人工智能降低筛查数字乳腺断层摄影的间期癌发生率
本研究回顾性分析2011年2月至2023年6月在同一学术机构因确诊间期癌而复查的筛查数字乳腺断层摄影(DBT)影像,评估美国FDA批准的人工智能(AI)算法检出和定位间期癌的性能,并以同一阈值(评分≥10为阳性)分析1000例真阳性、真阴性和假阳性筛查DBT。AI在回顾性评估中正确定位32.6%(73/224)的间期癌;在筛查检出(真阳性)癌中正确定位84.4%(282/334);真阴性和假阳性病例分别有85.9%(286/333)和73.3%(244/333)被正确判为阴性。
要点
- AI在回顾性筛查DBT中正确定位32.6%(73/224)的间期癌。
- AI检出的间期癌手术病理更大(37 vs 22 mm;P < .001),腋窝淋巴结阳性率更高(41.3% [26/63] vs 22.8% [28/123];P = .01)。
- 同一阈值(评分≥10为阳性)下,AI正确定位84.4%(282/334)的筛查检出(真阳性)癌,真阴性和假阳性分别有85.9%(286/333)和73.3%(244/333)判为阴性。
核心结论
- AI在回顾性评估筛查DBT时正确定位近三分之一的间期癌,可能降低间期癌发生率。
研究设计与样本
- 回顾性分析2011年2月至2023年6月在同一学术机构因确诊间期癌而复查的筛查DBT,由美国FDA批准的AI算法分析;AI阳性(评分≥10)检查由两名乳腺影像放射科医师独立复核以判断标注是否对应后续癌灶;另以同一阈值分析1000例真阳性、真阴性和假阳性筛查DBT。
诊断标准与关键数值
- 病灶评分0–100分,检查水平评分取最高病灶评分,评分≥10为AI阳性;AI正确定位32.6%(73/224)的间期癌、84.4%(282/334)的筛查检出(真阳性)癌;真阴性85.9%(286/333)和假阳性73.3%(244/333)判为阴性。
临床应用与阅片要点
- 作者认为AI在回顾性评估筛查DBT时正确定位近三分之一的间期癌,可能降低间期癌发生率。
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 Given the lack of long-term outcome data for screening digital breast tomosynthesis (DBT), the interval cancer rate is a commonly used surrogate for patient outcomes. Purpose To evaluate the performance of an artificial intelligence (AI) algorithm in detecting and localizing interval cancers at screening DBT and to validate the diagnostic threshold of the algorithm by analyzing its performance across interval, true-positive, true-negative, and false-positive screening DBT examinations. Materials and Methods Screening DBT examinations performed immediately before confirmed interval cancer diagnoses between February 2011 and June 2023 at an academic institution were retrospectively analyzed by a U.S. Food and Drug Administration-cleared AI algorithm. Lesions marked by AI on DBT sections were assigned a score from 0 to 100, with the examination-level score reflecting the highest lesion score. AI-positive examinations (score ≥10) were independently reviewed by two breast imaging radiologists to determine whether AI annotations corresponded to the site of the subsequent cancer. Imaging and clinicopathologic features were compared between interval cancers detected and not detected by AI using the Wilcoxon signed rank test and Fisher exact test. Using the same threshold score, 1000 true-positive, true-negative, and false-positive screening DBT examinations were also analyzed by AI. Results Among 224 interval cancers in 224 women (mean age, 61 years ± 14 [SD]), AI correctly localized 32.6% (73 of 224) of the cancers at retrospective evaluation of the screening DBT examinations. Features associated with interval cancers detected by AI (versus not detected) included larger size at surgical pathology (37 vs 22 mm; P < .001) and axillary lymph node positivity (41.3% [26 of 63] vs 22.8% [28 of 123]; P = .01). Using the same threshold (score of 10 or greater considered positive), AI correctly localized 84.4% (282 of 334) of screening-detected (true-positive) cancers and correctly categorized 85.9% (286 of 333) and 73.3% (244 of 333) of true-negative and false-positive cases, respectively, as negative. Conclusion AI correctly localized nearly one-third of interval cancers at retrospective evaluation of screening DBT examinations and has the potential to decrease the interval cancer rate. © RSNA, 2025 See also the editorial by Lee and Milch in this issue.
引用
- Bahl M, Langarica S, Lamb LR, et al. AI to Reduce the Interval Cancer Rate of Screening Digital Breast Tomosynthesis. Radiology. 2025. PMID: 40728399. doi:10.1148/radiol.241050
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。