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 Video

Updated: May 28, 2026

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

Conditional random fields and supervised learning in automated skin lesion diagnosis.

Paul Wighton1, Tim K Lee, Greg Mori

  • 1Department of Computing Science, Simon Fraser University, Burnaby, BC, Canada V5A 1S6.

International Journal of Biomedical Imaging
|November 3, 2011
PubMed
Summary

This study unifies automated skin lesion diagnosis (ASLD) challenges into a single pixel-labeling problem. Two probabilistic models, including conditional random fields (CRFs), were developed and evaluated for improved skin lesion segmentation.

Related Concept Videos

Skin Cancer01:30

Skin Cancer

Skin cancer is a type of cancer that occurs when there is an abnormal growth of skin cells, usually triggered by damage to the DNA within the skin cells. It is primarily caused by exposure to ultraviolet (UV) radiation from the sun or artificial sources like tanning beds. Skin cancer is the most common type of cancer worldwide, and its incidence continues to rise.
Basal Cell Carcinoma (BCC): BCC is the most common type of skin cancer, accounting for about 80% of cases. It typically develops in...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Improved, rapid fetal-brain localization and orientation detection for auto-slice prescription.

Proceedings of the International Society for Magnetic Resonance in Medicine ... Scientific Meeting and Exhibition. International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition·2026
Same author

Fast, automated slice prescription of standard anatomical planes for fetal brain MRI.

Proceedings of the International Society for Magnetic Resonance in Medicine ... Scientific Meeting and Exhibition. International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition·2026
Same author

Real-time Motion Compensated ΔB<sub>0</sub> Shimming with an AC/DC Shim Coil and Dual-Echo vNavs.

Proceedings of the International Society for Magnetic Resonance in Medicine ... Scientific Meeting and Exhibition. International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition·2026
Same author

Building an open ecosystem for molecular neuroimaging: standards and tools from the OpenNeuroPET initiative.

bioRxiv : the preprint server for biology·2026
Same author

MR software tools for real-time decision making and FOV prescription.

Proceedings of the International Society for Magnetic Resonance in Medicine ... Scientific Meeting and Exhibition. International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition·2026
Same author

The myth of digital biomarkers in Alzheimer's disease: how to make them a reality.

Current opinion in psychiatry·2026

Area of Science:

  • Medical Image Analysis
  • Computer Vision
  • Machine Learning

Background:

  • Automated skin lesion diagnosis (ASLD) faces diverse subproblems.
  • A unified approach to pixel-level image labeling is proposed.

Purpose of the Study:

  • To formalize pixel-level image labeling for ASLD.
  • To present and evaluate two probabilistic models for this task.

Main Methods:

  • Developed two probabilistic models: independent pixel labeling (MAP) and conditional random fields (CRFs).
  • Utilized supervised learning for automatic parameter determination.
  • Evaluated models on a dataset of 116 skin lesion images.

Main Results:

  • Both models demonstrated capability in segmenting skin lesions.

Related Experiment Videos

Last Updated: May 28, 2026

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

  • CRFs incorporated pixel dependencies via graph structures.
  • Performance was compared against five prior methods.

    • Conclusions:

    • The proposed generalization unifies ASLD subproblems.
    • Probabilistic models, particularly CRFs, offer a robust framework for skin lesion segmentation.
    • Supervised learning enables effective model parameterization.