A Computer-Aided Spectroscopic System for Early Diagnosis of Melanoma

Author

Lin Li ; Qizhi Zhang ; Yihua Ding ; Huabei Jiang ; Thiers, Bruce T. ; Wang, James Z.

Author_Institution

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

fYear

2013

fDate

4-6 Nov. 2013

Firstpage

145

Lastpage

150

Abstract

Early detection of melanoma, the deadliest type of skin cancer, has the potential to reduce morbidity and mortality. This paper presents an automated system for early identification of melanoma, which makes objective judgments based on quantitative measures. The system involves image processing, feature extraction, and support vector machine (SVM) classification. Images of 19 malignant melanoma and 168 benign subjects were collected by a spectroscopic device to reflect morphologies in diseased layers of skin. Features were extracted based on statistical parameters of pixel intensities and were fed into an SVM classifier. The system achieved 92% classification accuracy, 100% sensitivity and 92% specificity.

Keywords

biomedical optical imaging; cancer; feature extraction; image classification; medical image processing; skin; spectroscopy computing; statistical analysis; support vector machines; SVM classification; automated system; benign subjects; computer-aided spectroscopic system; diseased skin layer morphology; early melanoma diagnosis; feature extraction; image processing; malignant melanoma; objective judgments; pixel intensities; quantitative measures; skin cancer; statistical parameters; support vector machine; Accuracy; Cancer; Lesions; Malignant tumors; Sensitivity; Skin; Support vector machines; Melanoma; classification; feature extraction; spectroscopy; support vector machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Tools with Artificial Intelligence (ICTAI), 2013 IEEE 25th International Conference on

Conference_Location

Herndon, VA

ISSN

1082-3409

Print_ISBN

978-1-4799-2971-9

Type

conf

DOI

10.1109/ICTAI.2013.31

Filename

6735242