Group Method Data Handling Neural Network for CT Abdomen Image Segmentation based on First Order Statistics and Local Binary Pattern

This work proposes Group method Data Handling (GMDH) neural network for the segmentation of liver and liver tumor on abdomen CT images. The structure of the GMDH neural network is automatically structured using heuristic self-organization. Prior to segmentation, Nonlinear Tensor Diffusion (NLTD) filter was used for the preprocessing of input images. Feature extraction was performed by first order statistics and local binary pattern. The parameters of neural network like the number of useful input variables, the number of neurons in each layer and the selection of optimum neural network architecture are determined by using the error criterion derived from AIC (Akaike’s Information Criterion). The performance of the GMDH algorithm was evaluated by success and error rates, similarity measures and the results outperform the back propagation neural network algorithm. The algorithms are developed in Matlab 2013a and tested on real time abdomen CT datasets. The satisfactory results were obtained by GMDH algorithm and are useful for computer aided diagnosis of liver cancer.