Radiomics analysis of contrast-enhanced CT for staging liver fibrosis: an update for image biomarker

Abstract

Background To establish and validate a radiomics-based model for staging liver fibrosis at contrast-enhanced CT images. Materials and methods This retrospective study developed two radiomics-based models (R-score: radiomics signature; R-fibrosis: integrate radiomic and serum variables) in a training cohort of 332 patients (median age, 59 years; interquartile range, 51–67 years; 256 men) with biopsy-proven liver fibrosis who underwent contrast-enhanced CT between January 2017 and December 2020. Radiomic features were extracted from non-contrast, arterial and portal phase CT images and selected using the least absolute shrinkage and selection operator (LASSO) logistic regression to differentiate stage F3–F4 from stage F0–F2. Optimal cutoffs to diagnose significant fibrosis (stage F2–F4), advanced fibrosis (stage F3–F4) and cirrhosis (stage F4) were determined by receiver operating characteristic curve analysis. Diagnostic performance was evaluated by area under the curve, Obuchowski index, calibrations and decision curve analysis. An internal validation was conducted in 111 randomly assigned patients (median age, 58 years; interquartile range, 49–66 years; 89 men). Results In the validation cohort, R-score and R-fibrosis (Obuchowski index, 0.843 and 0.846, respectively) significantly outperformed aspartate transaminase-to-platelet ratio (APRI) (Obuchowski index, 0.651; p < .001) and fibrosis-4 index (FIB-4) (Obuchowski index, 0.676; p < .001) for staging liver fibrosis. Using the cutoffs, R-fibrosis and R-score had a sensitivity range of 70–87%, specificity range of 71–97%, and accuracy range of 82–86% in diagnosing significant fibrosis, advanced fibrosis and cirrhosis. Conclusion Radiomic analysis of contrast-enhanced CT images can reach great diagnostic performance of liver fibrosis.

The Application Value of MRI T 2 ∗ WI Radiomics Nomogram in Discriminating Hepatocellular Carcinoma from Intrahepatic Cholangiocarcinoma

“…Radiomics make it possible to extract enormous image features and transform them into data that can quantitatively characterize tumor biology. A great deal of clinical data can be integrated to develop models in favor of clinical decision-making and tumor heterogeneity quantification, which enables noninvasive, comprehensive, and dynamic accurate treatment and prognosis prediction of diseases [6][7][8]. Comprehensive analysis of multiple features tends to be the greatest encouraging approach.…”

Clinical-radiomic analysis for non-invasive prediction of liver steatosis on non-contrast CT: A pilot study

“…During radiomic features selection and radiomics signature establishment, Lasso regression and SVM algorithm were applied. We chose the LASSO model owing to its model interpretability benefit and its excellent performance in multiple radiomics-related research ( Ji et al, 2019 ; Wang et al, 2022b ; Wang et al, 2022c ). The advantage of the SVM is that an SVM classifier relies merely on the support vectors, and the classifier function is not affected by the whole dataset.…”

“…Secondly, LASSO regression analysis with penalty parameter tuning conducted by 10-fold cross-validation was used to select the training cohort’s steatosis-related features with non-zero coefficient. We selected LASSO because of its interpretation advantage and its excellent performance in multiple studies about radiomics ( Ji et al, 2019 ; Wang et al, 2022b ; Wang et al, 2022c ). We adopted Support vector machine (SVM) based on selected radiomics feature for model training on R software (version 3.6.1, http://www.r-project.org ).…”

Establishment and Validation of a Machine Learning Prediction Model Based on Big Data for Predicting the Risk of Bone Metastasis in Renal Cell Carcinoma Patients

“…Six ML models, including logistic regression (LR), gradient boosting machine (GBM), extreme gradient boosting (XGB), Random Forest (RF), Decision Tree (DT), and Naive Bayesian model (NBC), were used to build prediction models, the performance of which was compared by 10-fold cross-validation method [16][17][18][19]. The model with the greatest AUC value was regarded as the preferred prediction model, whose corresponding network calculator is designed to individually assess the risk of BM in patients with RCC [20][21][22][23].…”