A Novel Computer-Aided Diagnostic System for Early Assessment of Hepatocellular Carcinoma

Abstract

Purpose: Liver cancer is a major cause of morbidity and mortality in the world. The primary goals of this manuscript are the identification of novel imaging features (texture, functional, and shape), and development of a computer-aided diagnostic (CAD) system to accurately detect and grade liver tumors non-invasively. Methods: A total of 85 patients with liver tumors were enrolled in the study after consents were obtained. 34 patients had benign tumors, 17 patients had intermediate tumors, and 34 patients had hepatocellular carcinoma (HCC) malignant tumors. A multi-phase contrast-enhanced magnetic resonance imaging (CE-MRI) was collected to extract the imaging features. The proposed approach consists of three main steps. First, a pre-processing is applied to the CE-MRI scans to delineate the tumor lesions that will be used as a region of interest (ROI) across the four different phases of the CE-MRI. Second, a group of three features are modeled to provide a quantitative discrimination between the tumor lesions, namely: the tumor appearance that is modeled using a set of texture features, (namely; the first-order histogram features, second-order gray-level co-occurrence matrix (GLCM) features, and second-order gray-level run-length matrix (GLRLM) features), to capture any discrimination that may appear in the lesion texture; the spherical harmonics (SH) based shape features that have the ability to describe the shape complexity of the liver tumors; and the functional features that are based on the calculation of the wash-in/wash-out slopes to evaluate the intensity changes across different phases. Finally, these features were integrated together to obtain the combined features to be fed to a machine learning classifier towards getting the final diagnostic decision. Results: Using the Random Forests classifier with a leave-one-out (LOSO) cross-validation, the developed CAD system achieved an 87.1% accuracy in distinguishing between malignant, intermediate and benign tumors (i.e., First stage classification). LR-1 lesions were classified from LR-2 benign lesions with 91.2% accuracy, while 85.3% accuracy was achieved differentiating between LR-4 and LR-5 malignant tumors (i.e., Second stage classification).