文献速递泌尿生殖腹部MR

利用人工智能对双参数MRI和PSA筛查无临床显著前列腺癌的患者进行分诊

Using AI to triage patients without clinically significant prostate cancer using biparametric MRI and PSA.
PubMed 文献 · Abdom Radiol (NY) · 2025-05-30

本回顾性研究收集2895例MRI(内部1630例、公开1265例),在465例测试集上模拟分诊流程,比较U-Net分割模型(联合或不联合临床参数)与多种风险计算器及PSA密度。U-Net联合临床参数分诊使放射科医生工作量减少12.5%,敏感度从93%降至90%(p=0.023),特异度从39%升至47%(p<0.001),且阳性预测值提高而阴性预测值保持等效。作者结论认为机器学习分诊可减少工作量,但需进一步前瞻性验证。

要点

  • U-Net联合临床参数分诊使放射科工作量减少12.5%,敏感度降3%、特异度升8%。
  • 两种U-Net分诊策略均提高阳性预测值,阴性预测值在所有场景保持等效。
  • 临床信息辅助U-Net分诊正确排除了20例(13.4%)放射科医生的假阳性。

核心结论

  • 基于机器学习的 prostate MRI 分诊可使放射科医生工作量减少12.5%,敏感度降低3%、特异度提高8%,优于基于非影像风险模型的分诊,但需进一步前瞻性验证。

研究设计与样本

  • 回顾性研究,收集2895例MRI(内部1630例、公开1265例),在465例测试集上模拟分诊工作流并与放射科医生解读所有检查进行比较;参考标准为组织病理学或阴性随访。

诊断标准与关键数值

  • U-Net联合临床参数分诊 vs 放射科医生解读全部检查:敏感度93% vs 90%(p=0.023),特异度39% vs 47%(p<0.001)。

临床应用与阅片要点

  • 作者结论认为机器学习分诊可减少放射科医生工作量,但需进一步前瞻性验证。

局限性

  • 原文结论指出需进一步前瞻性验证。

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 train and evaluate the performance of a machine learning triaging tool that identifies MRI negative for clinically significant prostate cancer and to compare this against non-MRI models.

METHODS: 2895 MRIs were collected from two sources (1630 internal, 1265 public) in this retrospective study. Risk models compared were: Prostate Cancer Prevention Trial Risk Calculator 2.0, Prostate Biopsy Collaborative Group Calculator, PSA density, U-Net segmentation, and U-Net combined with clinical parameters. The reference standard was histopathology or negative follow-up. Performance metrics were calculated by simulating a triaging workflow compared to radiologist interpreting all exams on a test set of 465 patients. Sensitivity and specificity differences were assessed using the McNemar test. Differences in PPV and NPV were assessed using the Leisenring, Alonzo and Pepe generalized score statistic. Equivalence test p-values were adjusted within each measure using Benjamini-Hochberg correction.

RESULTS: Triaging using U-Net with clinical parameters reduced radiologist workload by 12.5% with sensitivity decrease from 93 to 90% (p = 0.023) and specificity increase from 39 to 47% (p < 0.001). This simulated workload reduction was greater than triaging with risk calculators (3.2% and 1.3%, p < 0.001), and comparable to PSA density (8.4%, p = 0.071) and U-Net alone (11.6%, p = 0.762). Both U-Net triaging strategies increased PPV (+ 2.8% p = 0.005 clinical, + 2.2% p = 0.020 nonclinical), unlike non-U-Net strategies (p > 0.05). NPV remained equivalent for all scenarios (p > 0.05). Clinically-informed U-Net triaging correctly ruled out 20 (13.4%) radiologist false positives (12 PI-RADS = 3, 8 PI-RADS = 4). Of the eight (3.6%) false negatives, two were misclassified by the radiologist. No misclassified case was interpreted as PI-RADS 5.

CONCLUSIONS: Prostate MRI triaging using machine learning could reduce radiologist workload by 12.5% with a 3% sensitivity decrease and 8% specificity increase, outperforming triaging using non-imaging-based risk models. Further prospective validation is required.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Grabke EP, Heming CAM, Hadari A, et al. Using AI to triage patients without clinically significant prostate cancer using biparametric MRI and PSA. Abdom Radiol (NY). 2025. PMID: 40445307. doi:10.1007/s00261-025-05019-2

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。