Related Experiment Video
Updated: May 5, 2026
06:16
Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies
Published on: July 28, 2023
3.5K
Detection of pigment network in dermoscopy images using supervised machine learning and structural analysis.
Jose Luis García Arroyo1, Begoña García Zapirain1
1Deustotech-LIFE Unit (eVIDA). University of Deusto. Avda. Universidades, 24. 48007 Bilbao, Spain.
Computers in Biology and Medicine
|December 10, 2013
Summary
A new algorithm detects the pigment network in dermoscopic images, aiding melanoma diagnosis. This reliable method achieves 86% sensitivity and 81.67% specificity in identifying this key indicator.
Area of Science:
- Dermatology
- Medical Imaging
- Artificial Intelligence
Background:
- The pigment network is a crucial indicator in melanoma diagnosis.
- Accurate detection of the pigment network is essential for early and correct diagnosis.
Purpose of the Study:
- To develop and validate a novel detection algorithm for the pigment network in dermoscopic images.
- To improve the accuracy and reliability of melanoma diagnosis through automated pattern recognition.
Main Methods:
- A two-block algorithm utilizing machine learning to generate detection rules.
- Image analysis to identify and segment pigment network structures.
- Validation on a database of 220 dermoscopic images.
Main Results:
- The algorithm successfully generates a mask for candidate pigment network pixels.
- It accurately identifies the presence or absence of the pigment network.
- Achieved 86% sensitivity and 81.67% specificity in image analysis.
Conclusions:
- The developed algorithm is a reliable tool for detecting the pigment network.
- This technology shows promise for enhancing melanoma diagnostic capabilities.
- Automated detection can support dermatologists in clinical decision-making.
