BackgroundPreoperative differentiation between malignant and benign soft‐tissue masses is important for treatment decisions.Purpose/HypothesisTo construct/validate a radiomics‐based machine method for differentiation between malignant and benign soft‐tissue masses.Study TypeRetrospective.PopulationIn all, 206 cases.Field Strength/SequenceThe T1 sequence was acquired with the following range of parameters: relaxation time / echo time (TR/TE), 352–550/2.75–19 msec. The T2 sequence was acquired with the following parameters: TR/TE, 700–6370/40–120 msec. The data were divided into a 3.0T training cohort, a 1.5T MR validation cohort, and a 3.0T external validationcohort.AssessmentTwelve machine‐learning methods were trained to establish classification models to predict the likelihood of malignancy of each lesion. The data of 206 cases were separated into a training set (n = 69) and two validation sets (n = 64, 73, respectively).Statistical Tests1) Demographic characteristics: a one‐way analysis of variance (ANOVA) test was performed for continuous variables as appropriate. The χ2 test or Fisher's exact test was performed for comparing categorical variables as appropriate. 2) The performance of four feature selection methods (least absolute shrinkage and selection operator [LASSO], Boruta, Recursive feature elimination [RFE, and minimum redundancy maximum relevance [mRMR]) and three classifiers (support vector machine [SVM], generalized linear models [GLM], and random forest [RF]) were compared for selecting the likelihood of malignancy of each lesion. The performance of the radiomics model was assessed using area under the receiver‐operating characteristic curve (AUC) and accuracy (ACC) values.ResultsThe LASSO feature method + RF classifier achieved the highest AUC of 0.86 and 0.82 in the two validation cohorts. The nomogram achieved AUCs of 0.96 and 0.88, respectively, in the two validation sets, which was higher than that of the radiomic algorithm in the two validation sets and clinical model of the validation 1 set (0.92, 0.88 respectively). The accuracy, sensitivity, and specificity of the radiomics nomogram were 90.5%, 100%, and 80.6%, respectively, for validation set 1; and 80.8%, 75.8%, and 85.0% for validation set 2.Data ConclusionA machine‐learning nomogram based on radiomics was accurate for distinguishing between malignant and benign soft‐tissue masses.Evidence Level3Technical EfficacyStage 2 J. Magn. Reson. Imaging 2020;52:873–882.

Background Preoperative prediction of the grade of soft tissue sarcomas (STSs) is important because of its effect on treatment planning. Purpose To assess the value of radiomics features in distinguishing histological grades of STSs. Study Type Retrospective. Population In all, 113 patients with pathology‐confirmed low‐grade (grade I), intermediate‐grade (grade II), or high‐grade (grade III) soft tissue sarcoma were collected. Field Strength/Sequence The 3.0T axial T1‐weighted imaging (T1WI) with 550 msec repetition time (TR); 18 msec echo time (TE), 312 × 312 matrix, fat‐suppressed fast spin‐echo T2WI with 4291 msec TR, 85 msec TE, 312 × 312 matrix. Assessment Multiple machine‐learning methods were trained to establish classification models for predicting STS grades. Eighty STS patients (18 low‐grade [grade I]; 62 high‐grade [grades II–III]) were enrolled in the primary set and we tested the model with a validation set with 33 patients (7 low‐grade, 26 high‐grade). Statistical Tests 1) Student's t‐tests were applied for continuous variables and the χ2 test were applied for categorical variables between low‐grade STS and high‐grade STS groups. 2) For feature subset selection, either no subset selection or recursive feature elimination was performed. This technology was combined with random forest and support vector machine‐learning methods. Finally, to overcome the disparity in the frequencies of the STS grades, each machine‐learning model was trained i) without subsampling, ii) with the synthetic minority oversampling technique, and iii) with random oversampling examples, for a total of 12 combinations of machine‐learning algorithms that were assessed, trained, and tested in the validation cohort. Results The best classification model for the prediction of STS grade was a combination of features selected by recursive feature elimination and random forest classification algorithms with a synthetic minority oversampling technique, which had an area under the curve of 0.9615 (95% confidence interval 0.8944–1.0) in the validation set. Data Conclusion Radiomics feature‐based machine‐learning methods are useful for distinguishing STS grades. Level of Evidence: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:791–797.

