Department of Electronic, Information, and Bioengineering, Politecnico di Milano, Milan, Italy.
Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy.
J Magn Reson Imaging. 2018 Mar;47(3):829-840. doi: 10.1002/jmri.25791. Epub 2017 Jun 27.
To assess the feasibility of grading soft tissue sarcomas (STSs) using MRI features (radiomics).
MRI (echo planar SE, 1.5T) from 19 patients with STSs and a known histological grading, were retrospectively analyzed. The apparent diffusion coefficient (ADC) maps, obtained by diffusion-weighted imaging acquisitions, were analyzed through 65 radiomic features, intensity-based (first order statistics, FOS) and texture (gray level co-occurrence matrix, GLCM; and gray level run length matrix, GLRLM) features. Feature selection (sequential forward floating search) and classification (k-nearest neighbor classifier) were performed to distinguish intermediate- from high-grade STSs. Classification was performed using the three different sub-groups of features separately as well as all the features together. The entire dataset was divided in three subsets: the training, validation and test set, containing, respectively, 60, 30, and 10% of the data.
Intermediate-grade lesions had a higher and less disperse ADC values compared with high-grade ones: most of FOS related to intensity are higher for the intermediate-grade STSs, while FOS related to signal variability were higher in the high grade (e.g., the feature variance is 2.610 ± 0.910 versus 3.310 ± 1.610 , P = 0.3). The GLCM features related to entropy and dissimilarity were higher in the high-grade. When performing classification, the best accuracy is obtained with a maximum of three features for each subgroup, FOS features being those leading to the best classification (validation set: FOS accuracy 0.90 ± 0.11, area under the curve [AUC] 0.85 ± 0.16; test set: FOS accuracy 0.88 ± 0.25, AUC 0.87 ± 0.34).
Good accuracy and AUC could be obtained using only few Radiomic features, belonging to the FOS class.
4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:829-840.
评估使用 MRI 特征（放射组学）对软组织肉瘤（STS）进行分级的可行性。
回顾性分析了 19 例 STS 患者的 MRI（回波平面 SE，1.5T）资料和已知的组织学分级。通过扩散加权成像采集获得表观扩散系数（ADC）图，通过 65 个放射组学特征进行分析，包括基于强度的特征（一阶统计量，FOS）和纹理特征（灰度共生矩阵，GLCM；和灰度游程长度矩阵，GLRLM）。进行特征选择（顺序前向浮动搜索）和分类（k-最近邻分类器），以区分中高级 STS。使用三种不同的特征子组以及所有特征分别进行分类，并将整个数据集分为三个子集：训练集、验证集和测试集，分别包含数据的 60%、30%和 10%。
中级病变的 ADC 值较高且分布较散，与高级病变相比：大多数与强度相关的 FOS 特征值在中级 STS 中较高，而与信号变异性相关的 FOS 特征值在高级病变中较高（例如，特征方差为 2.610 ± 0.910 与 3.310 ± 1.610 ，P = 0.3）。与熵和不相似性相关的 GLCM 特征在高级病变中较高。在进行分类时，每个子组使用最多三个特征可获得最佳准确性，FOS 特征是导致最佳分类的特征（验证集：FOS 准确性 0.90 ± 0.11，曲线下面积 [AUC] 0.85 ± 0.16；测试集：FOS 准确性 0.88 ± 0.25，AUC 0.87 ± 0.34）。
仅使用少量属于 FOS 类的放射组学特征即可获得良好的准确性和 AUC。
4 级 技术功效：2 期 J. 磁共振成像 2018；47：829-840.
