Two Systems for the Detection of Melanomas in Dermoscopy Images Using Texture and Color Features

• Type: Article in International Scientific Journal
• Date: 2014

Authors

Catarina Barata (Author) Other; Margarida Ruela (Author) Other; Mariana Francisco (Author) Other; Teresa Mendonca (Author) FCUP; Jorge S Marques (Author) Other

Journal

Title: IEEE Systems Journal

Vol. 8

Pages: 965-979

ISSN: 1932-8184

Publisher: IEEE

Indexing

ISI Web of Knowledge - 229 Citations

Scopus - 324 Citations

Scientific classification

FOS: Engineering and technology > Electrical engineering, Electronic engineering, Information engineering

Other information

Authenticus ID: P-008-C8Q

DOI: 10.1109/jsyst.2013.2271540

Abstract (EN): Melanoma is one of the deadliest forms of cancer; hence, great effort has been put into the development of diagnosis methods for this disease. This paper addresses two different systems for the detection of melanomas in dermoscopy images. The first system uses global methods to classify skin lesions, whereas the second system uses local features and the bag-of-features classifier. This paper aims at determining the best system for skin lesion classification. The other objective is to compare the role of color and texture features in lesion classification and determine which set of features is more discriminative. It is concluded that color features outperform texture features when used alone and that both methods achieve very good results, i.e., Sensitivity = 96% and Specificity = 80% for global methods against Sensitivity = 100% and Specificity = 75% for local methods. The classification results were obtained on a data set of 176 dermoscopy images from Hospital Pedro Hispano, Matosinhos.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 15