Characterization of digital medical images utilizing support vector machines

Maglogiannis, IG; Zafiropoulos, EP

dc.contributor.author	Maglogiannis, IG	en
dc.contributor.author	Zafiropoulos, EP	en
dc.date.accessioned	2014-03-01T01:20:00Z
dc.date.available	2014-03-01T01:20:00Z
dc.date.issued	2004	en
dc.identifier.issn	14726947	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/15800
dc.subject	Data Classification	en
dc.subject	Digital Image	en
dc.subject	Discriminant Analysis	en
dc.subject	Human Subjects	en
dc.subject	Image Analysis	en
dc.subject	Image Processing Techniques	en
dc.subject	Malignant Melanoma	en
dc.subject	Medical Image	en
dc.subject	Skin Lesion	en
dc.subject	Statistical Discrimination	en
dc.subject	Support Vector Machine	en
dc.subject	Neural Network	en
dc.subject.other	algorithm	en
dc.subject.other	article	en
dc.subject.other	artificial neural network	en
dc.subject.other	computer assisted diagnosis	en
dc.subject.other	diagnostic accuracy	en
dc.subject.other	discriminant analysis	en
dc.subject.other	disease classification	en
dc.subject.other	dysplastic nevus	en
dc.subject.other	image analysis	en
dc.subject.other	image processing	en
dc.subject.other	imaging system	en
dc.subject.other	intermethod comparison	en
dc.subject.other	melanoma	en
dc.subject.other	skin defect	en
dc.title	Characterization of digital medical images utilizing support vector machines	en
heal.type	journalArticle	en
heal.identifier.primary	10.1186/1472-6947-4-1	en
heal.identifier.secondary	http://dx.doi.org/10.1186/1472-6947-4-1	en
heal.identifier.secondary	1	en
heal.publicationDate	2004	en
heal.abstract	Background: In this paper we discuss an efficient methodology for the image analysis and characterization of digital images containing skin lesions using Support Vector Machines and present the results of a preliminary study. Methods: The methodology is based on the support vector machines algorithm for data classification and it has been applied to the problem of the recognition of malignant melanoma versus dysplastic naevus. Border and colour based features were extracted from digital images of skin lesions acquired under reproducible conditions, using basic image processing techniques. Two alternative classification methods, the statistical discriminant analysis and the application of neural networks were also applied to the same problem and the results are compared. Results: The SVM (Support Vector Machines) algorithm performed quite well achieving 94.1% correct classification, which is better than the performance of the other two classification methodologies. The method of discriminant analysis classified correctly 88% of cases (71% of Malignant Melanoma and 100% of Dysplastic Naevi), while the neural networks performed approximately the same. Conclusion: The use of a computer-based system, like the one described in this paper, is intended to avoid human subjectivity and to perform specific tasks according to a number of criteria. However the presence of an expert dermatologist is considered necessary for the overall visual assessment of the skin lesion and the final diagnosis.	en
heal.journalName	BMC Medical Informatics and Decision Making	en
dc.identifier.doi	10.1186/1472-6947-4-1	en
dc.identifier.volume	4	en
dc.identifier.spage	1	en
dc.identifier.epage	9	en