Performance Analysis of Data Mining Algorithms for Medical Image Classification

Image mining is one of the predominant researches in computer science field. It is a process of extracting valuable information from a huge amount of dataset. In image mining, there are several techniques are adopted such as image classification, image clustering, regression analysis and association rule mining. In this work, we have concentrated on image classification technique to analyze the performance of image mining algorithms based on classification accuracy, processing time, error rates, sensitivity and specificity. Image classification is an essential technique in image mining and it is most important part of medical image analysis. It has two level processes. In the first level, the typical model is built telling a determined collection of concept or data classes. In second level the model is used for classification. The main objective of this paper is to identify better method of image mining in medical image analysis based on the performance analysis. Some predominant image mining algorithms such as Classification, Regression Tree (CART), K-Means, Naive Bayes (NB), Decision Tree (DT) K-Nearest Neighbor and Support Vector Machine (SVM).These algorithms are used for the performance of medical image classification.