Title :
Image analysis and CADx system for mucosal lesions
Author :
Chodorowski, Artur ; Choudhury, Chitta R. ; Gustavsson, Tomas
Author_Institution :
Dept. of Signals & Syst., Chalmers Univ. of Technol., Goteborg
Abstract :
A computer aided diagnosis (CADx) system for oral mucosal lesions has been developed using clinical cases from India as training examples. The investigated classifiers were support vector machine (SVM) and Bayes point machine (BPM), and the task was to discriminate potentially precancerous lesions from non-precancerous lesions. The discriminating features consisted of color differences and lesionspsila shape properties. The overall classification accuracy was 85% (29 out of 34) for both SVM and BPM classifiers.
Keywords :
Bayes methods; biomedical optical imaging; biomembranes; cancer; feature extraction; image classification; image colour analysis; learning (artificial intelligence); medical image processing; skin; support vector machines; tumours; wounds; BPM classifiers; Bayes point machine; CAD system; SVM classifiers; color differences; computer aided diagnosis system; feature discrimination; image analysis; lesion shape properties; mucosal lesions; nonprecancerous lesion; precancerous lesion; support vector machine; Cancer detection; Charge coupled devices; Dentistry; Humans; Image analysis; Image color analysis; Lesions; Shape; Support vector machine classification; Support vector machines;
Conference_Titel :
BioInformatics and BioEngineering, 2008. BIBE 2008. 8th IEEE International Conference on
Conference_Location :
Athens
Print_ISBN :
978-1-4244-2844-1
Electronic_ISBN :
978-1-4244-2845-8
DOI :
10.1109/BIBE.2008.4696842
