Intelligent Systems Design and Applications, International Conference on (2006)
Oct. 16, 2006 to Oct. 18, 2006
Chun-Yi Lin , South China Univ. of Tech., China; Sun Yat-sen Univ., China
Jun-Xun Yin , South China Univ. of Tech., China
Xue Gao , South China Univ. of Tech., China
Jian-Yu Chen , Sun Yat-sen Univ., China
Pei Qin , Sun Yat-sen Univ., China
A multi-level semantic modeling method, which integrates Support Vector Machines (SVM) into hybrid Bayesian networks (HBN), is proposed in this paper. SVM discretizes the continuous variables of medical image features by classifying them into finite states as middle-level semantics. Based on the HBN, the semantic model for medical image semantic retrieval can be designed at multi-level semantics. To validate the method, a model is built to achieve automatic image annotation at the content level from a small set of astrocytona MRI (magnetic resonance imaging) samples. Multi-level annotation is a promising solution to enable medical image retrieval at different semantic levels. Experiment results show that this approach is very effective to enable multi-level interpretation of astrocytona MRI scan. It outperforms the Bayesian network-based model using k-nearest neighbor classifiers (K-NN). This study provides a novel way to bridge the gap between the high-level semantics and the low-level image features.
X. Gao, J. Chen, C. Lin, P. Qin and J. Yin, "A Semantic Modeling Approach for Medical Image Semantic Retrieval Using Hybrid Bayesian Networks," 2006 6th International Conference on Intelligent Systems Design and Applications(ISDA), Jinan, 2006, pp. 482-487.