文献速递泌尿生殖MR

T2WI影像组学机器学习预测前列腺癌ISUP分级

Machine learning using T2-weighted radiomics for International Society of Urological Pathology (ISUP) classification in prostate cancer.
PubMed 文献 · Clin Radiol · 2026-06-18

基于PROSTATEx数据集112个活检证实的前列腺癌病灶,评估T2加权MRI影像组学模型对ISUP<3与≥3分层的效能。随机森林在留出测试集上AUC为0.84,敏感度85.7%,特异度78.6%。研究支持T2WI影像组学用于前列腺癌侵袭性分层,仍需外部验证。

要点

  • T2WI影像组学随机森林模型可辅助区分ISUP<3与ISUP≥3病灶
  • 一阶特征和灰度级大小区域矩阵特征为主要预测因子
  • 模型经等张回归校准后期望校准误差从0.168降至0.099

核心结论

  • 基于T2加权MRI的影像组学能够对前列腺癌侵袭性进行准确的术后组织学分层

研究设计与样本

  • 回顾性研究,纳入PROSTATEx数据集中112个活检证实的前列腺癌病灶
  • 在放射科医生确定病灶层面的轴位T2WI上放置固定5mm球形ROI
  • 使用PyRadiomics提取107个影像组学特征,以10折交叉验证和患者水平留出测试训练模型
  • 以ISUP<3与ISUP≥3作为二分类目标,ISUP<3共77个,ISUP≥3共35个

关键影像表现/征象

  • 病灶位于外周带占44.6%、前部间质占40.2%、移行带占15.2%
  • 解剖分区与ISUP分级间无显著关联(P=0.639)
  • 一阶特征和灰度级大小区域矩阵特征在SHAP分析中为主要预测因子

诊断标准与关键数值

  • 随机森林在留出测试集AUC为0.84(95%CI:0.63-0.98),平均精确率AP为0.70(95%CI:0.35-0.97)
  • 随机森林在留出测试集敏感度为85.7%,特异度为78.6%,准确率为81.0%,F1分数为0.75
  • 随机森林Brier评分为0.18,经等张回归校准后期望校准误差从0.168降至0.099

临床应用与阅片要点

  • T2WI影像组学可作为区分ISUP<3与ISUP≥3前列腺癌病灶的辅助工具
  • 阅片时可将放射科医生确定的病灶层面轴位T2WI作为ROI勾画基础
  • 临床应用前仍需进行外部验证以确认模型稳定性

局限性

  • 研究为回顾性设计,数据来自PROSTATEx单一数据集
  • 原文结论指出仍需进一步外部验证

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

AIM: To evaluate the performance of an ARARAT radiomics-based artificial intelligence model using T2-weighted magnetic resonance imaging (MRI) for posthistological stratification of prostate cancer aggressiveness.

MATERIAL AND METHODS: A retrospective analysis of 112 biopsy-proven prostate cancer lesions (International Society of Urological Pathology [ISUP] <3 vs ≥ 3) from the PROSTATEx dataset was performed. Fixed 5-mm spherical region of interests (ROIs) were placed on axial T2-weighted MRI at radiologist-defined lesion sites, and 107 radiomic features were extracted using PyRadiomics. Machine-learning models were trained with 10-fold cross-validation and patient-level holdout testing. Model performance and feature importance of ARARAT were assessed using standard classification metrics and SHapley Additive exPlanations (SHAP).

RESULTS: The cohort comprised 112 lesions, including 77 ISUP < 3 (68.8%) and 35 ISUP ≥ 3 (31.2%). ISUP 1 and 2 accounted for 32.1% and 36.6% of cases, respectively, while ISUP 3, 4, and 5 represented 17.9%, 7.1%, and 6.3%, respectively. Lesions were located in the peripheral zone (44.6%), anterior stroma (40.2%), and transition zone (15.2%), with no association between anatomical zone and ISUP category (P = 0.639). The random forest achieved the highest performance on the holdout set, with an area under the curve (AUC) of 0.84 (95% confidence interval [CI]: 0.63-0.98), average precision (AP) 0.70 (95% CI: 0.35-0.97), sensitivity of 85.7%, specificity of 78.6%, accuracy of 81.0%, and an F1-score of 0.75. The Brier score was 0.18, and calibration improved after isotonic regression, reducing the expected calibration error from 0.168 to 0.099. First-order and grey-level size zone matrix features were the dominant predictors.

CONCLUSTION: T2-weighted MRI-based radiomics enables accurate posthistological stratification of prostate cancer aggressiveness, supporting further external validation.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Ohannesian, Toledo, Santos, et al. Machine learning using T2-weighted radiomics for International Society of Urological Pathology (ISUP) classification in prostate cancer. Clin Radiol. 2026. PMID: 42442123. doi:10.1016/j.crad.2026.107417

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。