文献速递乳腺MR

针对增强与非增强乳腺MRI分诊的自适应基础模型

Adapted foundation models for breast MRI triaging in contrast-enhanced and non-contrast-enhanced protocols.
PubMed 文献 · Eur Radiol · 2026-08-13

该回顾性研究纳入内部1847例及外部924例单侧乳腺MRI检查,评估基于DINOv2的医学切片Transformer对BI-RADS≥4病例的分诊效能。在97.5%敏感度下,T1sub+T2w特异度为19%±7%,DWI1500+T2w为17%±11%,外部验证T1sub方案AUC为0.77。

要点

  • T1sub+T2w在97.5%敏感度下特异度最高,为19%±7%
  • 95%及97.5%敏感度下漏诊病灶以小于10 mm的非肿块强化为主
  • 非增强DWI1500+T2w方案也具备分诊潜力,特异度为17%±11%

核心结论

  • 在97.5%敏感度下,MST框架可排除无BI-RADS≥4的检查,增强MRI特异度为19%,非增强MRI为17%
  • 基于基础模型的AI方法有潜力支持缩写乳腺MRI方案的高效分诊

研究设计与样本

  • 机构审查委员会批准的回顾性研究,内部数据集1847例单侧乳腺MRI检查,其中377例BI-RADS≥4
  • 外部数据集来自Duke大学,共924例检查,总研究人群为1448例女性患者,平均年龄49±12岁
  • 测试四种缩写方案:T1加权早期减影(T1sub)、b=1500 s/mm²的DWI(DWI1500)、DWI1500+T2加权(T2w)、T1sub+T2w
  • 采用五折交叉验证和受试者工作特征曲线下面积(AUC)评估性能,AUC差异用DeLong检验比较

关键影像表现/征象

  • 在95%和97.5%敏感度下,漏诊病灶主要为小于10 mm的病变,且多为非肿块强化
  • 外部数据集中,T1sub方案的注意力图88%被评为良好或中等

诊断标准与关键数值

  • T1sub+T2w的AUC为0.77±0.04,DWI1500+T2w的AUC为0.74±0.04,各方案间无显著差异
  • 在97.5%敏感度下,T1sub+T2w的特异度为19%±7%,DWI1500+T2w为17%±11%
  • 外部验证T1sub方案的AUC为0.77
  • 性能在90%、95%和97.5%敏感度水平下进行评估

临床应用与阅片要点

  • 该分诊方法可识别不太可能含可疑发现(BI-RADS≥4)的检查,从而优先处理高风险病例
  • 非增强方案同样具备分诊能力,可用于不适合对比剂的患者群体
  • 报告时需注意小于10 mm的非肿块强化是AI容易漏诊的类型

局限性

  • 回顾性研究设计
  • 内部数据集为单中心数据

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 evaluate a DINOv2-based medical slice transformer (MST) for triaging abbreviated breast MRI by ruling out examinations with suspicious findings that are immediately actionable (Breast Imaging Reporting and Data System [BI-RADS] ≥ 4) across contrast-enhanced and non-contrast-enhanced protocols.

MATERIALS AND METHODS: This institutional review board-approved retrospective study included 1847 single-breast MRI examinations (377 BI-RADS ≥ 4) from an in-house dataset and 924 from an external dataset (Duke). Four abbreviated protocols were tested: T1-weighted early subtraction (T1sub), diffusion-weighted imaging with b = 1500 s/mm² (DWI1500), DWI1500 + T2-weighted (T2w), and T1sub + T2w. Performance was assessed at 90%, 95%, and 97.5% sensitivity using five-fold cross-validation and area under the receiver operating characteristic curve (AUC). AUC differences were compared with the DeLong test. False negatives were characterized, and attention maps were rated in the external dataset.

RESULTS: A total of 1448 female patients (mean age, 49 ± 12 years) were included. T1sub + T2w achieved an AUC of 0.77 ± 0.04; DWI1500 + T2w, 0.74 ± 0.04, with no significant differences across protocols. At 97.5% sensitivity, T1sub + T2w had the highest specificity (19% ± 7%), followed by DWI1500 + T2w (17% ± 11%). At 95% and 97.5% sensitivity, missed lesions were predominantly < 10 mm, mainly non-mass enhancements. External validation of the T1sub protocol yielded an AUC of 0.77, with 88% of attention maps rated good or moderate.

CONCLUSION: At 97.5% sensitivity, the MST framework triaged cases without BI-RADS ≥ 4, achieving 19% specificity for contrast-enhanced and 17% for non-contrast-enhanced MRI. These findings highlight the potential of foundation-model-based AI to support efficient triaging of abbreviated breast MRI protocols.

KEY POINTS: Question Can an adapted DINOv2-based MST accurately stratify abbreviated breast MRI examinations to support triaging across contrast-enhanced and non-contrast-enhanced imaging protocols? Findings The model achieved 19% specificity for contrast-enhanced and 17% for non-contrast-enhanced MRI at 97.5% sensitivity; external validation of the T1sub protocol yielded an AUC of 0.77. Clinical relevance A foundation-model-based triage approach may reduce radiologist workload in breast MRI screening by identifying examinations unlikely to contain suspicious findings, including on non-contrast-enhanced protocols, thereby enabling prioritization of higher-risk studies.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Nguyen, Kapsner, Hepp, et al. Adapted foundation models for breast MRI triaging in contrast-enhanced and non-contrast-enhanced protocols. Eur Radiol. 2026. PMID: 42593493. doi:10.1007/s00330-026-12782-3

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。