文献速递前列腺癌

基于感兴趣区域算法在MRI-FIRST数据库-CAD-FIRST研究中诊断国际泌尿病理学会分级组≥2前列腺癌的性能

Performance of a Region of Interest-based Algorithm in Diagnosing International Society of Urological Pathology Grade Group ≥2 Prostate Cancer on the MRI-FIRST Database-CAD-FIRST Study.
PubMed 文献 · Eur Urol Oncol · 2024-03-16

本研究在MRI-FIRST数据集上回顾性勾画靶病灶,用先前开发的基于感兴趣区域的机器学习算法评估GG≥2前列腺癌诊断性能。232例患者中85例为GG≥2癌,算法与PI-RADSv2的AUC分别为77%和80%(p=0.36),算法敏感度86%、特异度65%。算法在多中心多扫描仪数据库表现稳健,可帮助筛选活检患者。

要点

  • 算法与PI-RADSv2诊断GG≥2前列腺癌的AUC分别为77%和80%,差异无统计学意义(p=0.36)。
  • 算法敏感度86%(95%CI 76-93)、特异度65%(95%CI 54-73);PI-RADSv2≥3阈值为95%和38%,≥4阈值为89%和47%。
  • 结合PSA密度、PI-RADSv2和算法评分可避免44-47%活检,漏诊6-9%的GG≥2癌。

核心结论

  • 该算法在多中心多扫描仪的MRI-FIRST数据库中表现稳健,可帮助筛选患者进行活检。
  • 患者层面,算法与PI-RADSv2诊断GG≥2癌的AUC分别为77%(95%CI 70-82)和80%(95%CI 74-85;p=0.36)。

研究设计与样本

  • 回顾性分析MRI-FIRST数据集中的靶向活检病灶,使用先前开发的基于感兴趣区域的机器学习算法进行评估。
  • 排除19例患者后,分析232例在16种不同扫描仪上成像的患者,其中85例活检为GG≥2癌。
  • 前瞻性分配的PI-RADSv2评分与回顾性计算的算法评分进行比较,并回顾性评估十种预定义活检策略。

主要发现

  • 患者层面,算法与PI-RADSv2的AUC分别为77%(95%CI 70-82)和80%(95%CI 74-85;p=0.36)。
  • 算法敏感度86%(95%CI 76-93)、特异度65%(95%CI 54-73)。
  • PI-RADSv2阈值≥3时敏感度95%(95%CI 89-100)、特异度38%(95%CI 26-47);阈值≥4时敏感度89%(95%CI 79-96)、特异度47%(95%CI 35-57)。
  • 使用PI-RADSv2评分触发活检可避免26-34%的活检,但漏诊5-11%的GG≥2癌。
  • 结合PSA密度、PI-RADSv2和算法评分可避免44-47%的活检,漏诊6-9%的GG≥2癌。

关键数值与推荐

  • 算法评分阈值定义为在训练数据库中达到90%敏感度。
  • PI-RADSv2阈值采用评分≥3和≥4。

临床怎么用

  • 原文结论指出该算法可帮助筛选患者进行活检。

局限性

  • 研究为回顾性性质。
  • 缺乏PI-RADS版本2.1评估。

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)。

原文

BACKGROUND AND OBJECTIVE: Prostate multiparametric magnetic resonance imaging (MRI) shows high sensitivity for International Society of Urological Pathology grade group (GG) ≥2 cancers. Many artificial intelligence algorithms have shown promising results in diagnosing clinically significant prostate cancer on MRI. To assess a region-of-interest-based machine-learning algorithm aimed at characterising GG ≥2 prostate cancer on multiparametric MRI. METHODS: The lesions targeted at biopsy in the MRI-FIRST dataset were retrospectively delineated and assessed using a previously developed algorithm. The Prostate Imaging-Reporting and Data System version 2 (PI-RADSv2) score assigned prospectively before biopsy and the algorithm score calculated retrospectively in the regions of interest were compared for diagnosing GG ≥2 cancer, using the areas under the curve (AUCs), and sensitivities and specificities calculated with predefined thresholds (PIRADSv2 scores ≥3 and ≥4; algorithm scores yielding 90% sensitivity in the training database). Ten predefined biopsy strategies were assessed retrospectively. KEY FINDINGS AND LIMITATIONS: After excluding 19 patients, we analysed 232 patients imaged on 16 different scanners; 85 had GG ≥2 cancer at biopsy. At patient level, AUCs of the algorithm and PI-RADSv2 were 77% (95% confidence interval [CI]: 70-82) and 80% (CI: 74-85; p = 0.36), respectively. The algorithm's sensitivity and specificity were 86% (CI: 76-93) and 65% (CI: 54-73), respectively. PI-RADSv2 sensitivities and specificities were 95% (CI: 89-100) and 38% (CI: 26-47), and 89% (CI: 79-96) and 47% (CI: 35-57) for thresholds of ≥3 and ≥4, respectively. Using the PI-RADSv2 score to trigger a biopsy would have avoided 26-34% of biopsies while missing 5-11% of GG ≥2 cancers. Combining prostate-specific antigen density, the PI-RADSv2 and algorithm's scores would have avoided 44-47% of biopsies while missing 6-9% of GG ≥2 cancers. Limitations include the retrospective nature of the study and a lack of PI-RADS version 2.1 assessment. CONCLUSIONS AND CLINICAL IMPLICATIONS: The algorithm provided robust results in the multicentre multiscanner MRI-FIRST database and could help select patients for biopsy. PATIENT SUMMARY: An artificial intelligence-based algorithm aimed at diagnosing aggressive cancers on prostate magnetic resonance imaging showed results similar to expert human assessment in a prospectively acquired multicentre test database.

来源:Eur Urol Oncol,查看原文。版权归原作者所有。

引用

  1. Couchoux T, Jaouen T, Melodelima-Gonindard C, et al. Performance of a Region of Interest-based Algorithm in Diagnosing International Society of Urological Pathology Grade Group ≥2 Prostate Cancer on the MRI-FIRST Database-CAD-FIRST Study. Eur Urol Oncol. 2024. PMID: 38493072. doi:10.1016/j.euo.2024.03.003

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。