文献速递泌尿生殖腹部MR

基于机器学习的MR影像组学分析有助于提高PI-RADS v2对临床有意义前列腺癌的诊断效能

Machine learning-based analysis of MR radiomics can help to improve the diagnostic performance of PI-RADS v2 in clinically relevant prostate cancer.
PubMed 文献 · Eur Radiol · 2017-04-03

本研究纳入54例前列腺癌患者术前行多参数MRI,基于组织学-影像学对照对54个肿瘤、47个正常外周带和48个正常移行带进行分析,用PI-RADS评分并提取影像组学特征,构建支持向量机模型。结果显示影像组学模型对肿瘤与正常移行带的鉴别AUC显著高于PI-RADS,联合影像组学后PI-RADS对肿瘤与正常外周带及移行带的鉴别效能均显著提高。

要点

  • 影像组学模型鉴别前列腺癌与正常移行带的AUC为0.955,显著高于PI-RADS的0.878。
  • 影像组学联合PI-RADS后,前列腺癌与正常外周带鉴别的AUC提高至0.983。
  • DKI衍生的Dapp和Kapp是诊断前列腺癌的两个强标志物。

核心结论

  • 基于机器学习的MR影像组学分析有助于提高PI-RADS对临床有意义前列腺癌的诊断效能。

研究设计与样本

  • 经IRB批准的研究,纳入54例前列腺癌患者,术前行多参数MRI,基于组织学-影像学对照分析54个肿瘤、47个正常外周带和48个正常移行带,采用支持向量机分别以影像组学、PI-RADS评分及两者联合训练预测模型,通过ROC分析进行配对比较。

诊断标准与关键数值

  • 影像组学模型鉴别前列腺癌与正常移行带的AUC为0.955(95%CI 0.923-0.976),高于PI-RADS的AUC 0.878(95%CI 0.834-0.914),P<0.001。
  • 影像组学模型与PI-RADS鉴别前列腺癌与正常外周带的AUC分别为0.972(95%CI 0.945-0.988)和0.940(95%CI 0.905-0.965),两者差异无统计学意义(P=0.097)。
  • 联合影像组学后,PI-RADS鉴别前列腺癌与正常外周带的AUC提高至0.983(95%CI 0.960-0.995),鉴别前列腺癌与正常移行带的AUC提高至0.968(95%CI 0.940-0.985)。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVE: To investigate whether machine learning-based analysis of MR radiomics can help improve the performance PI-RADS v2 in clinically relevant prostate cancer (PCa).

METHODS: This IRB-approved study included 54 patients with PCa undergoing multi-parametric (mp) MRI before prostatectomy. Imaging analysis was performed on 54 tumours, 47 normal peripheral (PZ) and 48 normal transitional (TZ) zone based on histological-radiological correlation. Mp-MRI was scored via PI-RADS, and quantified by measuring radiomic features. Predictive model was developed using a novel support vector machine trained with: (i) radiomics, (ii) PI-RADS scores, (iii) radiomics and PI-RADS scores. Paired comparison was made via ROC analysis.

RESULTS: For PCa versus normal TZ, the model trained with radiomics had a significantly higher area under the ROC curve (Az) (0.955 [95% CI 0.923-0.976]) than PI-RADS (Az: 0.878 [0.834-0.914], p < 0.001). The Az between them was insignificant for PCa versus PZ (0.972 [0.945-0.988] vs. 0.940 [0.905-0.965], p = 0.097). When radiomics was added, performance of PI-RADS was significantly improved for PCa versus PZ (Az: 0.983 [0.960-0.995]) and PCa versus TZ (Az: 0.968 [0.940-0.985]).

CONCLUSION: Machine learning analysis of MR radiomics can help improve the performance of PI-RADS in clinically relevant PCa.

KEY POINTS: • Machine-based analysis of MR radiomics outperformed in TZ cancer against PI-RADS. • Adding MR radiomics significantly improved the performance of PI-RADS. • DKI-derived Dapp and Kapp were two strong markers for the diagnosis of PCa.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Wang J, Wu CJ, Bao ML, et al. Machine learning-based analysis of MR radiomics can help to improve the diagnostic performance of PI-RADS v2 in clinically relevant prostate cancer. Eur Radiol. 2017. PMID: 28374077. doi:10.1007/s00330-017-4800-5

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。