多模态机器学习方法提高临床显著前列腺癌检出:一项大规模多中心研究
该研究基于12个医学中心的回顾性数据开发了整合双参数MRI影像组学、年龄、PSA、PI-RADS评分及前列腺带区病灶位置的多模态模型,并在回顾性和前瞻性验证集中与PI-RADS评分比较。模型在回顾性验证集AUC 0.88 vs 0.80、前瞻性验证集AUC 0.91 vs 0.85,特异性亦优于PI-RADS,并使活检数量减少22.7%。
要点
- 多模态模型在回顾性验证集AUC 0.88 vs PI-RADS 0.80,前瞻性验证集AUC 0.91 vs 0.85
- 模型特异性回顾性71% vs PI-RADS 58%,前瞻性77% vs 66%,均优于PI-RADS
- 应用该模型较PI-RADS减少22.7%的活检
核心结论
- 多模态模型提供了时间上可泛化的临床显著前列腺癌预测因子,性能优于PI-RADS评分。
研究设计与样本
- 回顾性数据(2022年3月31日前采集)来自12个医学中心,用于模型开发,纳入7157例男性患者(平均年龄64.78岁,3342例[46.7%]患临床显著前列腺癌)。
诊断标准与关键数值
- 回顾性验证集:多模态模型AUC 0.88 vs PI-RADS 0.80(P = .005),特异性71% vs 58%(P = .002)
- 前瞻性验证集:多模态模型AUC 0.91 vs PI-RADS 0.85(P < .001),特异性77% vs 66%(P < .001)
- 以PI-RADS >3为阈值比较特异性,多模态模型较PI-RADS减少22.7%的活检
- 敏感性分析显示单独使用特定序列(T2加权、表观扩散系数、扩散加权成像)或特定扫描仪厂商(GE、Philips、Siemens)会导致模型性能下降
- 公平性分析显示模型在不同类别间具有泛化性,但PI-RADS较高时敏感性增加,且在一个医学中心性能下降
局限性
- 公平性分析显示在一个医学中心模型性能下降。
- 敏感性分析显示单独使用特定序列或特定扫描仪厂商时模型性能下降,需多序列和多厂商数据以实现泛化。
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
Purpose To develop and prospectively validate a clinical and radiologic model to predict clinically significant prostate cancer (csPCa) using biparametric MRI (bpMRI). Materials and Methods Retrospective data (acquired before March 31, 2022) from 12 medical centers were collected. Radiomic features were extracted from the whole prostate gland using segmentations generated by an automatic deep learning algorithm. A model incorporating bpMRI radiomics, age, prostate-specific antigens, the Prostate Imaging Reporting and Data System (PI-RADS), and the prostate zone lesion location was trained. A retrospective validation set and prospective data (acquired after March 31, 2022) were used to compare PI-RADS scoring (area under the receiver operating characteristic curve [AUC] and specificity at PI-RADS >3). Sensitivity analyses for sequence (T2-weighted, apparent diffusion coefficient, diffusion-weighted imaging) and scanner vendor (GE, Philips, Siemens) were performed, in addition to fairness analyses for relevant categories. Results The retrospective dataset for model development included 7157 male patients (mean age, 64.78 years; 3342 [46.7%] with csPCa), and the prospective dataset for model validation included 1629 patients (mean age, 66.19 years; 592 [36.3%] with csPCa). The multimodal model outperformed PI-RADS in the retrospective (AUC, 0.88 vs 0.80, P = .005; specificity of 71% vs 58%, P = .002) and prospective validation sets (AUC, 0.91 vs 0.85, P < .001; specificity of 77% vs 66%, P < .001), leading to 22.7% fewer biopsies compared with PI-RADS. Sensitivity analyses showed the importance of multiple sequences and vendors in achieving model generalization, as using specific sequences or vendors alone led to worse performance. Fairness analysis showed generalizability across different categories but highlighted increased sensitivity with higher PI-RADS and reduced performance in one medical center. Conclusion A multimodal model provided a temporally generalizable predictor of csPCa that outperformed PI-RADS. Keywords: Algorithm Development, Machine Learning, Model Validation, Model Training, Genital/Reproductive, Neoplasms-Primary, Oncology, Comparative Studies, Technology Assessment Supplemental material is available for this article. © RSNA, 2025.
引用
- Rodrigues AC, de Almeida JG, Rodrigues N, et al. Improving Clinically Significant Prostate Cancer Detection with a Multimodal Machine Learning Approach: A Large-Scale Multicenter Study. Radiol Imaging Cancer. 2025. PMID: 40815224. doi:10.1148/rycan.240507
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。