Segmentation and classification of dermatological lesions

Aurora Sáez; Begoña Acha; Carmen Serrano

doi:10.1117/12.844323

9 March 2010 Segmentation and classification of dermatological lesions

Aurora Sáez, Begoña Acha, Carmen Serrano

Proceedings Volume 7624, Medical Imaging 2010: Computer-Aided Diagnosis; 76243L (2010) https://doi.org/10.1117/12.844323
Event: SPIE Medical Imaging, 2010, San Diego, California, United States

Abstract

Certain skin diseases are chronic, inflammatory and without cure. However, there are many treatment options that can clear them for a period of time. Measuring their severity and assessing their extent, is a fundamental issue to determine the efficacy of the treatment under test. Two of the most important parameters of severity assessment are Erythema (redness) and Scaliness. Physicians classify these parameters into several grades by visual grading method. In this paper a color image segmentation and classification algorithm is developed to obtain an assessment of erythema and scaliness of dermatological lesions. Color digital photographs taken under an acquisition protocol form the database. Difference between green band and blue band of images in RGB color space shows two modes (healthy skin and lesion) with clear separation. Otsu's method is applied to this difference in order to isolate the lesion. After the skin disease is segmented, some color and texture features are calculated and they are the inputs to a Fuzzy-ARTMAP neural network. The neural network classifies them into the five grades of erythema and the five grades of scaliness. The method has been tested with 31 images with a success percentage of 83.87 % when the images are classified in erythema, and 77.42 % for scaliness classification.

Citation Download Citation

Aurora Sáez, Begoña Acha, and Carmen Serrano "Segmentation and classification of dermatological lesions", Proc. SPIE 7624, Medical Imaging 2010: Computer-Aided Diagnosis, 76243L (9 March 2010); https://doi.org/10.1117/12.844323

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available