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 Videos

Counting moles automatically from back images.

Tim K Lee1, M Stella Atkins, Michael A King

  • 1School of Computing Science, Simon Fraser University, Burnaby, BC, Canada. tlee@bccancer.bc.ca

IEEE Transactions on Bio-Medical Engineering
|November 16, 2005
PubMed
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

A data-driven respiratory motion correction for pediatric DMSA renal SPECT imaging: A simulation study.

Medical physics·2026
Same author

GloW-VSNet: A scribble-based weakly supervised framework for global-view vitiligo lesion segmentation.

Medical image analysis·2025
Same author

Investigation of Attenuation Correction Methods for Dual-Gated Single Photon Emission Computed Tomography (DG-SPECT).

Bioengineering (Basel, Switzerland)·2025
Same author

Tumor miRNA Signatures Associate with Outcomes of Patients with Stage II/III Melanoma.

Clinical cancer research : an official journal of the American Association for Cancer Research·2025
Same author

Integrating Clinical Knowledge Graphs and Gradient-Based Neural Systems for Enhanced Melanoma Diagnosis via the Seven-Point Checklist.

IEEE transactions on neural networks and learning systems·2025
Same author

Enhancing <i>in vivo</i> morphological assessment of skin conditions using a four-state polarized multispectral imaging system.

Optics letters·2025
Same journal

SleepConFormer: A Single-Channel EEG Framework for Sleep Staging and Consciousness Assessment in Patients with Disorders of Consciousness.

IEEE transactions on bio-medical engineering·2026
Same journal

Modeling Partial and Total Support of Left Ventricular Assist Device for Discrete Hemodynamic Control Framework.

IEEE transactions on bio-medical engineering·2026
Same journal

A Low-Cost Wearable TI-TACS Stimulator With Bipolar Quadratic-Boost Converter for Current Stimulation Validation in the Rat Brain.

IEEE transactions on bio-medical engineering·2026
Same journal

EMG-Based Gait Estimation Using Koopman-Inspired Method.

IEEE transactions on bio-medical engineering·2026
Same journal

Soft Everting Robots for Medical Applications: A Review.

IEEE transactions on bio-medical engineering·2026
Same journal

Arterial spin labeling cerebral blood flow quantification from quantitative transport mapping based on multiscale fluid mechanics simulation and deep learning.

IEEE transactions on bio-medical engineering·2026
See all related articles

An automated algorithm accurately segments and counts moles, aiding melanoma research. This method achieves 91% sensitivity and 90% accuracy for moles over 1.5 mm, standardizing studies.

Area of Science:

  • Dermatology
  • Medical Imaging
  • Computer Vision

Background:

  • Mole density is a key indicator for malignant melanoma risk.
  • Accurate mole enumeration is crucial for melanoma research and risk assessment.
  • Manual mole counting is subjective and lacks standardization.

Purpose of the Study:

  • To develop an unsupervised algorithm for automatic mole segmentation and counting.
  • To standardize mole enumeration in studies evaluating melanoma risk factors, such as sunscreen effectiveness.
  • To assess the algorithm's performance against expert dermatological evaluation.

Main Methods:

  • Developed an unsupervised algorithm using a novel mean shift filtering variant for image clustering and noise reduction.
  • Employed a region growing procedure for candidate mole selection.

Related Experiment Videos

  • Utilized a rule-based classifier for accurate mole identification.

    • Main Results:

    • The algorithm demonstrated high performance in segmenting and counting moles from 2D color images of the back torso.
    • Achieved a sensitivity rate of 91% and a diagnostic accuracy of 90% for moles larger than 1.5 mm in diameter.
    • The automated method showed comparable results to expert dermatologist assessments.

    Conclusions:

    • The developed unsupervised algorithm provides a standardized and accurate method for mole segmentation and counting.
    • This automated approach can significantly aid in large-scale studies of malignant melanoma and risk factor evaluation.
    • The algorithm's high sensitivity and accuracy support its utility in clinical research settings.