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

Colorectal anastomotic safety assessment using ICG fluorescence and flexible endoscopy (COLOSSEUM): a global survey of 1367 surgeons.

Surgical endoscopy·2026
Same author

Engineered natural extracellular matrix platform for modelling skin diseases and identifying therapeutic targets.

Journal of advanced research·2026
Same author

Snail anaphylaxis is not only asthma.

European annals of allergy and clinical immunology·2026
Same author

AI Models to Reduce Surgical Complications Through Intraoperative Video Analysis: Protocol for a Prospective Cohort Study.

JMIR research protocols·2026
Same author

Are intertidal habitats keeping up with nutrient export? Insights from modelling climate and management scenarios.

The Science of the total environment·2025
Same author

Development of a platform-specific objective assessment tool for the accreditation of robotic setup and docking.

Surgical endoscopy·2025

Related Experiment Video

Updated: Jan 13, 2026

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

3.7K

Benchmarking variability in semantic segmentation in minimally invasive abdominal surgery.

L T Castro1, C Barata2, P Martins3

  • 1General Surgery Department, Hospital Prof. Dr. Fernando Fonseca, Lisbon, Portugal. laura.castro@ulsasi.min-saude.pt.

International Journal of Computer Assisted Radiology and Surgery
|January 6, 2026
PubMed
Summary

Surgical residents showed strong agreement when segmenting abdominal organs using MedSAM, with consistent overall shapes but some variability in precise boundary delineation. This study sets a benchmark for future anatomical annotation efforts.

Keywords:
Abdominal anatomyAgreementSemantic segmentationSurgery

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

732
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

3.3K

Related Experiment Videos

Last Updated: Jan 13, 2026

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

3.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

732
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

3.3K

Area of Science:

  • Medical Imaging
  • Surgical Anatomy
  • Artificial Intelligence in Medicine

Background:

  • Accurate anatomical identification in abdominal surgery is challenging due to subjective interpretations and unclear structure boundaries.
  • Semantic segmentation of surgical anatomy requires precise boundary identification, yet its uncertainty is not well-defined.
  • Assessing annotation adequacy is crucial given the subjective nature of anatomical identification.

Purpose of the Study:

  • To evaluate the variability in anatomical structure identification and semantic segmentation using MedSAM among surgical residents.
  • To assess annotation adequacy in the context of surgical resident performance with AI-assisted segmentation.
  • To establish a benchmark for MedSAM's utility in segmenting intraperitoneal organs.

Main Methods:

  • Surgery residents performed semantic segmentation of abdominal organs (abdominal wall, colon, liver, small bowel, spleen, stomach, gallbladder) using MedSAM on images from the Dresden Surgical Anatomy and Endoscapes2023 datasets.
  • Multiple sets of annotations (3-4 per class) were generated for each anatomical structure.
  • Inter-annotator variability was quantified using Dice Similarity Coefficient (DSC), Intraclass Correlation Coefficient (ICC), Boundary IoU (BIoU), and Fleiss' kappa, with consensus masks generated via the Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm.

Main Results:

  • Strong inter-annotator agreement was observed, with DSC values ranging from 0.84 to 0.95 and Fleiss' kappa between 0.85 and 0.91.
  • Surface area reliability was good to excellent (ICC = 0.62-0.91).
  • Boundary delineation exhibited lower reproducibility, indicated by BIoU values of 0.092-0.157, though STAPLE consensus masks showed consistent overall shape annotations.

Conclusions:

  • MedSAM demonstrated low variability in semantic segmentation of intraperitoneal organs by surgical residents during minimally invasive abdominal surgery.
  • While overall agreement is strong, challenges in boundary precision persist, particularly for complex or variable anatomical structures.
  • The findings provide a benchmark for future annotation efforts on larger datasets and more detailed anatomical features.