Classification of Liver Lesion Stages using pyRadiomics Features Combined with 3D-CNN in 3D-CT and US Images

Abstract

Objectives: The goal of this study is to identify the various stages in liver diseases employing pyRadiomics features by analyzing the 3-dimensional CT and US images. Methods: The study uses Gray level Run Length Matrix for feature extraction and 3D-CNN for classification and compared with methods like Support Vector Machine (SVM), Random Forest (RF), and Naïve Bayes (NB) classifiers to assess the efficiency of the proposed model. The suggested algorithm is implemented using the library functions in Tensorflow and Keras packages in Python. Findings: The study utilizes radiomic feature extraction and two-phase classification to detect and classify liver disorders. In the first phase, binary classification is used to classify US and CT images as normal or abnormal, with accuracy rates of 95.4% and 97.9%. This is followed by the second phase classification, which classifies the lesion stages for both US and CT aberrant images. CT images have been shown to be more accurate in categorizing lesion stages than US imaging. CT images have a much lower misclassification rate at each step than US images. Finally, the effectiveness of the 3D-CNN model is compared with SVM, RF, and NB and the suggested method outperforms the other methods. Novelty: The suggested architecture employs radionics feature extraction with two-phase CNN for classification and the suggested method is found to be more efficient than SVM, RF, and NB. Keywords: Radiomics; Feature Extraction; Convolutional Neural Networks (CNN); Classification; Liver Diseases