Special Issue Article Open Access

Mammographic Cancer Detection and Classification Using Bi Clustering and Supervised Classifier

Abstract

The project proposes an automatic support system for stage classification using probabilistic neural network based on the detection of cancer region through thresholding method for medical application. The detection of the breast cancer is a challenging problem, due to the structure of the cancer cells. This project presents a segmentation method, wavelet based threshold method, for segmenting mammographic images to detect the Breast cancer in its early stages. The threshold will be determined by biclustering an image based on row and column separation. The artificial neural network will be used to classify the stage of image that is abnormal or normal. The manual analysis of this samples are time consuming, inaccurate and requires intensive trained person to avoid diagnostic errors. The segmentation results will be used as a base for a Computer Aided Diagnosis system for early detection of cancer from mammographic images which will improves the chances of survival for the patient. Discrete wavelet transform technique is used for extracting texture features and it decomposed the image into four levels for getting the edge details in horizontal and vertical direction. The Cooccurrence matrix will be determined for these two high frequency sub bands for finding the texture features. Probabilistic Neural Network with radial basis function will be employed to implement an automated breast cancer classification. Decision making was performed in two stages: feature extraction using Wavelet transformation followed by GLCM and the classification using PNN-RBF. The performance of the PNN classifier was evaluated in terms of training performance and classification accuraci. Probabilistic Neural Network gives fast and accurate classification than other neural networks and it is a promising tool for classification of the cancers.

R.Pavitha, Ms T.Joyce Selva Hephzibah M.Tech.

To read the full article Download Full Article | Visit Full Article