文献速递泌尿生殖腹部MR

利用表征学习处理双参数前列腺MRI以区分PI-RADS 3并改进活检决策策略

Leveraging Representation Learning for Bi-parametric Prostate MRI to Disambiguate PI-RADS 3 and Improve Biopsy Decision Strategies.
PubMed 文献 · Invest Radiol · 2026-02-01

本研究纳入28263次MRI检查和6352次后续活检,训练PI-RADS引导的表征学习深度学习模型,用于从双参数前列腺MRI检测临床显著前列腺癌(Gleason评分≥7)。在仅PI-RADS 3测试队列中,基于表征学习的决策模型将良性活检避免率从临床模型的26%提高到41%,并将活检阳性率从PI-RADS≥3策略的0.40提高到0.50;在全部PI-RADS队列中,其避免额外良性活检27%,与放射科医生33%相比,敏感度相当(93% vs 92%),NPV更高(0.87 vs 0.77),活检阳性率更高(0.75 vs 0.64)。

要点

  • 在仅PI-RADS 3队列中,RL决策模型避免41%(62/150)良性活检,优于临床模型的26%(P<0.001)。
  • 在全部PI-RADS队列中,RL模型避免27%(138/231)额外良性活检,放射科医生为33%(P<0.001)。
  • RL模型在全部PI-RADS队列的敏感度与放射科医生相当(93% vs 92%),NPV更高(0.87 vs 0.77)。

核心结论

  • PI-RADS引导的深度学习表征学习模型可从双参数前列腺MRI学习总结表征,为区分中危PI-RADS 3评估提供额外信息;基于该表征学习的活检决策模型在全部PI-RADS队列中避免良性活检方面优于放射科医生,同时保持对临床显著前列腺癌的敏感度相当。

研究设计与样本

  • 研究纳入2015年至2023年本机构21个影像地点、34名阅片者的28263次MRI检查和21938名男性的影像与报告,其中6352次后续活检;使用放射科医生风险判断明确的检查(PI-RADS 1和2为无csPCa,PI-RADS 4和5为有csPCa,n=21465)训练表征学习模型,再训练活检决策模型检测csPCa(Gleason评分≥7),并与放射科医生及基于年龄、前列腺体积、PSA和PSA密度的临床模型比较;测试队列为仅PI-RADS 3(n=253,csPCa=103)和全部PI-RADS(n=531,csPCa=300)的治疗初治病例。

诊断标准与关键数值

  • 检测csPCa(Gleason评分≥7)的AUC:仅PI-RADS 3队列中RL模型为0.73(0.66,0.79),全部PI-RADS队列中为0.88(0.85,0.91);放射科医生(不确定)AUC=0.79(0.75,0.83);临床模型AUC分别为0.69(0.62,0.75)和0.78(0.74,0.82)。仅PI-RADS 3队列中RL决策模型避免41%(62/150)良性活检,临床模型为26%(P<0.001);活检阳性率RL模型0.50 vs PI-RADS≥3策略0.40。全部PI-RADS队列中RL模型避免27%(138/231)额外良性活检,放射科医生为33%(P<0.001);敏感度93% vs 92%,NPV 0.87 vs 0.77,活检阳性率0.75 vs 0.64。临床与RL决策模型联合在仅PI-RADS 3和全部PI-RADS队列分别避免46%和62%良性活检,NPV分别为0.82和0.88,活检阳性率分别为0.52和0.76。

临床应用与阅片要点

  • 本机构的标准诊疗是对仅PI-RADS 3队列全部进行活检;作者认为此类AI模型可方便地整合到临床实践中,辅助放射科医生的判读,并改善任何不确定决策的活检阳性率。

局限性

  • 原文未报告局限性。

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: Despite its high negative predictive value (NPV) for clinically significant prostate cancer (csPCa), MRI suffers from a substantial number of false positives, especially for intermediate-risk cases. In this work, we determine whether a deep learning model trained with PI-RADS-guided representation learning can disambiguate the PI-RADS 3 classification, detect csPCa from bi-parametric prostate MR images, and avoid unnecessary benign biopsies.

MATERIALS AND METHODS: This study included 28,263 MR examinations and radiology reports from 21,938 men imaged for known or suspected prostate cancer between 2015 and 2023 at our institution (21 imaging locations with 34 readers), with 6352 subsequent biopsies. We trained a deep learning model, a representation learner (RL), to learn how radiologists interpret conventionally acquired T2-weighted and diffusion-weighted MR images, using exams in which the radiologists are confident in their risk assessments (PI-RADS 1 and 2 for the absence of csPCa vs. PI-RADS 4 and 5 for the presence of csPCa, n=21,465). We then trained biopsy-decision models to detect csPCa (Gleason score ≥7) using these learned image representations, and compared them to the performance of radiologists, and of models trained on other clinical variables (age, prostate volume, PSA, and PSA density) for treatment-naïve test cohorts consisting of only PI-RADS 3 (n=253, csPCa=103) and all PI-RADS (n=531, csPCa=300) cases.

RESULTS: On the 2 test cohorts (PI-RADS-3-only, all-PI-RADS), RL-based biopsy-decision models consistently yielded higher AUCs in detecting csPCa (AUC=0.73 [0.66, 0.79], 0.88 [0.85, 0.91]) compared with radiologists (equivocal, AUC=0.79 [0.75, 0.83]) and the clinical model (AUCs=0.69 [0.62, 0.75], 0.78 [0.74, 0.82]). In the PIRADS-3-only cohort, all of whom would be biopsied using our institution's standard of care, the RL decision model avoided 41% (62/150) of benign biopsies compared with the clinical model (26%, P <0.001), and improved biopsy yield by 10% compared with the PI-RADS ≥3 decision strategy (0.50 vs. 0.40). Furthermore, on the all-PI-RADS cohort, RL decision model avoided 27% of additional benign biopsies (138/231) compared to radiologists (33%, P <0.001) with comparable sensitivity (93% vs. 92%), higher NPV (0.87 vs. 0.77), and biopsy yield (0.75 vs. 0.64). The combination of clinical and RL decision models further avoided benign biopsies (46% in PI-RADS-3-only and 62% in all-PI-RADS) while improving NPV (0.82, 0.88) and biopsy yields (0.52, 0.76) across the 2 test cohorts.

CONCLUSIONS: Our PI-RADS-guided deep learning RL model learns summary representations from bi-parametric prostate MR images that can provide additional information to disambiguate intermediate-risk PI-RADS 3 assessments. The resulting RL-based biopsy decision models also outperformed radiologists in avoiding benign biopsies while maintaining comparable sensitivity to csPCa for the all-PI-RADS cohort. Such AI models can easily be integrated into clinical practice to supplement radiologists' reads in general and improve biopsy yield for any equivocal decisions.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Umapathy L, Johnson PM, Dutt T, et al. Leveraging Representation Learning for Bi-parametric Prostate MRI to Disambiguate PI-RADS 3 and Improve Biopsy Decision Strategies. Invest Radiol. 2026. PMID: 40586610. doi:10.1097/RLI.0000000000001218

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。