Wang H, Zhang J, Bao S, et al. - A retrospective study was conducted to create a radiomics-based machine method for differentiation between malignant and benign soft-tissue masses. A total of 206 cases were included in this study. They divided data of 206 cases into a training set (n = 69) and two validation sets (n = 64, 73, respectively). Researchers trained twelve machine-learning methods to establish classification models to prognosticate the likelihood of malignancy of each lesion. A one-way analysis of variance (ANOVA) test was conducted for continuous variables as appropriate and χ²test or Fisher's exact test was carried out for analyzing categorical variables as appropriate. For identifying between malignant and benign soft-tissue masses, a machine-learning nomogram based on radiomics was found to be accurate.