Abstract: The paper presents an automatic approach to assessment of the stage of development of the kidney cancer on the basis of Fuhrman grades. The stage of advancement level of cancer is usually associated with 4 Fuhrman grades. Our approach to Fuhrman grade assessment is composed of few steps. The first one is extraction of the numerical features from the microscopic image of the histological slides of the biopsy of kidney by using mathematical morphology. The next step is the features selection providing descriptors of the best class separating abilities. The last one is application of the automatic classifiers and data mining techniques to assign the actually available samples to one of four classes.

• Publication Date: 05-May-2013
• DOI: 10.15224/978-981-07-6261-2-10
• Views: 0
• Downloads: 0

Abstract: n this paper colposcopy cervical image classification based on colour histogram and K Nearest Neighbor (KNN) is presented. The classification is achieved by extracting colour histogram features from the cervix. To extract the colour histogram features, the colour space of the given image is converted from RGB to CIE colour space because of its perceptual uniformity. KNN classifier is used to classify the cervical images into normal and abnormal images. The performance with overall sensitivity of 94.71% and accuracy of 93.75 % is achieved using k-NN classifier. The performance is evaluated using 240 images collected from the hospital.

• Publication Date: 05-May-2013
• DOI: 10.15224/978-981-07-6261-2-11
• Views: 0
• Downloads: 0