Yu Tiffany T, Hoyt Anne C, Joines Melissa M, Fischer Cheryce P, Yaghmai Nazanin, Chalfant James S, Chow Lucy, Mortazavi Shabnam, Sears Christopher D, Sayre James, Elmore Joann G, Hsu William, Milch Hannah S
David Geffen School of Medicine, University of California Los Angeles, CA, USA.
Department of Radiological Sciences, University of California Los Angeles Health Sciences, CA, USA.
J Natl Cancer Inst. 2025 Apr 18. doi: 10.1093/jnci/djaf103.
European studies suggest artificial intelligence (AI) can reduce interval breast cancers (IBCs). However, research on IBC classification and AI's effectiveness in the U.S., particularly using digital breast tomosynthesis (DBT) and annual screening, is limited. We aimed to mammographically classify IBCs and assess AI performance using a 12-month screening interval.
From digital mammography (DM) and DBT screening mammograms acquired 2010-2019 at a U.S. tertiary care academic center, we identified IBCs diagnosed <12 months after a negative mammogram. At least three breast radiologists retrospectively classified IBCs as missed-reading error, minimal signs-actionable, minimal signs-non-actionable, true interval, occult, or missed-technical error. A deep-learning AI tool assigned risk scores (1-10) to the negative index screening mammograms, with scores ≥8 considered "flagged." Statistical analysis evaluated associations among IBC types and AI exam scores, AI markings, and patient/tumor characteristics.
From 184,935 screening mammograms (65% DM, 35% DBT), we identified 148 IBCs in 148 women (mean age, 61±12 years). Of these, 26% were minimal signs-actionable; 24% occult; 22% minimal signs-non-actionable; 17% missed-reading error; 6% true interval; and 5% missed-technical error (p<.001). AI scored 131 mammograms (17 errors excluded). AI most frequently flagged exams with missed-reading errors (90%), minimal signs-actionable (89%) and minimal signs-non-actionable (72%) (p=.02). AI localized mammographically-visible types more accurately (35-68%) than non-visible types (0-50%, p=.02).
AI more frequently flagged and accurately localized IBC types that were mammographically visible at screening (missed or minimal signs), as compared to true interval or occult cancers.
欧洲的研究表明，人工智能（AI）可减少间期乳腺癌（IBC）。然而，关于美国IBC分类以及AI有效性的研究有限，尤其是使用数字乳腺断层合成（DBT）和年度筛查的研究。我们旨在通过乳腺钼靶对IBC进行分类，并使用12个月的筛查间隔评估AI的性能。
从2010年至2019年在美国一家三级医疗学术中心获取的数字乳腺X线摄影（DM）和DBT筛查乳腺X线片中，我们确定了在乳腺X线摄影检查结果为阴性后12个月内被诊断出的IBC。至少三名乳腺放射科医生回顾性地将IBC分类为漏读错误、微小征象-可采取行动、微小征象-不可采取行动、真性间期、隐匿性或漏技错误。一个深度学习AI工具为阴性索引筛查乳腺X线片分配风险评分（1至10），评分≥8被视为“标记”。统计分析评估了IBC类型与AI检查评分、AI标记以及患者/肿瘤特征之间的关联。
在184,935张筛查乳腺X线片（65%为DM，35%为DBT）中，我们在148名女性（平均年龄61±12岁）中发现了148例IBC。其中，26%为微小征象-可采取行动；24%为隐匿性；22%为微小征象-不可采取行动；17%为漏读错误；6%为真性间期；5%为漏技错误（p<0.001）。AI对131张乳腺X线片进行了评分（排除17个错误）。AI最常标记漏读错误（90%）、微小征象-可采取行动（89%）和微小征象-不可采取行动（72%）的检查（p = 0.02）。与不可见类型（0至50%，p = 0.02）相比，AI对乳腺钼靶可见类型（35至68%）的定位更准确。
与真性间期癌或隐匿性癌相比，AI更频繁地标记并更准确地定位了筛查时乳腺钼靶可见的IBC类型（漏诊或微小征象）。
