文献速递乳腺乳腺X线

人工智能仅在自信时判读乳腺X线摄影:一种混合乳腺癌筛查判读策略

AI Should Read Mammograms Only When Confident: A Hybrid Breast Cancer Screening Reading Strategy.
PubMed 文献 · Radiology · 2025-01-01

本研究提出一种混合判读策略:AI模型输出恶性概率及其不确定性,仅在预测自信时由模型决定召回,否则由放射科医师双读。在41 469次筛查检查中,61.9%的检查由放射科医师判读,混合判读的召回率23.6‰、癌检出率6.6‰,与标准双读(23.9‰、6.6‰)相似。结论认为该策略可能大幅减少放射科医师工作量而不改变癌检出率和召回率。

要点

  • AI模型对不确定预测的检查AUC为0.87,低于确定预测检查的0.96(P = .02)。
  • 混合判读下仅61.9%的检查需放射科医师判读,其余由自信的AI模型决定召回。
  • 混合判读召回率23.6‰、癌检出率6.6‰,与标准双读的23.9‰和6.6‰相似。

核心结论

  • 将包含不确定性量化的AI乳腺X线摄影判读模型纳入筛查判读,可能大幅减少放射科医师工作量,而不改变癌检出率和召回率。

研究设计与样本

  • 回顾性优化并在2003年7月至2018年8月间未见过的筛查检查集上测试,数据集按50-50分割,共纳入15 522名女性的41 469次检查,中位年龄59岁(IQR 54.0-66.0岁)。

诊断标准与关键数值

  • 测试了8种基于单个或全部可疑区域的不确定性指标;最佳指标为单个区域平均恶性概率的熵,此时61.9%的检查由放射科医师判读;混合判读召回率23.6‰(95%CI 21.6, 25.5)、癌检出率6.6‰(95%CI 5.5, 7.7),标准双读分别为23.9‰(95%CI 21.9, 25.8;P = .27)和6.6‰(95%CI 5.5, 7.7;P = .14)。

临床应用与阅片要点

  • 原文结论认为,该混合判读策略可能大幅减少放射科医师工作量而不改变癌检出和召回率;作者在结论中未给出具体操作推荐。

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

Background Quantifying the uncertainty in artificial intelligence (AI)-based interpretations of mammograms could help AI integration in screening. Purpose To evaluate the reduction in radiologists' reading workload in mammographic screening while maintaining performance by incorporating an AI model that includes uncertainty quantification. Materials and Methods An AI model was introduced that outputs a probability of malignancy (PoM) and a measure of its uncertainty. Eight candidate uncertainty metrics, based on one or all suspicious regions, were tested. A hybrid reading approach was proposed, with recall decisions made by the model only when predictions were deemed confident; otherwise, radiologist double reading was applied. The approach was retrospectively optimized and tested with a previously unseen set of screening examinations from July 2003 to August 2018, split 50-50. Recall and cancer detection rates were compared with standard double reading. The model's area under the receiver operating characteristic curve (AUC) was compared between examinations with uncertain predictions and examinations with certain predictions. One-tailed P values were obtained with bootstrapping, and the significance threshold was .05. Results The dataset included 41 469 examinations from 15 522 women; the median age was 59 years (IQR, 54.0-66.0 years). With the best-performing uncertainty metric, the entropy of the mean PoM of one region, 61.9% of the examinations were read by radiologists. Hybrid reading resulted in a recall rate of 23.6‰ (95% CI: 21.6, 25.5) and a cancer detection rate of 6.6‰ (95% CI: 5.5, 7.7), similar to that of standard double reading (23.9‰ [95% CI: 21.9, 25.8; P = .27] and 6.6‰ [95% CI: 5.5, 7.7; P = .14], respectively). The model's AUC was lower for examinations with uncertain predictions (0.87 [95% CI: 0.82, 0.92]) than for examinations with certain predictions (0.96 [95% CI: 0.89, 0.99]) (P = .02). Conclusion Incorporating an AI mammography interpretation model that includes uncertainty quantifications in the reading of screening mammograms may reduce the radiologists' workload substantially without changing cancer detection and recall rates. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Baltzer in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Verboom SD, Kroes J, Pires S, et al. AI Should Read Mammograms Only When Confident: A Hybrid Breast Cancer Screening Reading Strategy. Radiology. 2025. PMID: 40828041. doi:10.1148/radiol.242594

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。