Title :
Diagnosis of rheumatoid arthritis with optical tomography: Comparison of classification methods
Author :
Montejo, Ludguier D. ; Montejo, Julio D. ; Kim, Hyun K. ; Netz, Uwe J. ; Klose, Christian D. ; Blaschke, Sabine ; Zwaka, PA ; Muller, Gerhard A. ; Beuthan, J. ; Hielscher, Andreas H.
Author_Institution :
Dept. of Biomed. Eng., Columbia Univ., New York, NY, USA
Abstract :
Linear discriminant analysis (LDA) and support vector machines (SVM) are used to classify reconstructed absorption coefficient distributions of the proximal interphalangeal joints as affected or not affected by rheumatoid arthritis. The performance of each classification method is quantified using the leave-n-out method. LDA is shown to yield high sensitivities, while SVM yields high specificities.
Keywords :
bone; diseases; image classification; image reconstruction; medical image processing; optical tomography; support vector machines; classification methods; leave-n-out method; linear discriminant analysis; optical tomography; proximal interphalangeal joints; reconstructed absorption coefficient; rheumatoid arthritis diagnosis; support vector machines; Arthritis; Tomography;
Conference_Titel :
Bioengineering Conference, Proceedings of the 2010 IEEE 36th Annual Northeast
Conference_Location :
New York, NY
Print_ISBN :
978-1-4244-6879-9
DOI :
10.1109/NEBC.2010.5458156
