An Efficient Liver Disease Prediction Using Mask-Regional Convolutional Neural Network and Pelican Optimization Algorithm

Abstract

Various prediction approaches regarding liver diseases have been developed. Still, they are expensive and more complex. This work aims to design an effective method for identifying liver diseases at earlier stages. This paper presents a modified Mask-regionalconvolutional neural network (MRCNN) architecture for non-invasive liver disease prediction. The Pelican Optimization Algorithm (POA) is used to balance the bounding box regression and mask branching training losses of the RCNN model. The liver disease features are extracted from three datasets namely Indian liver patient records, Hepatitis C, and Cirrhosis Prediction datasets. The POA-modified MRCNN model is mainly used to identify the interrelationship that exists between different laboratory measurements and diagnoses. The efficiency of the proposed model is compared with different state-of-art methods such as Opposition-based Laplacian Equilibrium Optimizer, Adaptive Hybridized Deep CNN, SVM, and Tree-based classifiers in terms of Accuracy, Precision, Recall, F-measure, and Mathews Correlation Coefficient (MCC). The proposed model offers an MCC value of 94.89, an accuracy of 98%, a precision of 96.2%, an F-measure of 97.3%, and a recall of 95% respectively. The results demonstrate the efficiency of the proposed model in predicting liver disease at an early stage via automatic screening and minimizing the burden of physicians.