Y.U. Kim, J. Kim, K.H. Um, and H.J. Jo (Korea)
Image Retrieval, Classification, Learning, DecisionTree
In this paper we present a system that classifies brain MRI series by using decision tree learning. There are two kinds of information that can be obtained from MRI. One is a set of low-level features that can be obtained directly from the original image such as sizes, colors, textures and contours. The other is a set of high level features that be made through interpretation of the segmented images. To classify images based on the semantic contents, learning and classification should be performed based on high-level features. The proposed system first classifies the image segments by using low level features. Then the high-level features are synthesized and the whole MRI series are classified by using those features. Experiments have been performed to classify brain MRI series to normal brains, cerebral infarctions and brain tumors, and the results are discussed.
Important Links:
Go Back
