基于人工智能的自适应乳腺MRI扫描
这项回顾性阅片研究纳入2013年1月至2019年1月三个区域癌症中心的连续增强筛查乳腺MRI检查,模拟AI导向的分层扫描:AI对减影最大强度投影图像生成可疑度评分,低评分者仅行动态增强MRI(AB-MRI方案)。AI分流50%检查至AB-MRI与全方案相比,敏感度88.2%对86.3%、特异度80.8%对81.4%,特异度降低不超过2.7个百分点,无因未行全方案而漏检的癌症。结论为AI导向分层MRI在维持诊断性能的同时缩短模拟扫描时间。
要点
- AI对减影MIP生成可疑度评分,低评分者仅行动态增强MRI,可缩短模拟扫描时间。
- 分流50%检查至AB-MRI时敏感度88.2%对86.3%、特异度80.8%对81.4%,特异度降低不超过2.7个百分点。
- 无AI分流检查因未行全方案而额外检出癌症。
核心结论
- AI导向分层MRI在维持诊断性能的同时缩短了模拟扫描时间。
研究设计与样本
- 回顾性阅片研究,纳入2013年1月至2019年1月三个区域癌症中心的连续增强筛查乳腺MRI检查,共863名女性(平均年龄52岁±10[SD])、1423次MRI检查;由院内AI工具对减影最大强度投影图像生成可疑度评分,低评分者仅行动态增强MRI(AB-MRI方案),并与全MRI方案比较。
诊断标准与关键数值
- AI分流50%检查至AB-MRI与全方案相比:敏感度88.2%(45/51;95%CI:79.4,97.1)对86.3%(44/51;95%CI:76.8,95.7);特异度80.8%(1108/1372;95%CI:78.7,82.8)对81.4%(1117/1372;95%CI:79.4,83.5);阳性预测值3(活检检出癌症百分比)23.6%(43/182;95%CI:17.5,29.8)对24.7%(42/170;95%CI:18.2,31.2);癌症检出率(每1000次检查)31.6(95%CI:22.5,40.7)对30.9(95%CI:21.9,39.9);间期癌率(每1000次检查)4.2(95%CI:0.9,7.6)对4.9(95%CI:1.3,8.6);AI分流后特异度降低不超过2.7个百分点。
临床应用与阅片要点
- AI分流将50%检查归入AB-MRI方案,其诊断性能与全方案相近,且无AI分流检查因未行全方案而额外检出癌症;本模拟研究结果可供筛查乳腺MRI流程优化参考。
局限性
- 本文为模拟研究,结果基于回顾性数据。
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
Background MRI protocols typically involve many imaging sequences and often require too much time. Purpose To simulate artificial intelligence (AI)-directed stratified scanning for screening breast MRI with various triage thresholds and evaluate its diagnostic performance against that of the full breast MRI protocol. Materials and Methods This retrospective reader study included consecutive contrast-enhanced screening breast MRI examinations performed between January 2013 and January 2019 at three regional cancer sites. In this simulation study, an in-house AI tool generated a suspicion score for subtraction maximum intensity projection images during a given MRI examination, and the score was used to determine whether to proceed with the full MRI protocol or end the examination early (abbreviated breast MRI [AB-MRI] protocol). Examinations with suspicion scores under the 50th percentile were read using both the AB-MRI protocol (ie, dynamic contrast-enhanced MRI scans only) and the full MRI protocol. Diagnostic performance metrics for screening with various AI triage thresholds were compared with those for screening without AI triage. Results Of 863 women (mean age, 52 years ± 10 [SD]; 1423 MRI examinations), 51 received a cancer diagnosis within 12 months of screening. The diagnostic performance metrics for AI-directed stratified scanning that triaged 50% of examinations to AB-MRI versus full MRI protocol scanning were as follows: sensitivity, 88.2% (45 of 51; 95% CI: 79.4, 97.1) versus 86.3% (44 of 51; 95% CI: 76.8, 95.7); specificity, 80.8% (1108 of 1372; 95% CI: 78.7, 82.8) versus 81.4% (1117 of 1372; 95% CI: 79.4, 83.5); positive predictive value 3 (ie, percent of biopsies yielding cancer), 23.6% (43 of 182; 95% CI: 17.5, 29.8) versus 24.7% (42 of 170; 95% CI: 18.2, 31.2); cancer detection rate (per 1000 examinations), 31.6 (95% CI: 22.5, 40.7) versus 30.9 (95% CI: 21.9, 39.9); and interval cancer rate (per 1000 examinations), 4.2 (95% CI: 0.9, 7.6) versus 4.9 (95% CI: 1.3, 8.6). Specificity decreased by no more than 2.7 percentage points with AI triage. There were no AI-triaged examinations for which conducting the full MRI protocol would have resulted in additional cancer detection. Conclusion AI-directed stratified MRI decreased simulated scan times while maintaining diagnostic performance. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Strand in this issue.
引用
- Eskreis-Winkler S, Bhowmik A, Kelly LH, et al. Adaptive Breast MRI Scanning Using AI. Radiology. 2025. PMID: 40459419. doi:10.1148/radiol.242924
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。