文献速递乳腺乳腺X线

基于人群筛查项目中人工智能与放射科医生在数字乳腺断层摄影假阳性检查上的比较

Artificial Intelligence Versus Radiologist False-Positives on Digital Breast Tomosynthesis Examinations in a Population-Based Screening Program.
PubMed 文献 · AJR Am J Roentgenol · 2026-01-21

该回顾性研究纳入2977名女性3183次筛查数字乳腺断层摄影检查,比较人工智能与放射科医生假阳性检查的特征。人工智能与放射科医生的假阳性率均为10%,仅43%的假阳性为人工智能独有、44%为放射科医生独有、13%为两者一致;两者独有假阳性的患者特征和影像表现不同,一致的阳性发现中活检高危病变比例较高。

要点

  • 人工智能与放射科医生假阳性率均为10%(304/3183 vs 308/3183),仅13%的假阳性检查为两者重叠。
  • 人工智能独有假阳性多见于良性钙化(40%)、不对称(13%)和良性术后改变(12%)。
  • 放射科医生独有假阳性多见于肿块(47%)、不对称(19%)和不定性钙化(15%)。

核心结论

  • 人工智能与放射科医生假阳性数字乳腺断层摄影检查在影像和患者层面存在差异;仅小部分假阳性检查重叠,但一致的阳性发现高危病变比例较高。

研究设计与样本

  • 回顾性研究,纳入2977名女性(平均年龄55岁)的3183次筛查数字乳腺断层摄影检查,检查时间2013年1月至2017年6月,属于一项观察性人群筛查研究;使用商业人工智能工具分析图像,以BI-RADS 0类作为放射科医生阳性标准,假阳性定义为1年内未诊断乳腺癌。

关键影像表现/征象

  • 人工智能独有假阳性 flagged 发现最常见为良性钙化(40%)、不对称(13%)和良性术后改变(12%)。
  • 放射科医生独有假阳性 flagged 发现最常见为肿块(47%)、不对称(19%)和不定性钙化(15%)。
  • 人工智能独有假阳性与放射科医生独有假阳性相比,患者平均年龄更高(60岁 vs 52岁,p < .001),致密乳腺频率更低(24% vs 57%,p < .001)。
  • 人工智能独有假阳性与放射科医生独有假阳性相比,个人乳腺癌史频率更高(13% vs 2%,p < .001),既往乳腺影像检查频率更高(95% vs 78%,p < .001),既往乳腺手术频率更高(37% vs 11%,p < .001)。

诊断标准与关键数值

  • 人工智能阳性定义为 elevated-risk 结果,放射科医生阳性定义为BI-RADS 0类。
  • 假阳性检查定义为1年内未诊断乳腺癌。
  • 人工智能假阳性率为10%(304/3183),放射科医生假阳性率为10%(308/3183)。
  • 541次假阳性检查中,233次(43%)为仅人工智能假阳性,237次(44%)为仅放射科医生假阳性,71次(13%)为两者均假阳性。
  • 18个一致 flagged 发现接受活检,其中44%为高危病变。

临床应用与阅片要点

  • 人工智能与放射科医生假阳性检查在患者年龄、乳腺密度、个人乳腺癌史、既往影像和手术史方面存在差异,可帮助理解两者假阳性来源。
  • 两者一致的阳性发现可能代表富集的可操作异常子集,但原文未据此给出具体临床推荐。

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. Insights into the nature of false-positive findings flagged by contemporary mammography artificial intelligence (AI) systems could inform the potential use of AI to reduce false-positive recall rates. OBJECTIVE. The purpose of this study was to compare AI and radiologists in terms of characteristics of false-positive digital breast tomosynthesis (DBT) examinations in a breast cancer screening population. METHODS. This retrospective study included 2977 women (mean age, 55 years) who were participating in an observational population-based screening study and underwent 3183 screening DBT examinations from January 2013 to June 2017. A commercial AI tool analyzed DBT examinations. Positive examinations were defined as having an elevated-risk result for AI and as having been assigned BI-RADS category 0 for interpreting radiologists. False-positive examinations were defined as the absence of a breast cancer diagnosis within 1 year. Radiologists rereviewed the imaging for AI-flagged false-positive findings. RESULTS. The false-positive rate was 10% for both AI (304/3183) and radiologists (308/3183). Of 541 total false-positive examinations, 233 (43%) were false-positives for AI only, 237 (44%) were false-positives for radiologists only, and 71 (13%) were false-positives for both. AI-only versus radiologist-only false-positives were associated with greater mean patient age (60 vs 52 years, p < .001), lower frequency of dense breasts (24% vs 57%, p < .001), and greater frequencies of a personal history of breast cancer (13% vs 2%, p < .001), prior breast imaging studies (95% vs 78%, p < .001), and prior breast surgical procedures (37% vs 11%, p < .001). The false-positive examinations included 932 AI-only flagged findings, 315 radiologist-only flagged findings, and 49 flagged findings concordant between AI and radiologists. AI-only flagged findings were most commonly benign calcifications (40%), asymmetries (13%), and benign postsurgical change (12%); radiologist-only flagged findings were most commonly masses (47%), asymmetries (19%), and indeterminate calcifications (15%). Of 18 concordant flagged findings that were biopsied, 44% yielded high-risk lesions. CONCLUSION. Imaging and patient-level differences were observed between AI and radiologist false-positive DBT examinations. Although only a small fraction of false-positive examinations overlapped between AI and radiologists, concordant flagged findings had a high rate of representing high-risk lesions. CLINICAL IMPACT. The findings may help guide strategies for using AI to improve DBT recall specificity. In particular, concordant findings may represent an enriched subset of actionable abnormalities.

来源:AJR Am J Roentgenol,查看原文。版权归原作者所有。

引用

  1. Shahrvini T, Wood EJ, Joines MM, et al. Artificial Intelligence Versus Radiologist False-Positives on Digital Breast Tomosynthesis Examinations in a Population-Based Screening Program. AJR Am J Roentgenol. 2026. PMID: 41031942. doi:10.2214/AJR.25.33412

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。