DocumentCode
2960378
Title
Inductive learning of skin lesion images for early diagnosis of melanoma
Author
Surówka, Grzegorz
Author_Institution
Fac. of Phys., Astron. & Appl. Comput. Sci., Jagiellonian Univ., Krakow
fYear
2008
fDate
1-8 June 2008
Firstpage
2623
Lastpage
2627
Abstract
We take advantage of natural induction methods to build classifiers of the pigmented skin lesion images. This methodology can be treated as a non-invasive approach to early diagnosis of melanoma. We use the AQ21 application, which is based on the attributional calculus, to discover patterns in the skin images. Our classifier has good efficiency and may potentially be an important diagnostic aid.
Keywords
calculus; cancer; feature extraction; image classification; learning by example; medical image processing; skin; tumours; wavelet transforms; attributional calculus; epidemiology; feature selection; image classification; inductive learning; malignant human cancer; melanoma early diagnosis; natural induction methods; pattern discovery; pigmented skin lesion image; wavelet transform; Calculus; Cancer; Learning systems; Lesions; Machine learning; Malignant tumors; Pigmentation; Probes; Skin; Wavelet analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
Conference_Location
Hong Kong
ISSN
1098-7576
Print_ISBN
978-1-4244-1820-6
Electronic_ISBN
1098-7576
Type
conf
DOI
10.1109/IJCNN.2008.4634165
Filename
4634165
Link To Document