Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands.
Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands.
Ultrasound Med Biol. 2024 Aug;50(8):1194-1202. doi: 10.1016/j.ultrasmedbio.2024.04.007. Epub 2024 May 11.
To assess the value of 3D multiparametric ultrasound imaging, combining hemodynamic and tissue stiffness quantifications by machine learning, for the prediction of prostate biopsy outcomes.
After signing informed consent, 54 biopsy-naïve patients underwent a 3D dynamic contrast-enhanced ultrasound (DCE-US) recording, a multi-plane 2D shear-wave elastography (SWE) scan with manual sweeping from base to apex of the prostate, and received 12-core systematic biopsies (SBx). 3D maps of 18 hemodynamic parameters were extracted from the 3D DCE-US quantification and a 3D SWE elasticity map was reconstructed based on the multi-plane 2D SWE acquisitions. Subsequently, all the 3D maps were segmented and subdivided into 12 regions corresponding to the SBx locations. Per region, the set of 19 computed parameters was further extended by derivation of eight radiomic features per parameter. Based on this feature set, a multiparametric ultrasound approach was implemented using five different classifiers together with a sequential floating forward selection method and hyperparameter tuning. The classification accuracy with respect to the biopsy reference was assessed by a group-k-fold cross-validation procedure, and the performance was evaluated by the Area Under the Receiver Operating Characteristics Curve (AUC).
Of the 54 patients, 20 were found with clinically significant prostate cancer (csPCa) based on SBx. The 18 hemodynamic parameters showed mean AUC values varying from 0.63 to 0.75, and SWE elasticity showed an AUC of 0.66. The multiparametric approach using radiomic features derived from hemodynamic parameters only produced an AUC of 0.81, while the combination of hemodynamic and tissue-stiffness quantifications yielded a significantly improved AUC of 0.85 for csPCa detection (p-value < 0.05) using the Gradient Boosting classifier.
Our results suggest 3D multiparametric ultrasound imaging combining hemodynamic and tissue-stiffness features to represent a promising diagnostic tool for biopsy outcome prediction, aiding in csPCa localization.
评估通过机器学习结合血流动力学和组织硬度定量的 3D 多参数超声成像在预测前列腺活检结果中的价值。
在签署知情同意书后，54 名首次接受前列腺活检的患者接受了 3D 动态对比增强超声（DCE-US）记录、从前列腺底部到顶部的多平面 2D 剪切波弹性成像（SWE）手动扫查，并接受了 12 核系统活检（SBx）。从 3D DCE-US 定量中提取了 18 个血流动力学参数的 3D 图谱，并基于多平面 2D SWE 采集重建了 3D SWE 弹性图谱。随后，对所有 3D 图谱进行分割，并分为与 SBx 位置相对应的 12 个区域。对于每个区域，根据参数衍生出的 8 个放射组学特征，进一步扩展了 19 个计算参数的集合。基于该特征集，使用 5 种不同的分类器和顺序浮动前向选择方法以及超参数调优，实现了一种多参数超声方法。使用组-k 折交叉验证程序评估分类准确性，并通过接收者操作特征曲线下面积（AUC）评估性能。
在 54 名患者中，根据 SBx，有 20 名患者发现患有临床显著前列腺癌（csPCa）。18 个血流动力学参数的 AUC 值从 0.63 到 0.75 不等，SWE 弹性的 AUC 值为 0.66。仅使用血流动力学参数衍生的放射组学特征的多参数方法产生了 0.81 的 AUC，而血流动力学和组织硬度定量的组合使用梯度提升分类器产生了显著提高的 0.85 的 AUC，用于 csPCa 检测（p 值<0.05）。
我们的结果表明，结合血流动力学和组织硬度特征的 3D 多参数超声成像代表了一种有前途的活检结果预测诊断工具，有助于 csPCa 的定位。
