A novel computer-aided diagnostic system for accurate detection and grading of liver tumors

Abstract

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 markers (morphological, functional, and anatomical/textural), and development of a computer-aided diagnostic (CAD) system to accurately detect and grade liver tumors non-invasively. A total of 95 patients with liver tumors (M = 65, F = 30, age range = 34–82 years) were enrolled in the study after consents were obtained. 38 patients had benign tumors (LR1 = 19 and LR2 = 19), 19 patients had intermediate tumors (LR3), and 38 patients had hepatocellular carcinoma (HCC) malignant tumors (LR4 = 19 and LR5 = 19). A multi-phase contrast-enhanced magnetic resonance imaging (CE-MRI) was collected to extract the imaging markers. A comprehensive CAD system was developed, which includes the following main steps: i) estimation of morphological markers using a new parametric spherical harmonic model, ii) estimation of textural markers using a novel rotation invariant gray-level co-occurrence matrix (GLCM) and gray-level run-length matrix (GLRLM) models, and iii) calculation of the functional markers by estimating the wash-in/wash-out slopes, which enable quantification of the enhancement characteristics across different CE-MR phases. These markers were subsequently processed using a two-stages random forest-based classifier to classify the liver tumor as benign, intermediate, or malignant and determine the corresponding grade (LR1, LR2, LR3, LR4, or LR5). The overall CAD system using all the identified imaging markers achieved a sensitivity of 91.8%±0.9%, specificity of 91.2%±1.9%, and F$$_{1}$$ 1 score of 0.91±0.01, using the leave-one-subject-out (LOSO) cross-validation approach. Importantly, the CAD system achieved overall accuracies of $$88\%\pm 5\%$$ 88 % ± 5 % , 85%±2%, 78%±3%, 83%±4%, and 79%±3% in grading liver tumors into LR1, LR2, LR3, LR4, and LR5, respectively. In addition to LOSO, the developed CAD system was tested using randomly stratified 10-fold and 5-fold cross-validation approaches. Alternative classification algorithms, including support vector machine, naive Bayes classifier, k-nearest neighbors, and linear discriminant analysis all produced inferior results compared to the proposed two stage random forest classification model. These experiments demonstrate the feasibility of the proposed CAD system as a novel tool to objectively assess liver tumors based on the new comprehensive imaging markers. The identified imaging markers and CAD system can be used as a non-invasive diagnostic tool for early and accurate detection and grading of liver cancer.

Radiomics-Based Machine Learning Models for Predicting P504s/P63 Immunohistochemical Expression: A Noninvasive Diagnostic Tool for Prostate Cancer

“…Of these 27 prominent texture contributors, 7 were GLCM features and 9 were the GLRLM features. These GLCM and GLRLM features represented gray value changes between pixels and could reflect the complexity and heterogeneity of lesions ( 23 ), demonstrating a great ability to differentiate between benign, intermediate, and malignant tumors because the malignant tumors had more inhomogeneous internal structures than the benign and intermediate lesions ( 24 ). Moreover, cancer cells have rapid and overcrowded growth patterns as well as an insufficient supply of blood and oxygen, which causes cell hypoxia and the formation of various types of neovasculature.…”

Evaluation of liver tumor identification rate of volumetric-interpolated breath-hold images using the compressed sensing method and qualitative evaluation of tumor contrast effect via visual evaluation

“…Among the studies on this topic, Alksas et al suggested the possibility of Computer Assisted Diagnosis (CAD) for LI-RADS using more detailed analysis (i.e., functional markers, texture analysis, and morphological markers). Their CAD system distinguished between benign, intermediate, and malignant hepatocellular carcinoma and also allowed for the classification of subtypes, which was previously considered difficult (12). In this study, we obtained higher-contrast, multitemporal TICs in the prototype sequence, which enabled us to perform detailed analysis.…”

The fractal and textural analysis of glomeruli in obese and non-obese patients

“…All these models could in the future increase the potential diagnostic sensitivity and accuracy of computational methods such as GLCM in pathology and related fields. 33 , 34 …”