人工智能（AI）在乳腺癌筛查中的应用：基于乳腺筛查人群队列的癌症检测研究。
Artificial intelligence (AI) for breast cancer screening: BreastScreen population-based cohort study of cancer detection.
机构信息
The Daffodil Centre, The University of Sydney, a joint venture with Cancer Council NSW, Sydney, New South Wales, Australia; Curtin School of Population Health, Curtin University, Perth, Western Australia, Australia.
BreastScreen WA, Perth, Western Australia, Australia.
出版信息
EBioMedicine. 2023 Apr;90:104498. doi: 10.1016/j.ebiom.2023.104498. Epub 2023 Feb 28.
BACKGROUND
Artificial intelligence (AI) has been proposed to reduce false-positive screens, increase cancer detection rates (CDRs), and address resourcing challenges faced by breast screening programs. We compared the accuracy of AI versus radiologists in real-world population breast cancer screening, and estimated potential impacts on CDR, recall and workload for simulated AI-radiologist reading.
METHODS
External validation of a commercially-available AI algorithm in a retrospective cohort of 108,970 consecutive mammograms from a population-based screening program, with ascertained outcomes (including interval cancers by registry linkage). Area under the ROC curve (AUC), sensitivity and specificity for AI were compared with radiologists who interpreted the screens in practice. CDR and recall were estimated for simulated AI-radiologist reading (with arbitration) and compared with program metrics.
FINDINGS
The AUC for AI was 0.83 compared with 0.93 for radiologists. At a prospective threshold, sensitivity for AI (0.67; 95% CI: 0.64-0.70) was comparable to radiologists (0.68; 95% CI: 0.66-0.71) with lower specificity (0.81 [95% CI: 0.81-0.81] versus 0.97 [95% CI: 0.97-0.97]). Recall rate for AI-radiologist reading (3.14%) was significantly lower than for the BSWA program (3.38%) (-0.25%; 95% CI: -0.31 to -0.18; P < 0.001). CDR was also lower (6.37 versus 6.97 per 1000) (-0.61; 95% CI: -0.77 to -0.44; P < 0.001); however, AI detected interval cancers that were not found by radiologists (0.72 per 1000; 95% CI: 0.57-0.90). AI-radiologist reading increased arbitration but decreased overall screen-reading volume by 41.4% (95% CI: 41.2-41.6).
INTERPRETATION
Replacement of one radiologist by AI (with arbitration) resulted in lower recall and overall screen-reading volume. There was a small reduction in CDR for AI-radiologist reading. AI detected interval cases that were not identified by radiologists, suggesting potentially higher CDR if radiologists were unblinded to AI findings. These results indicate AI's potential role as a screen-reader of mammograms, but prospective trials are required to determine whether CDR could improve if AI detection was actioned in double-reading with arbitration.
FUNDING
National Breast Cancer Foundation (NBCF), National Health and Medical Research Council (NHMRC).
背景
人工智能（AI）被提议用于减少假阳性筛查、提高癌症检出率（CDR）并解决乳腺筛查项目面临的资源挑战。我们比较了 AI 与放射科医生在真实人群乳腺癌筛查中的准确性，并估计了模拟 AI-放射科医生阅读对 CDR、召回率和工作量的潜在影响。
方法
对基于人群的筛查计划中 108970 例连续乳腺 X 线摄影的回顾性队列进行商业化 AI 算法的外部验证，并通过登记处链接确定结果（包括间隔性癌症）。比较 AI 的 ROC 曲线下面积（AUC）、敏感度和特异度与实际阅片的放射科医生。对模拟 AI-放射科医生阅读（仲裁）进行 CDR 和召回率估计，并与项目指标进行比较。
结果
AI 的 AUC 为 0.83，而放射科医生为 0.93。在前瞻性阈值下，AI 的敏感度（0.67；95%CI：0.64-0.70）与放射科医生（0.68；95%CI：0.66-0.71）相当，但特异性较低（0.81；95%CI：0.81-0.81 与 0.97；95%CI：0.97-0.97）。AI-放射科医生阅读的召回率（3.14%）明显低于 BSWA 计划（3.38%）（-0.25%；95%CI：-0.31 至-0.18；P<0.001）。CDR 也较低（每 1000 例 6.37 例与 6.97 例）（-0.61%；95%CI：-0.77% 至-0.44%；P<0.001）；然而，AI 检测到了放射科医生未发现的间隔性癌症（每 1000 例 0.72 例；95%CI：0.57-0.90）。AI-放射科医生阅读增加了仲裁，但总体筛查阅读量减少了 41.4%（95%CI：41.2-41.6）。
解释
用 AI（仲裁）替代一名放射科医生导致召回率和总体筛查阅读量降低。AI 阅读的 CDR 略有下降。AI 检测到了放射科医生未发现的间隔性病例，这表明如果放射科医生对 AI 结果不盲目，CDR 可能会更高。这些结果表明 AI 作为乳腺 X 线摄影筛查者的潜在作用，但需要前瞻性试验来确定如果 AI 检测在仲裁的双重阅读中得到实施，CDR 是否可以提高。
资助
国家乳腺癌基金会（NBCF）、澳大利亚国家卫生和医学研究委员会（NHMRC）。
Zotero 插件