A Computer-Aided Diagnostic Tool for Melanoma

Author

Lin Li ; Clark, Andrew ; Wang, James Z.

Author_Institution

Dept. of Comput. Sci. & Inf. Syst., Murray State Univ., Murray, KY, USA

Volume

1

fYear

2014

fDate

10-13 March 2014

Firstpage

114

Lastpage

118

Abstract

Early detection of melanoma, the deadliest form of skin cancer, has the potential to reduce morbidity and mortality. However, clinical diagnosis of melanoma is not trivial even for experienced dermatologists, as it is complex and subjective. Thus, it is necessary to develop an automated computer-aided diagnosis (CAD) system for melanoma, which makes objective judgments based on quantitative measures. In this paper, we present a CAD tool with functionalities of image acquisition, image processing, feature extraction, and diagnosis. The tool provides the capability of detecting melanoma with 92% accuracy, 100% sensitivity, and 92% specificity.

Keywords

feature extraction; medical image processing; skin; CAD system; CAD tool; automated computer-aided diagnosis; clinical diagnosis; computer aided diagnostic tool; feature extraction; image acquisition; image processing; melanoma; morbidity; mortality; skin cancer; Cancer; Feature extraction; Lesions; Malignant tumors; Skin; Support vector machines; classification; feature extraction; image processing; melanoma diagnosis; support vector machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Science and Computational Intelligence (CSCI), 2014 International Conference on

Conference_Location

Las Vegas, NV

Type

conf

DOI

10.1109/CSCI.2014.26

Filename

6822093