文献速递泌尿生殖腹部MR

机器学习在MRI上识别临床显著前列腺癌:一项荟萃分析

Machine learning for the identification of clinically significant prostate cancer on MRI: a meta-analysis.
PubMed 文献 · Eur Radiol · 2020-06-30

该荟萃分析系统检索截至2019年7月31日的文献,纳入12项机器学习诊断准确性研究,评估其在MRI上识别临床显著前列腺癌的效能。总体合并AUC为0.86(95%CI 0.81-0.91),活检参考标准亚组AUC为0.85(95%CI 0.79-0.91),根治性前列腺切除术亚组AUC为0.88(95%CI 0.76-0.99);深度学习组AUC为0.78(95%CI 0.69-0.86),非深度学习组AUC为0.90(95%CI 0.85-0.94)。作者认为机器学习流程显示出良好准确性,应进一步研究,并可能在设计和结果报告方面实现更好的标准化。

要点

  • 机器学习在MRI上识别临床显著前列腺癌的总体合并AUC为0.86(95%CI 0.81-0.91)。
  • 深度学习流程AUC为0.78(95%CI 0.69-0.86),低于其他方法的AUC 0.90(95%CI 0.85-0.94)。
  • 活检与根治性前列腺切除术参考标准亚组的合并AUC分别为0.85和0.88,算法准确性相似。

核心结论

  • 使用前列腺MRI的机器学习流程在识别临床显著前列腺癌方面显示出良好准确性,应进一步研究,并可能在设计和结果报告方面实现更好的标准化。

研究设计与样本

  • 研究为系统综述与荟萃分析,系统检索多个医学数据库至2019年7月31日,由两名评审员独立筛选文献,最终纳入12项机器学习诊断准确性研究。
  • 采用随机效应模型估计总体效应量,以I2值评估统计异质性,并用漏斗图探究发表偏倚;亚组分析基于参考标准(活检或根治性前列腺切除术)和机器学习类型(深度与非深度)进行。

诊断标准与关键数值

  • 机器学习识别临床显著前列腺癌的总体合并AUC为0.86(95%CI 0.81-0.91)。
  • 活检参考标准亚组(n=9)合并AUC为0.85(95%CI 0.79-0.91),根治性前列腺切除术亚组(n=3)合并AUC为0.88(95%CI 0.76-0.99)。
  • 深度学习机器学习亚组(n=4)AUC为0.78(95%CI 0.69-0.86),其余8项研究AUC为0.90(95%CI 0.85-0.94)。

临床应用与阅片要点

  • 原文结论认为机器学习流程显示出良好准确性,应进一步研究,并可能在设计和结果报告方面实现更好的标准化。

局限性

  • 总体分析和亚组分析的统计异质性均较高。

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

OBJECTIVES: The aim of this study was to systematically review the literature and perform a meta-analysis of machine learning (ML) diagnostic accuracy studies focused on clinically significant prostate cancer (csPCa) identification on MRI.

METHODS: Multiple medical databases were systematically searched for studies on ML applications in csPCa identification up to July 31, 2019. Two reviewers screened all papers independently for eligibility. The area under the receiver operating characteristic curves (AUC) was pooled to quantify predictive accuracy. A random-effects model estimated overall effect size while statistical heterogeneity was assessed with the I2 value. A funnel plot was used to investigate publication bias. Subgroup analyses were performed based on reference standard (biopsy or radical prostatectomy) and ML type (deep and non-deep).

RESULTS: After the final revision, 12 studies were included in the analysis. Statistical heterogeneity was high both in overall and in subgroup analyses. The overall pooled AUC for ML in csPCa identification was 0.86, with 0.81-0.91 95% confidence intervals (95%CI). The biopsy subgroup (n = 9) had a pooled AUC of 0.85 (95%CI = 0.79-0.91) while the radical prostatectomy one (n = 3) of 0.88 (95%CI = 0.76-0.99). Deep learning ML (n = 4) had a 0.78 AUC (95%CI = 0.69-0.86) while the remaining 8 had AUC = 0.90 (95%CI = 0.85-0.94).

CONCLUSIONS: ML pipelines using prostate MRI to identify csPCa showed good accuracy and should be further investigated, possibly with better standardisation in design and reporting of results.

KEY POINTS: • Overall pooled AUC was 0.86 with 0.81-0.91 95% confidence intervals. • In the reference standard subgroup analysis, algorithm accuracy was similar with pooled AUCs of 0.85 (0.79-0.91 95% confidence intervals) and 0.88 (0.76-0.99 95% confidence intervals) for studies employing biopsies and radical prostatectomy, respectively. • Deep learning pipelines performed worse (AUC = 0.78, 0.69-0.86 95% confidence intervals) than other approaches (AUC = 0.90, 0.85-0.94 95% confidence intervals).

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Cuocolo R, Cipullo MB, Stanzione A, et al. Machine learning for the identification of clinically significant prostate cancer on MRI: a meta-analysis. Eur Radiol. 2020. PMID: 32607629. doi:10.1007/s00330-020-07027-w

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。