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: Jun 6, 2026

Dermoscopy Aids in the Diagnosis of Discoid Lupus Erythematosus
05:39

Dermoscopy Aids in the Diagnosis of Discoid Lupus Erythematosus

Published on: May 16, 2025

Boosting instance prototypes to detect local dermoscopic features.

Ning Situ1, Xiaojing Yuan, George Zouridakis

  • 1University of Houston, USA.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
|November 25, 2010
PubMed
Summary

This study enhances skin cancer detection by using multi-instance learning (MIL) to identify local dermoscopic features in skin lesion images. Boosting this MIL approach significantly improves diagnostic performance compared to standard methods.

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

Glycogen metabolic dysfunction in T2DM with MASLD: linking α-hydroxybutyrate to GYS2 downregulation.

Frontiers in nutrition·2026
Same author

P. gingivalis-host interactions direct antibiotic adjuvants for periodontitis antimicrobial therapy.

International journal of oral science·2026
Same author

Drugging the intrinsically disordered transactivation domain of androgen receptor.

Signal transduction and targeted therapy·2026
Same author

Aerobic exercise is associated with divergent regulation of macrophage migration inhibitory factor and enhanced remyelination in experimental autoimmune neuritis.

Bioscience reports·2026
Same author

A cell-nonautonomous heme acquisition pathway enables erythroid hemoglobinization under stress.

Science (New York, N.Y.)·2026
Same author

Advanced small extracellular vesicles delivery systems for <i>in situ</i> tissue engineering.

Extracellular vesicles and circulating nucleic acids·2026

Area of Science:

  • Dermatology
  • Computer Science
  • Machine Learning

Background:

  • Local dermoscopic features are crucial for accurate skin cancer diagnosis.
  • Detecting these features in epiluminescence microscopy (ELM) images presents a significant challenge.
  • Existing methods may not fully leverage the complex patterns within lesion images.

Purpose of the Study:

  • To develop and validate a machine learning approach for detecting local dermoscopic features in skin lesion images.
  • To investigate the effectiveness of multi-instance learning (MIL) for this task.
  • To enhance classification performance through boosting techniques.

Main Methods:

  • Formulated dermoscopic feature recognition as a multi-instance learning (MIL) problem.
  • Utilized diverse density (DD) and evidence confidence (EC) to convert MIL to single-instance learning (SIL).

More Related Videos

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

Related Experiment Videos

Last Updated: Jun 6, 2026

Dermoscopy Aids in the Diagnosis of Discoid Lupus Erythematosus
05:39

Dermoscopy Aids in the Diagnosis of Discoid Lupus Erythematosus

Published on: May 16, 2025

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

  • Applied Adaboost with support vector machines (SVMs) and proposed a boosted prototype selection method.

    • Main Results:

    • The boosted MIL approach demonstrated improved performance in detecting ten local dermoscopic features.
    • Comparison against a baseline method and non-boosted MIL showed significant gains.
    • The method was validated on a dataset of 360 skin lesion images.

    Conclusions:

    • Boosting multi-instance learning significantly enhances the detection of local dermoscopic features.
    • This approach offers a promising advancement for computer-aided skin cancer diagnosis.
    • Further development could refine diagnostic accuracy in dermatological imaging.