文献速递泌尿生殖腹部MR

基于ADC的影像组学工具检测PI-RADS 3病变临床显著性前列腺癌的多中心研究

An Apparent Diffusion Coefficient-Based Radiomics Tool for Clinically Significant Prostate Cancer Detection in PI-RADS 3 Lesions: A Multicenter Study.
PubMed 文献 · Acad Radiol · 2026-08-28

本研究回顾性纳入443例患者开发基于ADC图的影像组学模型,用于检测PI-RADS 3病变中的临床显著性前列腺癌,并在前瞻性队列(206例)和五个分中心回顾性队列(197例)中验证。所有病灶均经MRI-TRUS靶向活检确认,两名放射科医师共识勾画ROI。模型训练集AUC为0.939,外部验证集AUC为0.782,DCA显示在0.3-0.6阈值范围内提供净获益。

要点

  • PI-RADS 3病变中csPCa比例为24.6%,影像组学模型训练集AUC达0.939。
  • 模型外部验证集AUC为0.782,表现为中等效能,应用时需注意阈值范围。
  • ADC影像组学特征可为PI-RADS 3病变的活检决策提供辅助依据。

核心结论

  • 基于ADC的影像组学模型在训练集中能有效检测PI-RADS 3病变中的csPCa,在外部验证集中表现出中等效能。

研究设计与样本

  • 研究类型为回顾性模型开发加外部验证,训练集来自医院1的443例患者(2017年5月至2023年7月)。
  • 验证集包括同一机构前瞻性队列206例及五个分中心回顾性队列197例(2023年8月至2025年2月),共846例患者。
  • 参考标准为MRI-TRUS靶向活检病理结果,ROI由两名放射科医师共识勾画并复核。

关键影像表现/征象

  • 影像组学特征提取自ADC图,针对PI-RADS 3病灶区域进行勾画与分析。
  • 训练集中846例患者平均年龄66.2±7.5岁,总体csPCa阳性率为24.6%。

诊断标准与关键数值

  • 训练集AUC为0.939(95% CI:0.914-0.963),验证集AUC为0.782(95% CI:0.731-0.832)。
  • PR曲线下面积训练集为0.883,验证集为0.480。
  • 模型校准Brier评分训练集为0.126,验证集为0.152。
  • DCA显示验证集在阈值0.3-0.6范围内模型对判定csPCa提供净获益。

临床应用与阅片要点

  • 该模型可辅助对PI-RADS 3病灶进行csPCa风险分层,减少不必要的活检。
  • 临床应用时应注意模型在外部验证集中PR曲线下面积较低,阳性预测价值有限。
  • 模型净获益阈值区间为0.3-0.6,超出该范围时临床决策需谨慎。

局限性

  • 训练集为单中心回顾性数据,存在选择偏倚和过拟合风险。
  • 验证集PR曲线下面积仅0.480,提示在阳性样本稀少时精确率受限。
  • ROI勾画依赖两名医师共识,未评估观察者间变异性。

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

RATIONALE AND OBJECTIVES: The clinical management of Prostate Imaging Reporting and Data System (PI-RADS) 3 lesions remains controversial due to their equivocal likelihood of clinically significant prostate cancer (csPCa). This study aimed to develop and validate a prediction model for csPCa detection to assist in clinical decision-making for these indeterminate lesions.

MATERIALS AND METHODS: We retrospectively collected 443 patients from Hospital 1 (May 2017 to July 2023) for model development. The model was subsequently validated externally using a prospective cohort (n = 206) from the same institution and a retrospective cohort (n = 197) from five subcenters (August 2023 to February 2025). All lesions were confirmed by magnetic resonance imaging-transrectal ultrasound targeted biopsy. Regions of interest were delineated and reviewed by two radiologists in consensus. Model performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, specificity, and additional metrics derived from ROC curves, precision-recall (PR) curves, calibration plots, and decision-curve analysis (DCA) in both training and validation sets.

RESULTS: Among 846 patients (mean age 66.2 ± 7.5 years), 24.6% had csPCa. The radiomics model achieved an AUC of 0.939 (95% confidence interval [CI]: 0.914-0.963) in the training set and 0.782 (95% CI: 0.731-0.832) in the validation set. The area under the PR curve was 0.883 (training set) and 0.480 (validation set). The Brier score for model calibration was 0.126 (training set) and 0.152 (validation set). Per DCA, the model provided a net benefit for determining csPCa in the validation set at thresholds of 0.3-0.6.

CONCLUSION: The apparent diffusion coefficient-based radiomics model effectively detected csPCa in PI-RADS 3 lesions in the training set and demonstrated moderate performance in the external validation set.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Gao, Wang, Wang, et al. An Apparent Diffusion Coefficient-Based Radiomics Tool for Clinically Significant Prostate Cancer Detection in PI-RADS 3 Lesions: A Multicenter Study. Acad Radiol. 2026. PMID: 42660733. doi:10.1016/j.acra.2026.07.072

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。