An efficient classification of cirrhosis liver disease using hybrid convolutional neural network-capsule network

Abstract

Liver cirrhosis is the diffuse and advanced phase of liver disease. Several morphological methods are used for imaging modalities. But, these modalities are biased and lack in higher detection accuracy. Hence, this work introduces automated cirrhosis liver disease classification using an optimized hybrid deep learning model. In this work, Magnetic Resonance Image (MRI) is considered for the process. Initially, an Extended Guided Filter (EGF) is used for eliminating the noise from input MRI images. Binomial thresholding is used to segment the tumor from the image. Then, Feature Extraction (FE) phase is carried out by Grey Level Co-occurrence Matrix (GLCM) and Gray level Run-length Matrix (GRLM). Finally, a hybrid of two Deep Learning (DL) algorithms Convolutional Neural Network and Capsule Network (HCNN-CN) are integrated to classify the Cirrhosis liver disease. Moreover, for fine tuning the parameters of the neural network, an optimization approach Adaptive Emperor Penguin Optimization (AEPO) is used. The proposed HCNN-CN-AEPO is compared over several approaches and depicted accuracy and sensitivity value of 0.993 and 0.986 on the real time dataset. The experimental results proved that the proposed HCNN-CN-AEPO can exactly diagnose the tumour.