Skip to content

Program for autonomously predicting whether a lesion is cancerous based on a picture of it

Notifications You must be signed in to change notification settings

zorn96/Melanoma-Detection-Color

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 

Repository files navigation

Melanoma-Detection-Color

This is a program that, given an image of a skin lesion, can calculate the number of perceptually significant colors in the skin lesion through autonomous clustering and various cluster validity measures.

It was applied with a data set and a symbolic regression algorithm in order to determine an equation for calculating whether a lesion is cancerous based on the number of colors as given by the various cluster validity indexes that were programmed. The equation developed, when implemented with this system had an accuracy of 72%

About

Program for autonomously predicting whether a lesion is cancerous based on a picture of it

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages