文献速递泌尿生殖腹部MR

基于影像组学机器学习的重定义评分可稳健识别PI-RADS 3分不确定病灶中的临床显著性前列腺癌

A radiomics machine learning-based redefining score robustly identifies clinically significant prostate cancer in equivocal PI-RADS score 3 lesions.
PubMed 文献 · Abdom Radiol (NY) · 2020-08-01

本研究纳入263例PI-RADS 3分主导病灶患者,构建一步式与两步式影像组学机器学习重定义评分模型,用于筛查临床显著性前列腺癌(csPCa)。一步式模型AUC为0.89(95%CI 0.88-0.90),高于两步式模型的0.87(95%CI 0.86-0.88),差异有统计学意义(P=0.003);决策曲线分析显示两模型在20%至80%阈值概率区间较按PI-RADS 3分或单独影像组学标签分层能显著改善风险预测。作者认为该模型有潜力预测PI-RADS 3分病灶中的csPCa,从而辅助活检决策。

要点

  • 一步式影像组学机器学习模型在PI-RADS 3分病灶中预测csPCa的AUC为0.89(95%CI 0.88-0.90)。
  • 一步式模型AUC高于两步式模型0.87(95%CI 0.86-0.88),差异有统计学意义(P=0.003)。
  • 两位放射科医师主观二分类评估的读者间一致性为中等(Kappa=0.435)。

核心结论

  • 基于影像组学机器学习的重定义评分模型有潜力预测PI-RADS 3分病灶中的临床显著性前列腺癌,从而辅助活检决策。

研究设计与样本

  • 本研究为影像组学研究,纳入263例主导指数病灶评为PI-RADS 3分且接受活检和/或随访的患者构成主要队列。一步式影像组学机器学习模型整合T2WI、DWI和ADC图像的影像组学特征;两步式模型将T2WI、DWI和ADC三个独立影像组学标签分别整合入回归模型。比较两种模型及三个独立标签的AUC、校准曲线和决策曲线分析,并由两位放射科医师进行主观二分类评估、计算Cohen kappa统计量。

诊断标准与关键数值

  • 263例中检出59例(22.4%)临床显著性前列腺癌;一步式模型AUC为0.89(95%CI 0.88-0.90),两步式模型AUC为0.87(95%CI 0.86-0.88),一步式模型AUC更高(P=0.003);两位放射科医师主观二分类评估的读者间一致性为中等(Kappa=0.435)。

临床应用与阅片要点

  • 决策曲线分析显示,在临床显著性前列腺癌阈值概率20%至80%区间,一步式与两步式影像组学机器学习模型较按PI-RADS 3分进行不干预或全部干预、或按单独DWI影像组学标签、ADC影像组学标签、T2WI影像组学标签分层,能显著改善风险预测。

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

PURPOSE: PI-RADS score 3 is recognized as equivocal likelihood of clinically significant prostate cancer (csPCa) occurrence. We aimed to develop a Radiomics machine learning (RML)-based redefining score to screen out csPCa in equivocal PI-RADS score 3 category.

METHODS: Total of 263 patients with the dominant index lesion scored PI-RADS 3 who underwent biopsy and/or follow-up formed the primary cohort. One-step RML (RML-i) model integrated radiomic features of T2WI, DWI, and ADC images all together, and two-step RML (RML-ii) model integrated the three independent radiomic signatures from T2WI (T2WIRS), DWI (DWIRS), and ADC (ADCRS) separately into a regression model. The two RML models, as well as T2WIRS, DWIRS, and ADCRS, were compared using the receiver operating characteristic-derived area under the curve (AUC), calibration plot, and decision-curve analysis (DCA). Two radiologists were asked to give a subjective binary assessment, and Cohen's kappa statistics were calculated.

RESULTS: A total of 59/263 (22.4%) csPCa were identified. Inter-reader agreement was moderate (Kappa = 0.435). The AUC of RML-i (0.89; 95% CI 0.88-0.90) is higher (p = 0.003) than that of RML-ii (0.87; 95% CI 0.86-0.88). The DCA demonstrated that the RML-i and RML-ii significantly improved risk prediction at threshold probabilities of csPCa at 20% to 80% compared with doing-none or doing-all by PI-RADS score 3 or stratifying by separated DWIRS, ADCRS, or T2WIRS.

CONCLUSION: Our RML models have the potential to predict csPCa in PI-RADS score 3 lesions, thus can inform the decision making process of biopsy.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Hou Y, Bao ML, Wu CJ, et al. A radiomics machine learning-based redefining score robustly identifies clinically significant prostate cancer in equivocal PI-RADS score 3 lesions. Abdom Radiol (NY). 2020. PMID: 32740863. doi:10.1007/s00261-020-02678-1

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。