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

A Prospective Observational Study to Evaluate the Effectiveness of Platelet-Rich Plasma Therapy for Complex Wounds: Influential Clinical Variables on Wound Healing Outcomes.

Advances in wound care·2024
Same author

Use of Virtual Reality in the Reduction of Pain After the Administration of Vaccines Among Children in Primary Care Centers: Protocol for a Randomized Clinical Trial.

JMIR research protocols·2022
Same author

Functional connectivity alterations associated with literacy difficulties in early readers.

Brain imaging and behavior·2020
Same author

Social Networking App Use Among Primary Health Care Professionals: Web-Based Cross-Sectional Survey.

JMIR mHealth and uHealth·2018

Related Experiment Video

Updated: Aug 31, 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

2.9K

Interactive Medical Image Labeling Tool to Construct a Robust Convolutional Neural Network Training Data Set:

David Reifs1, Ramon Reig-Bolaño1, Marta Casals2

  • 1Digital Care Research Group, Centre for Health and Social Care, Universitat of Vic-Central University of Catalonia, Vic, Spain.

JMIR Medical Informatics
|August 22, 2022
PubMed
Summary
This summary is machine-generated.

A new, fast, and accurate method for labeling wound images significantly speeds up data preparation for neural network training. This tool improves efficiency, especially for untrained users, producing high-quality, indistinguishable results from expert labeling.

Keywords:
labelingmachine learningpressure ulcerswound assessmentwound tissue classification

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

488
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.3K

Related Experiment Videos

Last Updated: Aug 31, 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

2.9K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

488
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.3K

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in healthcare
  • Wound healing research

Background:

  • Skin ulcers are a global health concern, often resulting from complex conditions like diabetes and venous insufficiency.
  • Current wound assessment methods are rudimentary, leading to diagnostic errors and invasive patient procedures.
  • Accurate tissue classification in wounds is crucial for training convolutional neural networks (CNNs), but manual labeling is time-consuming and labor-intensive.

Purpose of the Study:

  • To implement an innovative, rapid, and precise method for annotating wound images.
  • To facilitate the training of neural networks for effective wound tissue classification.

Main Methods:

  • Development of a novel support tool for image annotation.
  • Evaluation of the tool's accuracy and reliability through comparative analysis.
  • Comparison of the tool's classification output against a digital gold standard created using image editing software.

Main Results:

  • High agreement was observed between the proposed method and the gold standard across various tissue types (e.g., background 0.9789, intact skin 0.9842, necrotic tissue 0.9871).
  • The developed tool demonstrated a significant increase in labeling speed, averaging 2.6 times faster than advanced image editing users.
  • The efficiency gains were even more pronounced when utilized by untrained users.

Conclusions:

  • The new annotation method substantially enhances the speed of wound sample labeling compared to traditional approaches.
  • The system produces labeled samples that are visually and quantitatively indistinguishable from those generated using the gold standard method.
  • This advancement streamlines the data preparation process for AI-driven wound analysis, improving accessibility and efficiency for healthcare professionals.