To evaluate the feasibility of using radiomics with precontrast magnetic resonance imaging for classifying hepatocellular carcinoma (HCC) and hepatic haemangioma (HH). This study enrolled 369 consecutive patients with 446 lesions (a total of 222 HCCs and 224 HHs). A training set was constituted by randomly selecting 80% of the samples and the remaining samples were used to test. On magnetic resonance (MR) images of HCC and HH obtained with in-phase, out-phase, T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI) sequences, we outlined the target lesions and extracted 1029 radiomics features, which were classified as first-, second-, higher-order statistics and shape features. Then, the variance threshold, select k best, and least absolute shrinkage and selection operator algorithms were explored for dimensionality reduction of the features. We used four classifiers (decision tree, random forest, K nearest neighbours, and logistic regression) to identify HCC and HH on the basis of radiomics features. Two abdominal radiologists also performed the conventional qualitative analysis for classification of HCC and HH. Diagnostic performances of radiomics and radiologists were evaluated by receiver operating characteristic (ROC) analysis. Valuable radiomics features for building a radiomics signature were extracted from in-phase (n = 22), out-phase (n = 24), T2WI (n = 34) and DWI (n = 24) sequences. In comparison, the logistic regression classifier showed better predictive ability by combining four sequences. In the training set, the area under the ROC curve (AUC) was 0.86 (sensitivity: 0.76; specificity: 0.78), and in the testing set, the AUC was 0.89 (sensitivity: 0.822; specificity: 0.714). The diagnostic performance for the optimal radiomics-based combined model was significantly higher than that for the less experienced radiologist (2-years experience) (AUC = 0.702, p < 0.05), and had no statistic difference with the experienced radiologist (10-years experience) (AUC = 0.908, p>0.05). We developed and validated a radiomics signature as an adjunct tool to distinguish HCC and HH by combining in-phase, out-phase, T2W, and DW MR images, which outperformed the less experienced radiologist (2-years experience), and was nearly equal to the experienced radiologist (10-years experience).

To evaluate the application of conventional MRI histogram analysis based on the whole tumor measurement on assessing meningioma grading. This retrospective study was approved by the institutional review board. A total amount of 90 patients with meningioma were enrolled and the preoperative MRI of them were analyzed. To be specific, the patient group were consisted of 45 patients with grade I, 38 with grade II, and 7 with grade III meningioma. Grade I meningioma is classified as low grade meningioma (LGM), whereas Grade II and III meningioma were combined and classified as high grade meningioma (HGM). ROIs were drawn along the edge of the tumor on each section of T1WI, T2WI, and contrasted T1WI. 3D ROI signal intensity histogram and all its parameters were obtained. Independent t-test and Kruskal-Wallis test were used for comparison between two groups. Univariate logistic regression analysis and Spearman's correlation analysis were used to screen for the parameters with high predictive efficiency, while multivariate logistic regression analysis was used to determine the optimal model for the classification of meningioma. There were significant differences observed between HGM and LGM groups regarding to histogram volume count, uniformity of three sequences, range of T1WI and T2WI, kurtosis, standard deviation, variance, max intensity of T2WI, skewness, mean deviation, minimum intensity, mean value, the 5th percentile, the 10th percentile, the 25th percentile, the 50th percentile, the 75th percentile, and the 90th percentile of contrasted T1WI. Volume count and uniformity were high predictive parameters in distinguishing HGM from LGM. Logistic regression model included contrasted T1WI histogram parameters (i.e. minimum intensity, volume count, skewness, uniformity, and the 75th percentile) showed the best diagnostic efficiency for meningioma grade, with a sensitivity and specificity of 83.9% and 77.4% (AUC = 0.834, cutoff value = 0.413), respectively. The optimal model was achieved with a sensitivity of 71.4% and a specificity of 78.6% in the test set (AUC = 0.791, cutoff value = 0.413). Histogram analysis of conventional MRI based on 3D tumor measurement can be applied in the assessment of meningioma grading in clinical.