Classification of liver diseases from CT images using BP-CMAC neural network

In this paper, a novel BP-CMAC neural network classifier for the classification of liver diseases is proposed. The BP-CMAC neural network takes the advantages of the back-propagation (BP) and CMAC networks. It utilities the CMAC to simplify the input space and forwards to the BP network as inputs. Therefore, it can reduce the memory allocation for CMAC network, and speed up the learning process. The BP-CMAC is used to construct the liver disease diagnosis system for testing the liver cyst, hepatoma, and cavernous hemagioma. The overall distinction rate is about 87% even though the symptoms of hepatoma and cavernous hemagioma are very similar.