基于预处理双参数 MRI 的放射组学特征可预测前列腺癌生化复发：初步研究结果
Radiomic features from pretreatment biparametric MRI predict prostate cancer biochemical recurrence: Preliminary findings.
机构信息
Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA.
Department of Diagnostic Radiology, University of Turku, Finland.
出版信息
J Magn Reson Imaging. 2018 Dec;48(6):1626-1636. doi: 10.1002/jmri.26178. Epub 2018 May 7.
BACKGROUND
Radiomics or computer-extracted texture features derived from MRI have been shown to help quantitatively characterize prostate cancer (PCa). Radiomics have not been explored depth in the context of predicting biochemical recurrence (BCR) of PCa.
PURPOSE
To identify a set of radiomic features derived from pretreatment biparametric MRI (bpMRI) that may be predictive of PCa BCR.
STUDY TYPE
Retrospective.
SUBJECTS
In all, 120 PCa patients from two institutions, I and I , partitioned into training set D (N = 70) from I and independent validation set D (N = 50) from I . All patients were followed for ≥3 years.
SEQUENCE
3T, T -weighted (T WI) and apparent diffusion coefficient (ADC) maps derived from diffusion-weighted sequences.
ASSESSMENT
PCa regions of interest (ROIs) on T WI were annotated by two experienced radiologists. Radiomic features from bpMRI (T WI and ADC maps) were extracted from the ROIs. A machine-learning classifier (C ) was trained with the best discriminating set of radiomic features to predict BCR (p ).
STATISTICAL TESTS
Wilcoxon rank-sum tests with P < 0.05 were considered statistically significant. Differences in BCR-free survival at 3 years using p was assessed using the Kaplan-Meier method and compared with Gleason Score (GS), PSA, and PIRADS-v2.
RESULTS
Distribution statistics of co-occurrence of local anisotropic gradient orientation (CoLlAGe) and Haralick features from T WI and ADC were associated with BCR (P < 0.05) on D . C predictions resulted in a mean AUC = 0.84 on D and AUC = 0.73 on D . A significant difference in BCR-free survival between the predicted classes (BCR + and BCR-) was observed (P = 0.02) on D compared to those obtained from GS (P = 0.8), PSA (P = 0.93) and PIRADS-v2 (P = 0.23).
DATA CONCLUSION
Radiomic features from pretreatment bpMRI can be predictive of PCa BCR after therapy and may help identify men who would benefit from adjuvant therapy.
LEVEL OF EVIDENCE
4 Technical Efficacy: Stage 5 J. Magn. Reson. Imaging 2018;48:1626-1636.
背景
从 MRI 提取的放射组学或计算机提取的纹理特征已被证明有助于定量描述前列腺癌（PCa）。在预测 PCa 生化复发（BCR）方面，放射组学尚未深入研究。
目的
从预处理双参数 MRI（bpMRI）中确定一组放射组学特征，这些特征可能对 PCa BCR 有预测作用。
研究类型
回顾性研究。
受试者
本研究共纳入来自两个机构（I 和 II）的 120 例 PCa 患者，其中 70 例来自机构 I 的训练集 D，50 例来自机构 I 的独立验证集 D。所有患者均随访≥3 年。
序列
3T，T2 加权（T WI）和来自扩散加权序列的表观扩散系数（ADC）图。
评估
由两位有经验的放射科医生对 T WI 上的 PCa 感兴趣区（ROI）进行注释。从 ROI 中提取 bpMRI（T WI 和 ADC 图）的放射组学特征。使用具有最佳判别力的放射组学特征集训练机器学习分类器（C）来预测 BCR（p）。
统计学检验
具有 P<0.05 的 Wilcoxon 秩和检验被认为具有统计学意义。使用 p 评估 3 年时 BCR 无复发生存率的差异，使用 Kaplan-Meier 方法进行比较，并与 Gleason 评分（GS）、PSA 和 PIRADS-v2 进行比较。
结果
在 D 上，T WI 和 ADC 上的局部各向异性梯度方向（CoLlAGe）和 Haralick 特征的共现分布统计数据与 BCR 相关（P<0.05）。在 D 上，C 的预测结果平均 AUC=0.84，在 D 上 AUC=0.73。与从 GS（P=0.8）、PSA（P=0.93）和 PIRADS-v2（P=0.23）获得的结果相比，在 D 上观察到预测类别（BCR+和 BCR-）之间 BCR 无复发生存率的显著差异（P=0.02）。
数据结论
治疗前 bpMRI 的放射组学特征可预测 PCa BCR，可能有助于识别需要辅助治疗的患者。
证据水平
4 级 技术效果：第 5 阶段 J. Magn. Reson. Imaging 2018;48:1626-1636.
Zotero 插件