AI 前列腺体积测量与椭球公式在 PSAD 风险分层中的验证比较
本回顾性单中心研究纳入 171 例接受 3T 前列腺 MRI 及融合活检的患者,比较 AI 体积测量与椭球公式计算的 PSA 密度对临床有意义前列腺癌的诊断效能。两者与 ISUP 分级均显著正相关,AI 法 AUC 为 0.79,椭球法各阅片者 AUC 为 0.76~0.78,仅一名阅片者 AUC 显著低于 AI 法。
要点
- AI 体积测量可作为椭球公式的替代方法,PSAD 对 csPCa 诊断效能非劣效。
- 预定义 PSAD 阈值(0.10~0.20)下两种方法的敏感度和特异度相当。
- AI 自动体积测量可能减少不同阅片者之间的变异。
核心结论
- AI 前列腺体积测量是椭球公式计算体积的有效替代方案,对临床有意义前列腺癌检测的诊断效能非劣效。
研究设计与样本
- IRB 批准的回顾性单中心研究,纳入 171 例接受 TRUS 引导经会阴融合活检的患者,中位年龄 68 岁。
- 采用 3T 前列腺 MRI 数据集,由三名阅片者计算椭球公式体积,使用商用 AI 工具获取 AI 体积。
诊断标准与关键数值
- 针对 csPCa 检测,AI 体积法 PSAD 的 AUC 为 0.79,椭球公式法 PSAD 各阅片者 AUC 范围为 0.76~0.78。
- 仅一名阅片者的椭球法 AUC 显著低于 AI 体积法 PSAD(p=0.002)。
- 在预定义 PSAD 阈值 0.10~0.20 范围内,两种方法的敏感度和特异度相当。
- AI 体积法与椭球公式法计算的 PSAD 均与 ISUP 分级呈显著正相关(所有 p<0.001)。
临床应用与阅片要点
- AI 自动前列腺体积测量可用于 PSAD 计算,替代手工椭球公式测算,减少阅片者间变异。
- 在 PSAD 阈值 0.10~0.20 的活检决策区间内,AI 法与椭球法可互换使用。
局限性
- 回顾性单中心设计。
- 仅纳入接受 TRUS 引导经会阴融合活检的患者,存在选择偏倚可能。
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: State-of-the-art AI tools offer automated prostate MR volumetry, potentially improving accuracy and efficiency compared to approximation using the ellipsoid formula (A x P x L x 0.52). However, data on the clinical validity of AI-derived volumetry (AI-V) for PSA density (PSAD)-based risk stratification remain limited. We therefore investigated the correlation of AI-V- and ellipsoid formula volume (EL-V)-calculated PSAD with ISUP group and their diagnostic performance for the detection of clinically significant prostate cancer (csPCa).
MATERIALS AND METHODS: In this IRB-approved retrospective single-centre study, 3-T prostate MRI datasets of 171 patients (median age 68 years) undergoing TRUS-guided transperineal fusion biopsy were analysed. EL-V was calculated by three readers, while AI-V was obtained using a commercially available AI tool. Associations between PSAD and ISUP group were assessed using Spearman's rho and linear regression, and diagnostic performance using receiver operating characteristic (ROC) analysis and predefined PSAD thresholds.
RESULTS: Both AI-derived and EL-V-calculated PSAD showed significant positive correlations with ISUP group (all p<0.001). For csPCa detection, AI-V-derived and EL-V-calculated PSAD demonstrated overall comparable diagnostic performance, with AI-V-derived PSAD achieving an AUC of 0.79 and EL-V-calculated PSAD showing AUC values ranging from 0.76 to 0.78 across readers. Only one reader demonstrated a significantly lower AUC compared with AI-V-derived PSAD (p=0.002). At predefined PSAD thresholds (0.10-0.20), sensitivity and specificity were comparable between both methods.
CONCLUSION: AI-based prostate volumetry represents a valid alternative to ellipsoid formula-calculated volumetry with non-inferior diagnostic performance for csPCa detection.
引用
- Bayraktaroglu, Heimer, Kuhnle, et al. Validation of AI-derived whole prostate volumetry versus ellipsoid formula for PSA density-based risk stratification. Eur J Radiol. 2026. PMID: 42447771. doi:10.1016/j.ejrad.2026.113080
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。