Background: Preoperative differentiation between malignant and benign tumors is important for treatment decisions. Purpose/Hypothesis: To investigate/validate a radiomics nomogram for preoperative differentiation between malignant and benign masses. Study Type: Retrospective. Population: Imaging data of 91 patients. Field Strength/Sequence: T 1 -weighted images (570 msec repetition time [TR]; 17.9 msec echo time [TE], 200-400 mm field of view [FOV], 208-512 × 208-512 matrix), fat-suppressed fast-spin-echo (FSE) T 2 -weighted images (T 2 WIs) (4331 msec TR; 87.9 msec TE, 200-400 mm FOV, 312 × 312 matrix), slice thickness 4 mm, and slice spacing 1 mm. Assessment: Fat-suppressed FSE T 2 WIs were selected for extraction of features. Radiomics features were extracted from fat-suppressed T 2 WIs. A radiomics signature was generated from the training dataset using least absolute shrinkage and selection operator algorithms. Independent risk factors were identified by multivariate logistic regression analysis and a radiomics nomogram was constructed. Nomogram capability was evaluated in the training dataset and validated in the validation dataset. Performance of the nomogram, radiomics signature, and clinical model were compared. Statistical Tests: 1) Independent t-test or Mann-Whitney U-test: for continuous variables. Fisher's exact test or χ 2 test: comparing categorical variables between two groups. Univariate analysis: evaluating associations between clinical/morphological characteristics and malignancy. 2) Least absolute shrinkage and selection operator (LASSO)-logistic regression model: selection of malignancy features. 3) Significant clinical/morphological characteristics and radiomics signature were input variables for multiple logistic regression analysis. Area under the curve (AUC): evaluation of ability of the nomogram to identify malignancy. Hosmer-Lemeshow test and decision curve: evaluation and validation of nomogram results. Results: The radiomics nomogram was able to differentiate malignancy from benignity in the training and validation datasets with an AUC of 0.94. The nomogram outperformed both the radiomics signature and clinical model alone. Data Conclusion: This radiomics nomogram is a noninvasive, low-cost preoperative prediction method combining the radiomics signature and clinical model. Level of Evidence: 3 Technical Efficacy: Stage 2

Background Preoperative prediction of soft tissue sarcoma (STS) grade is important for treatment decisions. Therefore, formulation an STS grade model is strongly needed. Purpose To develop and test an magnetic resonance imaging (MRI)‐based radiomics nomogram for predicting the grade of STS (low‐grade vs. high grade). Study Type Retrospective Population One hundred and eighty patients with STS confirmed by pathologic results at two independent institutions were enrolled (training set, N = 109; external validation set, N = 71). Field Strength/Sequence Unenhanced T1‐weighted (T1WI) and fat‐suppressed T2‐weighted images (FS‐T2WI) were acquired at 1.5 T and 3.0 T. Assessment Clinical‐MRI characteristics included age, gender, tumor‐node‐metastasis (TNM) stage, American Joint Committee on Cancer (AJCC) stage, progression‐free survival (PFS), and MRI morphological features (ie, margin). Radiomics feature extraction were performed on T1WI and FS‐T2WI images by minimum redundancy maximum relevance (MRMR) method and least absolute shrinkage and selection operator (LASSO) algorithm. The selected features constructed three radiomics signatures models (RS‐T1， RS‐FST2, and RS‐Combined). Univariate and multivariate logistic regression analysis were applied for screening significant risk factors. Radiomics nomogram was constructed by incorporating the radiomics signature and risk factors. Statistical Tests Clinical‐MRI characteristics were performed by a univariate analysis. Model performances (discrimination, calibration, and clinical usefulness) were validated in the external validation set. The RS‐T1 model, RS‐FST2 model, and RS‐Combined model had an area under curves (AUCs) of 0.645, 0.641, and 0.829, respectively, in the external validation set. The radiomics nomogram, incorporating significant risk factors and the RS‐Combined model had AUCs of 0.916 (95%CI, 0.866–0.966, training set) and 0.879 (95%CI, 0.791–0.967, external validation set), and demonstrated good calibration and good clinical utility. Data Conclusion The proposed noninvasive MRI‐based radiomics models showed good performance in differentiating low‐grade from high‐grade STSs. Level of Evidence 3 Technical Efficacy Stage 2

No abstract