深度学习检测MRI临床显著性前列腺癌的系统综述与荟萃分析
合并敏感度为0.91，特异度为0.55，LR-为0.16。直接比较研究中，AI辅助/DL+PI-RADS特异度最高，单独PI-RADS特异度最低。
要点
- DL单独应用敏感度高、LR-低，适合辅助排除，但特异度不足以单独确诊。
- AI辅助/DL联合PI-RADS较单独PI-RADS可降低假阳性，减少不必要的活检。
- 合并特异度异质性大，诊断效能的外推性有限，需结合本机构数据谨慎解读。
核心结论
- DL用于前列腺MRI检测临床显著性前列腺癌具有高敏感度和低LR-，支持排除或辅助诊断角色。
- 中等且不稳定的特异度限制了DL单独用于确诊，AI辅助/DL+PI-RADS联合流程可能减少假阳性。
研究设计与样本
- 遵循PRISMA-DTA的系统综述与HSROC荟萃分析，检索MEDLINE、Embase和Web of Science，时限2010年至2025年6月。
- 使用QUADAS-2评估偏倚风险，采用双变量随机效应和HSROC模型合并敏感度与特异度。
诊断标准与关键数值
- 合并敏感度为0.91（95% CI, 0.89-0.93），特异度为0.55（95% CI, 0.46-0.64）。
- 阳性似然比LR+为2.04，阴性似然比LR-为0.16。
- 九项直接比较研究中，三组敏感度相近，AI辅助/DL+PI-RADS特异度最高，单独PI-RADS特异度最低。
临床应用与阅片要点
- 在报告中可将DL结果定位为辅助排除工具，高敏感度和低LR-有助于筛查低风险患者。
- 不推荐将DL单独作为确诊依据，其特异度不足以排除假阳性。
- 优先考虑AI辅助与PI-RADS联合的报告流程，可能减少不必要的穿刺。
- 解释DL输出时应警惕合并特异度异质性大，单中心效能不能直接外推。
局限性
- 合并特异度变异大，HSROC预测区域宽，提示合并特异度的可迁移性有限。
- 原文指出需要前瞻性验证、校准、可解释性评估和患者层面安全性研究。
- Deeks检验未发现显著发表偏倚（p = 0.393），但小样本研究效应仍需关注。
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: To estimate patient-level diagnostic accuracy of deep learning (DL) for MRI-based detection of clinically significant prostate cancer (csPCa), assess heterogeneity and clinical-readiness signals, and compare DL-alone, PI-RADS-alone, and AI-assisted/DL + PI-RADS interpretation where direct comparator data were available.
METHODS: Following PRISMA-DTA, MEDLINE, Embase, and Web of Science were searched from 2010 to June 2025 for studies reporting patient-level 2 × 2 diagnostic accuracy data for DL applied to prostate MRI. Risk of bias was assessed using QUADAS-2. Pooled sensitivity and specificity were estimated using bivariate random-effects and HSROC models, with prespecified subgroup, meta-regression, and sensitivity analyses. Deeks' funnel plot asymmetry test assessed publication bias and small-study effects. A secondary direct three-way comparative analysis was performed in studies reporting DL-alone, PI-RADS-alone, and AI-assisted/DL + PI-RADS data within the same or closely matched cohorts. AI-specific reporting and clinical-readiness signals were mapped using items adapted from STARD-AI, CLAIM, and DECIDE-AI.
RESULTS: Thirty-six studies including 9,411 patients were included. Pooled sensitivity was 0.91 (95% CI, 0.89-0.93), specificity was 0.55 (95% CI, 0.46-0.64), LR + was 2.04, and LR - was 0.16. Sensitivity was relatively consistent, whereas specificity varied widely, with a broad HSROC prediction region indicating limited transportability of pooled specificity. Deeks' test showed no significant funnel plot asymmetry (p = 0.393). Sensitivity analyses excluding MRI + clinical-variable hybrid models and small cohorts produced similar estimates. In nine directly comparative studies, sensitivity was similar across groups, while specificity was highest for AI-assisted/DL + PI-RADS and lowest for PI-RADS-alone.
CONCLUSION: DL for prostate MRI shows high sensitivity and low LR-, supporting a rule-out or assistive role. However, moderate and variable specificity limits stand-alone rule-in use. Combined AI/DL + PI-RADS workflows may reduce false positives, but prospective validation, calibration, interpretability evaluation, and patient-level safety studies are needed.
引用
- Gete, Ayele. Deep learning for clinically significant prostate cancer detection on MRI: a systematic review, HSROC meta-analysis, and direct comparison with PI-RADS-based interpretation. Abdom Radiol (NY). 2026. PMID: 42240646. doi:10.1007/s00261-026-05594-y
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。