Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Characterizing and Optimizing Rater Performance for Internet-based Collaborative Labeling.

Joshua A Stein¹, Andrew J Asman, Bennett A Landman

¹Electrical Engineering, Vanderbilt University, Nashville, TN, USA 37235.

Proceedings of Spie--The International Society for Optical Engineering

|August 23, 2011

Summary

This summary is machine-generated.

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

Applying the Algorithm "Assessing Quality Using Image Registration Circuits" (AQUIRC) to Multi-Atlas Segmentation.

Proceedings of SPIE--the International Society for Optical Engineering·2025

Same author

Nucleus subtype classification using inter-modality learning.

Proceedings of SPIE--the International Society for Optical Engineering·2024

Same author

Inter-vendor harmonization of CT reconstruction kernels using unpaired image translation.

Proceedings of SPIE--the International Society for Optical Engineering·2024

Same author

Integration of estimated regional gene expression with neuroimaging and clinical phenotypes at biobank scale.

PLoS biology·2024

Same author

Deep network and multi-atlas segmentation fusion for delineation of thigh muscle groups in three-dimensional water-fat separated MRI.

Journal of medical imaging (Bellingham, Wash.)·2024

Same author

Functional correlation tensors in brain white matter and the effects of normal aging.

Brain imaging and behavior·2024

Researchers improved medical image labeling with mouse gestures, increasing speed by 27% and accuracy by up to 50%. An inexpensive touch screen was less effective, requiring further development for efficient use in large-scale studies.

Area of Science:

Medical Imaging
Computational Anatomy
Human-Computer Interaction

Background:

Accurate medical image labeling is essential for analyzing morphometric and volumetric features.
Manual landmarking is time-consuming and resource-intensive, hindering large-scale studies.
Existing internet-based collaborative labeling tools often have high training requirements, limiting throughput.

Purpose of the Study:

To enhance the efficiency and accuracy of medical image labeling systems.
To evaluate the usability and reliability of novel input methods for image annotation.
To investigate the potential of mouse gesture recognition and inexpensive touch-screen technology for high-throughput labeling.

Main Methods:

Developed a platform-independent overlay for mouse gesture recognition.

Related Experiment Videos

Integrated an inexpensive touch-screen tracking device as an alternative input method.

Quantified rater reliability and performance across point, line, curve, and region placement tasks.

Main Results:

Mouse gesture software improved labeling speed by 27% and accuracy by 30-50% for specific tasks.
Placement accuracy for mouse input: 2.48±5.29 pixels (point), 0.630±1.81 pixels (curve), 1.234±6.99 pixels (line).
The touch screen module resulted in slower, more error-prone labeling, indicating a need for improved sensitivity and calibration.

Conclusions:

Mouse gesture integration offers a seamless overlay to enhance existing labeling software.
The developed gesture recognition system shows potential for improving high-throughput medical image analysis.
The inexpensive touch screen system requires significant optimization before it can be considered an efficient labeling solution.