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

Melanoma computer-aided diagnosis: reliability and feasibility study.

Marco Burroni1, Rosamaria Corona, Giordana Dell'Eva

  • 1Department of Dermatology, University of Siena, Italy.

Clinical Cancer Research : an Official Journal of the American Association for Cancer Research
|March 26, 2004
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

Minimum mortality temperature by cause of death and age group: A multi-country observational study (1990-2019).

Environmental research·2026
Same author

Temporal changes in mortality risk associated with PM<sub>10</sub> across 143 cities in 26 countries: a multicountry, multicity time-series study.

The Lancet. Planetary health·2026
Same author

The burden of premature births attributed to heat across 13 countries.

Environment international·2026
Same author

The burden of El Niño-Southern Oscillation-related dengue attributable to anthropogenic climate change: a multicountry modelling study.

The Lancet. Planetary health·2026
Same author

The joint impact of temperature, humidity, and air pollution on COVID-19 incidence: a multi-country time-series study in 439 cities.

Environment international·2026
Same author

Accuracy of the central vein sign in diagnosis of multiple sclerosis: a systematic review and meta-analysis.

Journal of neurology·2026
Same journal

Presenting features and outcomes to standard systemic therapies in patients with MTAP-deleted advanced non-small cell lung cancer.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same journal

Clinical Validation of a Multiplex Urine Biomarker Assay for Surveillance of Recurrent Bladder Cancer.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same journal

Epigenetic Liquid Biopsy Enables Universal Mutation-Agnostic Molecular Surveillance for High-Risk Neuroblastoma.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same journal

Claudin 18.2 Targeting: A Pan-Cancer Perspective.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same journal

High-Sensitivity ctDNA Analysis Uncovers Relevant Signals Missed by NGS in Pancreatic Cancer.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same journal

Pediatric Brain Tumor Consortium phase 1 study of CD40 agonist sotigalimab in pediatric and young adult patients with recurrent CNS tumors and newly-diagnosed DIPG.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
See all related articles

Automated analysis of skin lesion images using statistical classifiers can reliably differentiate melanoma from benign nevi. This computer-aided approach shows promise for improving early melanoma diagnosis and reducing unnecessary surgeries.

Area of Science:

  • Dermatology
  • Medical Imaging
  • Computational Pathology

Background:

  • Distinguishing melanoma from melanocytic nevi is clinically challenging.
  • Automated analysis of dermoscopic images is gaining interest for melanoma detection.
  • Digital image analysis aids in differentiating early melanoma from benign skin lesions.

Purpose of the Study:

  • Evaluate diagnostic accuracy of statistical classifiers for pigmented skin lesions.
  • Assess performance across multiple digital analyzers and dermatological units.

Main Methods:

  • Utilized images of 391 melanomas and 449 melanocytic nevi.
  • Developed a linear classifier with 95% sensitivity using ROC curves.
  • Constructed a K-nearest-neighbor classifier trained for 98% sensitivity.

Related Experiment Videos

Main Results:

  • Linear classifier achieved 95% sensitivity and 78% specificity.
  • K-nearest-neighbor classifier achieved 98% sensitivity and 79% specificity.
  • Similar diagnostic accuracy was observed across different units and instruments.

Conclusions:

  • Computer-aided differentiation of melanoma from benign lesions using DB-Mips is feasible and reliable.
  • Consistent diagnostic accuracy across different settings supports the technology's robustness.
  • Further randomized clinical trials are needed to confirm improved early diagnosis and reduced surgery.