Advances in the medical imaging technology has lead to an exponential growth in the number of digital images that needs to be acquired, analyzed, classiﬁed, stored and retrieved in medical centers. As a result, medical image classiﬁcation and retrieval has recently gained high interest in the scientiﬁc community. Despite several attempts, such as the yearly-held ImageCLEF Medical Image Annotation Challenge, the proposed solutions are still far from being sufficiently accurate for real-life implementations.
In this paper we summarize the technical details of our experiments for the ImageCLEF 2009 medical image annotation challenge. We use a direct and two ensemble classiﬁcation schemes that employ local binary patterns as image descriptors. The direct scheme employs a single SVM to automatically annotate X-ray images. The two proposed ensemble schemes divide the classiﬁcation task into sub-problems. The ﬁrst ensemble scheme exploits ensemble SVMs trained on IRMA sub-codes. The second learns from subgroups of data deﬁned by frequency of classes. Our experiments show that ensemble annotation by training individual SVMs over each IRMA sub-code dominates its rivals in annotation accuracy with increased process time relative to the direct scheme.
European Conference on Digital Libraries (ECDL), Cross-Language Evaluation Forum (CLEF) Workshop, Corfu, Greece, September-October 2009