Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Technology and Science, Jiefang Avenue, Wuhan, China.
J Xray Sci Technol. 2021;29(2):307-315. doi: 10.3233/XST-200785.
Since Gleason score (GS) 4 + 3 prostate cancer (PCa) has a worse prognosis than GS 3 + 4 PCa, differentiating these two types of PCa is of clinical significance.
To assess the predictive roles of using T2WI and ADC-derived image texture parameters in differentiating GS 3 + 4 from GS 4 + 3 PCa.
Forty-eight PCa patients of GS 3 + 4 and 37 patients of GS 4 + 3 are retrieved and randomly divided into training (60%) and testing (40%) sets. Axial image showing the maximum tumor size is selected in the T2WI and ADC maps for further image texture feature analysis. Three hundred texture features are computed from each region of interest (ROI) using MaZda software. Feature reduction is implemented to obtain 30 optimal features, which are then used to generate the most discriminative features (MDF). Receiver operating characteristic (ROC) curve analysis is performed on MDF values in the training sets to achieve cutoff values for determining the correct rates of discrimination between two Gleason patterns in the testing sets.
ROC analysis on T2WI and ADC-derived MDF values in the training set (n = 51) results in a mean area under the curve (AUC) of 0.953±0.025 (with sensitivity 0.9274±0.0615 and specificity 0.897±0.069), and 0.985±0.013 (with sensitivity 0.9636±0.0446 and specificity 0.9726±0.0258), respectively. Using the corresponding MDF cutoffs, 95.3% (ranges from 76.5% to 100%) and 94.1% (ranged from 76.5% to 100%) of test cases (n = 34) are correctly discriminated using T2WI and ADC-derived MDF values, respectively.
The study demonstrates that using T2WI and ADC-derived image texture parameters has a potential predictive role in differentiating GS 3 + 4 and GS 4 + 3 PCa.
由于 Gleason 评分 (GS) 4+3 前列腺癌 (PCa) 的预后比 GS 3+4 PCa 差，因此区分这两种类型的 PCa 具有临床意义。
评估使用 T2WI 和 ADC 衍生的图像纹理参数在区分 GS 3+4 和 GS 4+3 PCa 中的预测作用。
回顾性收集了 48 例 GS 3+4 患者和 37 例 GS 4+3 患者，随机分为训练集 (60%) 和测试集 (40%)。在 T2WI 和 ADC 图上选择显示最大肿瘤大小的轴位图像，用于进一步的图像纹理特征分析。使用 MaZda 软件从每个感兴趣区 (ROI) 计算 300 个纹理特征。通过特征降维获得 30 个最优特征，然后使用这些特征生成最具判别力的特征 (MDF)。在训练集中对 MDF 值进行 ROC 曲线分析，以获得确定测试集中两种 Gleason 模式正确区分率的截断值。
在训练集 (n=51) 中对 T2WI 和 ADC 衍生的 MDF 值进行 ROC 分析，得到平均曲线下面积 (AUC) 为 0.953±0.025(灵敏度为 0.9274±0.0615，特异性为 0.897±0.069)，0.985±0.013(灵敏度为 0.9636±0.0446，特异性为 0.9726±0.0258)。使用相应的 MDF 截断值，分别使用 T2WI 和 ADC 衍生的 MDF 值对 95.3% (范围为 76.5% 至 100%)和 94.1% (范围为 76.5% 至 100%)的测试病例 (n=34) 进行正确区分。
本研究表明，使用 T2WI 和 ADC 衍生的图像纹理参数在区分 GS 3+4 和 GS 4+3 PCa 方面具有潜在的预测作用。
