Department of Radiology, Peking University People's Hospital, Beijing, P. R. China.
Department of Radiology, Qindao University Medical College Affiliated Yantai Yuhuangding Hospital, Yantai, Shandong, P. R. China.
J Magn Reson Imaging. 2019 Mar;49(3):752-759. doi: 10.1002/jmri.26238. Epub 2018 Nov 14.
Preoperative differentiation between primary sacral chordoma (SC), sacral giant cell tumor (SGCT), and sacral metastatic tumor (SMT) is important for treatment decisions.
To develop and validate a triple-classification radiomics model for the preoperative differentiation of SC, SGCT, and SMT based on T2-weighted fat saturation (T2w FS) and contrast-enhanced T1-weighted (CE T1w) MRI.
Retrospective.
A total of 120 pathologically confirmed sacral patients (54 SCs, 30 SGCTs, and 36 SMTs) were retrospectively analyzed and divided into a training set (n = 83) and a validation set (n = 37).
FIELD STRENGTH/SEQUENCE: The 3.0T axial T2w FS and CE T1w MRI.
Morphology, intensity, and texture features were assessed based on Formfactor, Haralick, Gray-level co-occurrence matrix (GLCM), Gray-level run-length matrix (GLRLM), histogram.
Analysis of variance, least absolute shrinkage and selection operator (LASSO), Pearson correlation, Random Forest (RF), area under the receiver operating characteristic curve (AUC) and accuracy analysis.
The median age of SGCT (33.5, 25.3-45.5) was significantly lower than those of SC (58.0, 48.8-64.3) and SMT (59.0, 46.3-65.5) groups (χ = 37.6; P < 0.05). No significant difference was found when compared in terms of genders, tumor locations, and tumor sizes of SC, SGCT, and SMT ( ; P1 = 0.15, P2 = 0.29, P3 = 0.06). For the differential value, features extracted from joint T2w FS and CE T1w images outperformed those from T2w FS or CE T1w images alone. Compared with CE T1w images, features derived from T2w FS images yielded higher AUC in both training and validating set. The best performance of radiomics model based on joint T2w FS and CE T1w images reached an AUC of 0.773, an accuracy of 0.711.
Our 3.0T MRI-based triple-classification radiomics model is feasible to differentiate SC, SGCT, and SMT, which may be applied to improve the precision of preoperative diagnosis in clinical practice.
4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:752-759.
术前区分原发性骶骨脊索瘤（SC）、骶骨巨细胞瘤（SGCT）和骶骨转移瘤（SMT）对于治疗决策很重要。
基于 T2 加权脂肪饱和（T2w FS）和对比增强 T1 加权（CE T1w）MRI ，开发和验证用于 SC、SGCT 和 SMT 术前鉴别诊断的三分类放射组学模型。
回顾性。
共回顾性分析了 120 例经病理证实的骶骨患者（54 例 SC、30 例 SGCT 和 36 例 SMT），并将其分为训练集（n=83）和验证集（n=37）。
场强/序列：3.0T 轴位 T2w FS 和 CE T1w MRI。
基于形态、强度和纹理特征进行评估，包括形态因子、哈勒尼克、灰度共生矩阵（GLCM）、灰度游程长度矩阵（GLRLM）、直方图。
方差分析、最小绝对收缩和选择算子（LASSO）、皮尔逊相关性、随机森林（RF）、接收者操作特征曲线下面积（AUC）和准确性分析。
SGCT 的中位年龄（33.5，25.3-45.5）明显低于 SC（58.0，48.8-64.3）和 SMT（59.0，46.3-65.5）组（χ²=37.6；P<0.05）。SC、SGCT 和 SMT 之间在性别、肿瘤位置和肿瘤大小方面没有显著差异（ ；P1=0.15，P2=0.29，P3=0.06）。在鉴别值方面，联合 T2w FS 和 CE T1w 图像提取的特征优于单独 T2w FS 或 CE T1w 图像提取的特征。与 CE T1w 图像相比，T2w FS 图像提取的特征在训练集和验证集均能获得更高的 AUC。基于联合 T2w FS 和 CE T1w 图像的放射组学模型的最佳性能达到了 0.773 的 AUC 和 0.711 的准确率。
我们的 3.0T MRI 三分类放射组学模型能够区分 SC、SGCT 和 SMT，这可能有助于提高临床实践中术前诊断的精度。
4 级技术疗效：2 期 J. Magn. Reson. Imaging 2019;49:752-759.
