An MR-Based Radiomics Model for Differentiation Between Hepatocellular Carcinoma and Focal Nodular Hyperplasia in Non-Cirrhotic Liver

Abstract

Purpose:This study aimed to develop and validate a radiomics model for differentiating between hepatocellular carcinoma (HCC) and focal nodular hyperplasia (FNH) in non-cirrhotic livers using Gd-DTPA contrast-enhanced magnetic resonance imaging (MRI).Methods:We retrospectively enrolled 149 HCC patients and 75 FNH patients seen between May 2015 and May 2019 at our center and randomly allocated patients to a training set (n = 156) and a validation set (n = 68). A total of 2,260 radiomics features were extracted from the arterial phase and portal venous phase of Gd-DTPA contrast-enhanced MRI. Using Max-Relevance and Min-Redundancy, random forests, and the least absolute shrinkage and selection operator algorithm for dimensionality reduction, multivariable logistic regression was used to build the radiomics model. A clinical model and combined model were also established. The diagnostic performance of the three models was compared. Results:Eight radiomics features were chosen to build a radiomics model, and four clinical factors (age, sex, HbsAg, and enhancement pattern) were chosen to build the clinical model. When evaluating the performance of three models, the clinical model that included clinical data and visual MRI findings achieved excellent performance in the training set (AUC, 0.937; 95% CI, 0.887–0.970) and the validation set (AUC, 0.903; 95% CI, 0.807–0.962), and there was no significant difference between the radiomics model and the clinical model. The AUC of the combined model was significantly better than that of the clinical model for both the training (0.984 vs. 0.937, p = 0.002) and validation (0.972 vs. 0.903, p = 0.032) sets.Conclusions:The combined model based on clinical and radiomics features can well distinguish HCC from FNH in non-cirrhotic liver. Our model may assist clinicians in the clinical decision-making process.

The Value of Contrast‐Enhanced Ultrasound Liver Imaging Reporting and Data System in the Diagnosis of Hepatocellular Carcinoma: A Meta‐Analysis

“…Among all methods used in the early diagnosis of HCC, radiological examinations, including computerized tomography (CT), magnetic resonance imaging (MRI), and contrast‐enhanced ultrasound (CEUS), are widely used for its noninvasiveness. Based on these examinations, radiomics become a useful tool in the diagnosis and prognosis of liver tumors 4–6 . Compared with CT or MRI, the CEUS has some unique advantages.…”

HRH4 may be a new predictor for preterm birth

“…Hub genes were screened via integrated analysis of three algorithms consisting of least absolute shrinkage and selection operator (LASSO) regression analysis, support vector machine-recursive feature elimination (SVM-RFE), and random forest. To screen the diagnostic gene, the DEGs were performed the LASSO regression analysis in the "glmnet" R package [11]. Meanwhile, SVM-RFE is a very effective feature selection algorithm, it can lter relevant features and remove relatively insigni cant feature variables to achieve higher classi cation performanc e [12].…”

“…Similarly, Random Forest is an ensembles-learning algorithm forming with a series of decision trees [13]. The random forest method in the "randomForest" package of R software analyzed the DEGs and screen the diagnostic gene [11]. Finally, the key genes identi ed by the three algorithms described above were selected by Venn diagram.…”