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 authorSame journal

Evaluating FlexTail: a wearable device for spinal posture tracking.

Biomedizinische Technik. Biomedical engineering·2026
Same author

Wearable Devices for Remote Monitoring of Chronic Diseases: Systematic Review.

JMIR mHealth and uHealth·2026
Same author

Wearable Spine Tracker vs. Video-Based Pose Estimation for Human Activity Recognition.

Sensors (Basel, Switzerland)·2025
Same author

Multi-species probiotic supplement enhances vagal nerve function - results of a randomized controlled trial in patients with depression and healthy controls.

Gut microbes·2025
Same author

Explainable AI associates ECG aging effects with increased cardiovascular risk in a longitudinal population study.

NPJ digital medicine·2025
Same author

AI and machine learning in medical imaging: key points from development to translation.

BJR artificial intelligence·2024

Related Experiment Video

Updated: Jul 7, 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

2.8K

Crowdsourcing image segmentation for deep learning: integrated platform for citizen science, paid microtask, and

Nicolai Spicher1, Tim Wesemeyer1, Thomas M Deserno1

  • 1Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Braunschweig, Lower Saxony, Germany.

Biomedizinische Technik. Biomedical Engineering
|December 25, 2023
PubMed
Summary

Citizen science, paid microtasks, and gamification were compared for medical image segmentation using a novel crowdsourcing platform. Citizen science achieved the highest accuracy, demonstrating crowdsourcing

Keywords:
crowdsourcingdeep learningimage segmentationplatform

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.6K

Related Experiment Videos

Last Updated: Jul 7, 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

2.8K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.6K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Human-Computer Interaction

Background:

  • Accurate medical image segmentation is vital but hindered by data scarcity and observer variability.
  • Deep learning shows promise but requires large, annotated datasets.
  • Crowdsourcing offers a potential solution by leveraging non-expert contributions.

Purpose of the Study:

  • To compare the effectiveness of different crowdsourcing models for medical image segmentation.
  • To evaluate a novel crowdsourcing platform integrating citizen science, paid microtasks, and gamification.
  • To assess the accuracy of crowdsourced segmentations and the generalizability of models trained on such data.

Main Methods:

  • Developed a crowdsourcing platform supporting citizen science, paid microtasks, and gamification.
  • Used sclera segmentation in fundus images as a proof-of-concept.
  • Analyzed accuracy of crowdsourced masks and deep learning model generalization.

Main Results:

  • Citizen science yielded the highest median F-score (82.2%) for segmentation accuracy.
  • Consensus masks improved gamification results (78.3%).
  • Deep learning models trained on crowdsourced data showed good generalizability, with F-scores ranging from 73.5% to 80.0%.

Conclusions:

  • The developed platform effectively supports diverse crowdsourcing approaches for medical image segmentation.
  • Citizen science emerged as a highly effective crowdsourcing model.
  • The platform will be released as open-source software to benefit the research community.