Reconizing tumor cells in liver images using probabilitistic neural network

Image processing has become an essential component in many fields of biomedical research such as tumor detection, automatically determining the volume of a heart chamber, screening lung scans for possible diseases. Different techniques for automatic detection of liver tumor involve various steps: image acquisition, segmentation, classification using neural network and optimization, and identification of tumor type. This paper presents a new approach to detect and segment liver tumors. The detection and segmentation of liver tumors can be formulized as novelty detection by pre-processing, segmentation feature extraction. The main objective of the proposed method is to precisely identify the presence of tumor cells in liver images as an early indication of malignant cells that may cause to the demise of patients. The proposed hybrid kernel classifier is compare with existing techniques which shows it have better accuracy, sensitivity and specificity.