用AI模型快速筛查乳腺MRI，97.5%敏感度下准确排除严重病灶
Adapted Foundation Models for Breast MRI Triaging in Contrast-Enhanced and Non-Contrast Enhanced Protocols
- 基于DINOv2的医学切片变压器模型，融合不同MRI序列进行病灶筛查
- 在97.5%敏感度下，对比增强组特异性达19%，非对比增强组17%
- 适用于临床前筛，尤其适合处理小病灶和非肿块强化病变
背景：磁共振成像（MRI）对乳腺癌检测具有高敏感性，但阅片耗时。人工智能可辅助初步筛查。目的：评估基于DINOv2的医学切片变压器（MST）在对比增强与非对比增强简略乳腺MRI中排除显著病灶（BI-RADS ≥4）的能力。方法：本机构审查委员会批准的回顾性研究纳入1,847例单侧乳腺MRI检查（377例BI-RADS ≥4），并使用外部验证数据集（杜克大学）的924例。测试了四种简略协议：早期减影T1加权（T1sub）、b=1500 s/mm²扩散加权成像（DWI1500）、DWI1500+T2加权（T2w）以及T1sub+T2w。通过五折交叉验证，在90%、95%和97.5%敏感度下评估性能，并采用受试者工作特征曲线下面积（AUC）分析，差异用DeLong检验比较。对假阴性结果进行分析，并对外部数据集中的真阳性注意力图进行评级。结果：共纳入1,448名女性患者（平均年龄49±12岁）。T1sub+T2w的AUC为0.77±0.04；DWI1500+T2w为0.74±0.04（p=0.15）。在97.5%敏感度下，T1sub+T2w特异性最高（19%±7%），其次为DWI1500+T2w（17%±11%）。在95%和97.5%阈值下，漏诊病灶平均直径均小于10 mm，主要为非肿块样强化。外部验证得AUC为0.77，88%的注意力图被评为良好或中等。结论：在97.5%敏感度下，MST框架能有效排除无BI-RADS≥4的病例，对比增强和非对比增强组特异性分别达19%和17%。临床应用前需进一步研究。
原文摘要 · Abstract (English)
Background: Magnetic resonance imaging (MRI) has high sensitivity for breast cancer detection, but interpretation is time-consuming. Artificial intelligence may aid in pre-screening. Purpose: To evaluate the DINOv2-based Medical Slice Transformer (MST) for ruling out significant findings (Breast Imaging Reporting and Data System [BI-RADS] >=4) in contrast-enhanced and non-contrast-enhanced abbreviated breast MRI. Materials and Methods: This institutional review board approved retrospective study included 1,847 single-breast MRI examinations (377 BI-RADS >=4) from an in-house dataset and 924 from an external validation 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) analysis. AUC differences were compared with the DeLong test. False negatives were characterized, and attention maps of true positives were rated in the external dataset. Results: A total of 1,448 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 (p=0.15). At 97.5% sensitivity, T1sub+T2w had the highest specificity (19% +/- 7%), followed by DWI1500+T2w (17% +/- 11%). Missed lesions had a mean diameter <10 mm at 95% and 97.5% thresholds for both T1sub and DWI1500, predominantly non-mass enhancements. External validation yielded an AUC of 0.77, with 88% of attention maps rated good or moderate. Conclusion: At 97.5% sensitivity, the MST framework correctly triaged cases without BI-RADS >=4, achieving 19% specificity for contrast-enhanced and 17% for non-contrast-enhanced MRI. Further research is warranted before clinical implementation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。