文献速递泌尿生殖MR

基于T2WI和DWI的临床-影像组学模型预测PSA与PI-RADS双灰区前列腺癌

Clinical-Radiomics Model Based on T2-Weighted and Diffusion-Weighted Magnetic Resonance Images on Predicting "Double Gray Zone" Prostate Cancer of PSA and PI-RADS.
PubMed 文献 · Acad Radiol · 2026-07-10

本研究回顾性纳入93例PSA 4-10 ng/mL且PI-RADS评分为3分的患者,从T2WI和DWI序列提取影像组学特征,结合临床变量构建预测模型。结果显示联合临床-影像组学模型在验证集中AUC达0.867,优于单独临床模型和单独影像组学模型,校准曲线和决策曲线分析证实模型拟合良好且具有临床净获益。

要点

  • PSA 4-10 ng/mL且PI-RADS 3分的双灰区患者诊断困难,联合模型可辅助决策
  • DWI_T2融合影像组学模型中ExtraTrees算法表现最佳,验证集AUC为0.833
  • 联合临床-影像组学模型验证集AUC达0.867,优于单一模型

核心结论

  • 联合临床-影像组学模型在PSA 4-10 ng/mL且PI-RADS 3分的双灰区人群中具有良好的诊断性能,可作为辅助临床决策的非侵入性工具

研究设计与样本

  • 回顾性研究,共纳入93例PSA 4-10 ng/mL且PI-RADS评分为3分的患者
  • 从T2WI和DWI序列提取影像组学特征,采用mRMR和LASSO回归进行特征筛选
  • 使用6种机器学习算法构建T2WI、DWI、DWI_T2和临床模型,采用逻辑回归构建联合模型

关键影像表现/征象

  • 筛选出10个T2WI特征和13个DWI特征用于构建影像组学模型
  • 临床变量中年龄、上下径和前列腺特异性抗原密度经LASSO筛选为关键变量

诊断标准与关键数值

  • DWI_T2融合模型中ExtraTrees算法最佳,验证集AUC为0.833,95%CI为0.662-1.000,F1分数为0.778
  • 临床模型采用RandomForest构建,验证集AUC为0.767,95%CI为0.561-0.973
  • 联合临床-影像组学模型验证集AUC为0.867,优于单独临床模型和单独影像组学模型
  • 校准曲线、Hosmer-Lemeshow检验和决策曲线分析证实联合模型拟合良好且具有临床净获益

临床应用与阅片要点

  • 对于PSA 4-10 ng/mL且PI-RADS 3分的双灰区患者,可结合T2WI和DWI的影像组学特征及PSAD、年龄等临床变量辅助判断前列腺癌风险

局限性

  • 回顾性研究设计

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: This study aimed to develop a clinical-radiomics model based on T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) to improve the diagnostic performance in the "double gray zone" population characterized by prostate-specific antigen (PSA) levels of 4-10 ng/mL and a Prostate Imaging Reporting and Data System (PI-RADS) score of 3.

MATERIALS AND METHODS: A total of 93 eligible patients (PSA 4-10 ng/mL and PI-RADS score 3) were retrospectively included. Radiomics features were extracted from T2WI and DWI sequences. Feature selection was performed using Maximum Relevance Minimum Redundancy (mRMR) and Least Absolute Shrinkage and Selection Operator (LASSO) regression. Six machine learning algorithms were used to construct the T2WI, DWI, DWI_T2, and clinical models and the logistic regression (LR) algorithm was used to construct a combined model.

RESULTS: 10 T2WI and 13 DWI features were selected to build radiomics models. Among the radiomics models, the DWI_T2 fusion model demonstrated improved performance compared to the other two models, and the ExtraTrees algorithm performed best, with the area under the curve (AUC) value of 0.833 (95% confidence interval (CI): 0.662-1.000) and an F1 score of 0.778 in the validation set. Key clinical variables-age, Upper_and_lower_diameter, and prostate-specific antigen density (PSAD)-were identified via LASSO. Meanwhile, the clinical model built using RandomForest achieved a validation set AUC of 0.767 (95% CI: 0.561-0.973). A combined clinical-radiomics model was further constructed, achieving a validation set AUC of 0.867, outperforming both the standalone clinical model and the standalone radiomics model. Calibration curves, the Hosmer-Lemeshow (HL) test, and decision curve analysis (DCA) confirmed that the combined model demonstrated good fit and clinical net benefit.

CONCLUSION: The combined clinical-radiomic model we constructed demonstrate good diagnostic performance in the "double gray zone" population, holding potential as an effective non-invasive tool to aid clinical decision-making.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang, Li, Yao, et al. Clinical-Radiomics Model Based on T2-Weighted and Diffusion-Weighted Magnetic Resonance Images on Predicting "Double Gray Zone" Prostate Cancer of PSA and PI-RADS. Acad Radiol. 2026. PMID: 42431796. doi:10.1016/j.acra.2026.06.033

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。