Knot-Tying for Uterine Vessel Occlusion during Hysterectomy with Cervical Cerclage in Large Uteri

Published on: September 12, 2025

Related Experiment Videos

Last Updated: Jun 25, 2026

Manual Segmentation of the Human Choroid Plexus Using Brain MRI
04:25

Manual Segmentation of the Human Choroid Plexus Using Brain MRI

Published on: December 15, 2023

Laparoscopic Extracorporeal Knot-Tying for Uterine Vessel Occlusion during Hysterectomy with Cervical Cerclage in Large Uteri
05:21

Laparoscopic Extracorporeal Knot-Tying for Uterine Vessel Occlusion during Hysterectomy with Cervical Cerclage in Large Uteri

Published on: September 12, 2025

  • Defined a novel segmentation complexity measure based on inter-observer variability within the GT map.
  • Developed an accuracy measure to evaluate automated segmentation algorithms, applied to cervix boundary detection.

    • Main Results:

    • Successfully generated a multi-expert GT segmentation map for cervigrams.
    • Introduced a new measure to quantify segmentation task complexity, identifying challenging images for experts.
    • Presented an accuracy metric that effectively reflects the performance of automated segmentation algorithms, demonstrated by comparing two cervix boundary detection methods.

    Conclusions:

    • The developed methods for GT generation, complexity assessment, and performance evaluation are generalizable to various medical imaging segmentation tasks.
    • The study provides a robust framework for analyzing and validating automated segmentation in medical imaging, using cervigrams as a case study.
    • The findings contribute to the advancement of automated analysis in digital pathology and medical image repositories.