Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, 266003, China.
Department of Pathology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, 266003, China.
J Magn Reson Imaging. 2021 Jun;53(6):1683-1696. doi: 10.1002/jmri.27532. Epub 2021 Feb 18.
Preoperative prediction of soft tissue sarcoma (STS) grade is important for treatment decisions. Therefore, formulation an STS grade model is strongly needed.
To develop and test an magnetic resonance imaging (MRI)-based radiomics nomogram for predicting the grade of STS (low-grade vs. high grade).
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.
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.
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.
The proposed noninvasive MRI-based radiomics models showed good performance in differentiating low-grade from high-grade STSs.
3 TECHNICAL EFFICACY STAGE: 2.
术前预测软组织肉瘤（STS）的分级对于治疗决策非常重要。因此，强烈需要建立 STS 分级模型。
建立并验证基于磁共振成像（MRI）的放射组学列线图，用于预测 STS（低级别与高级别）的分级。
回顾性
180 例经病理结果证实的 STS 患者分别来自两家独立机构（训练集，N=109；外部验证集，N=71）。
磁场强度/序列：1.5T 和 3.0T 下采集未增强 T1 加权（T1WI）和脂肪抑制 T2 加权图像（FS-T2WI）。
临床-MRI 特征包括年龄、性别、肿瘤-淋巴结-转移（TNM）分期、美国癌症联合委员会（AJCC）分期、无进展生存期（PFS）和 MRI 形态学特征（即边缘）。通过最小冗余最大相关性（MRMR）方法和最小绝对值收缩和选择算子（LASSO）算法，在 T1WI 和 FS-T2WI 图像上提取放射组学特征。选择的特征构建了三个放射组学特征模型（RS-T1、RS-FST2 和 RS-Combined）。应用单变量和多变量逻辑回归分析筛选显著风险因素。通过结合放射组学特征和风险因素，构建放射组学列线图。
临床-MRI 特征采用单变量分析。在外部验证集中验证模型性能（判别、校准和临床实用性）。在外部验证集中，RS-T1 模型、RS-FST2 模型和 RS-Combined 模型的曲线下面积（AUC）分别为 0.645、0.641 和 0.829。包含显著风险因素和 RS-Combined 模型的放射组学列线图在训练集和外部验证集中的 AUC 分别为 0.916（95%CI，0.866-0.966）和 0.879（95%CI，0.791-0.967），表现出良好的校准和良好的临床实用性。
所提出的基于非侵入性 MRI 的放射组学模型在区分低级别和高级别 STS 方面表现出良好的性能。
3
2
