Departments of Diagnostic Radiology and Nuclear Medicine (I.Y., Y.S., U.T.), Comprehensive Reproductive Medicine (N.M., K.W., N.O., A.W.), Human Pathology (D.K., Y.E.), and Oral and Maxillofacial Radiology (J.S.), Graduate School, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8519, Japan.
Radiol Imaging Cancer. 2019 Nov 29;1(2):e190054. doi: 10.1148/rycan.2019190054. eCollection 2019 Nov.
To determine the feasibility of texture analysis (TA) of apparent diffusion coefficient (ADC) maps for predicting histologic grade (HG) and recurrence-free survival (RFS) in patients with endometrial carcinoma (EMC).
One hundred twenty-one patients with EMC were examined by using a 1.5-T MRI system and diffusion-weighted imaging (DWI) with values of 0 and 1000 sec/mm. Software with volumes of interest on ADC maps was used to extract 45 texture features including higher-order texture features. Receiver operating characteristic analysis was performed to compare the diagnostic performance of the random forest (RF) model and ADC values for HG and recurrence.
Area under the curve (AUC) for predicting high-grade EMCs was significantly larger for RF model than for ADC values (0.967 vs 0.898; = .0336). AUC for predicting recurrence was larger for the RF model than for ADC values (0.890 vs 0.875; = .7248), although the difference was not significant. Mean RFS was significantly shorter for high-grade EMCs than for low-grade EMCs ( = .0002; hazard ratio, 4.9) and for ADC values less than or equal to 0.802 × 10 mm/sec than for ADC values greater than 0.802 × 10 mm/sec ( < .0001; hazard ratio, 32.9). RF model showed that the mean RFS was significantly shorter for the presence of recurrence than for its absence ( < .0001; hazard ratio, 94.7).
TA of ADC maps had significantly higher diagnostic performance than did ADC values for predicting HG and was a more useful indicator than HG and ADC values for predicting RFS in patients with EMC. Comparative Studies, Genital/Reproductive, MR-Diffusion Weighted Imaging, MR-Imaging, Neoplasms-Primary, Pathology, Pelvis, Tissue Characterization, Uterus© RSNA, 2019.
旨在探讨表观扩散系数（ADC）图纹理分析（TA）预测子宫内膜癌（EMC）患者组织学分级（HG）和无复发生存率（RFS）的可行性。
121 例 EMC 患者采用 1.5T MRI 系统和扩散加权成像（DWI）， 值为 0 和 1000 sec/mm。使用 ADC 图感兴趣容积软件提取 45 个纹理特征，包括高阶纹理特征。采用受试者工作特征（ROC）分析比较随机森林（RF）模型和 ADC 值预测 HG 和复发的诊断性能。
预测高级别 EMC 的曲线下面积（AUC），RF 模型明显大于 ADC 值（0.967 比 0.898； =.0336）。预测复发的 AUC ，RF 模型大于 ADC 值（0.890 比 0.875； =.7248），但差异无统计学意义。高级别 EMC 的平均 RFS 明显短于低级别 EMC（ =.0002；危险比，4.9），ADC 值小于或等于 0.802×10 mm/sec 明显短于 ADC 值大于 0.802×10 mm/sec（ <.0001；危险比，32.9）。RF 模型显示，复发存在的平均 RFS 明显短于不存在（ <.0001；危险比，94.7）。
与 ADC 值相比，ADC 图 TA 预测 HG 的诊断性能显著提高，并且是预测 EMC 患者 RFS 比 HG 和 ADC 值更有用的指标。
