Objective To examine the accuracy of artificial intelligence (AI) for the detection of breast cancer in mammography screening practice. Design Systematic review of test accuracy studies. Data sources Medline, Embase, Web of Science, and Cochrane Database of Systematic Reviews from 1 January 2010 to 17 May 2021. Eligibility criteria Studies reporting test accuracy of AI algorithms, alone or in combination with radiologists, to detect cancer in women’s digital mammograms in screening practice, or in test sets. Reference standard was biopsy with histology or follow-up (for screen negative women). Outcomes included test accuracy and cancer type detected. Study selection and synthesis Two reviewers independently assessed articles for inclusion and assessed the methodological quality of included studies using the QUality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. A single reviewer extracted data, which were checked by a second reviewer. Narrative data synthesis was performed. Results Twelve studies totalling 131 822 screened women were included. No prospective studies measuring test accuracy of AI in screening practice were found. Studies were of poor methodological quality. Three retrospective studies compared AI systems with the clinical decisions of the original radiologist, including 79 910 women, of whom 1878 had screen detected cancer or interval cancer within 12 months of screening. Thirty four (94%) of 36 AI systems evaluated in these studies were less accurate than a single radiologist, and all were less accurate than consensus of two or more radiologists. Five smaller studies (1086 women, 520 cancers) at high risk of bias and low generalisability to the clinical context reported that all five evaluated AI systems (as standalone to replace radiologist or as a reader aid) were more accurate than a single radiologist reading a test set in the laboratory. In three studies, AI used for triage screened out 53%, 45%, and 50% of women at low risk but also 10%, 4%, and 0% of cancers detected by radiologists. Conclusions Current evidence for AI does not yet allow judgement of its accuracy in breast cancer screening programmes, and it is unclear where on the clinical pathway AI might be of most benefit. AI systems are not sufficiently specific to replace radiologist double reading in screening programmes. Promising results in smaller studies are not replicated in larger studies. Prospective studies are required to measure the effect of AI in clinical practice. Such studies will require clear stopping rules to ensure that AI does not reduce programme specificity. Study registration Protocol registered as PROSPERO CRD42020213590. No additional data available.

中文翻译：

---

在乳腺癌筛查项目中使用人工智能进行图像分析：测试准确性的系统评价

目的检验人工智能（AI）在乳腺钼靶筛查实践中检测乳腺癌的准确性。设计 测试准确性研究的系统审查。数据来源 Medline、Embase、Web of Science 和 Cochrane 系统评价数据库，时间为 2010 年 1 月 1 日至 2021 年 5 月 17 日。筛选练习，或在测试集中。参考标准是活检组织学或随访（对于筛查阴性的女性）。结果包括测试准确性和检测到的癌症类型。研究选择和综合 两名评审员独立评估纳入的文章，并使用诊断准确性研究的质量评估-2 (QUADAS-2) 工具评估纳入研究的方法学质量。一位评论者提取数据，由第二位评论者检查。进行了叙述性数据合成。结果 共纳入 12 项研究，共 131 822 名接受筛查的女性。没有发现在筛选实践中测量 AI 测试准确性的前瞻性研究。研究方法学质量较差。三项回顾性研究将 AI 系统与原始放射科医生的临床决策进行了比较，其中包括 79 910 名女性，其中 1878 人在筛查后的 12 个月内筛查出癌症或间期癌症。在这些研究中评估的 36 个 AI 系统中，有 34 个（94%）的准确度低于单个放射科医生，并且都低于两位或更多放射科医生的共识准确度。五项较小的研究（1086 名女性，520 名癌症）具有较高的偏倚风险和对临床背景的普遍性较低的报告称，所有五个评估的人工智能系统（作为独立的替代放射科医生或作为阅读辅助）比单个放射科医生阅读一份更准确实验室中的测试集。在三项研究中，用于分类的 AI 筛选出 53%、45% 和 50% 的低风险女性，以及放射科医生检测到的 10%、4% 和 0% 的癌症。结论 目前的 AI 证据尚不能判断其在乳腺癌筛查项目中的准确性，目前尚不清楚 AI 在临床路径中的哪些方面可能最受益。人工智能系统不够具体，无法取代筛查程序中放射科医师的双重阅读。小型研究中的有希望的结果不会在大型研究中重复。需要前瞻性研究来衡量人工智能在临床实践中的作用。此类研究将需要明确的停止规则，以确保人工智能不会降低程序的特异性。研究注册协议注册为 PROSPERO CRD42020213590。没有可用的额外数据。研究注册协议注册为 PROSPERO CRD42020213590。没有可用的额外数据。研究注册协议注册为 PROSPERO CRD42020213590。没有可用的额外数据。