文献速递乳腺乳腺X线

在乳腺筛查项目中加入人工智能病例恶性评分以减少阅片工作量:回顾性REAI项目结果

Adding artificial intelligence case malignancy scoring to reduce screen-reading workload in breast screening program: results of the retrospective REAI program.
PubMed 文献 · Radiol Med · 2025-11-26

基于2023-2024年雷焦艾米利亚乳腺筛查项目89176例连续筛查检查(含479例活检证实癌),回顾性模拟将AI病例恶性评分(AI-CMS)整合入标准筛查流程以减少放射科医生阅片工作量。在AI-CMS阈值5%-25%时,人工阅片工作量降低13.4%-36.1%,最终召回率4.0%-4.3%(当前双读为4.4%),阳性预测值12.6%-13.3%(当前12.2%),假阳性率3.5%-3.8%(当前3.9%);阈值≤5%时未漏诊真阳性病例,癌检出率维持当前双读的5.4‰。结论认为该策略可大幅减少阅片工作量并轻微减少不必要的进一步检查,且经济上可持续,但受回顾性模拟设计及间期癌数据部分可得的限制。

要点

  • AI-CMS阈值5%-25%时人工阅片工作量降低13.4%-36.1%,阈值≤5%时未漏诊真阳性病例。
  • 最终召回率4.0%-4.3%略低于当前双读的4.4%,阳性预测值12.6%-13.3%高于当前12.2%。
  • 假阳性率3.5%-3.8%低于当前3.9%,癌检出率维持当前双读的5.4‰。

核心结论

  • 将AI-CMS支持整合入标准筛查场景可大幅减少阅片工作量并轻微减少不必要的进一步检查,且不影响癌检出率。
  • 该策略在经济上可持续,但受回顾性模拟设计及间期癌数据部分可得的限制。

研究设计与样本

  • 回顾性模拟研究,基于2023-2024年雷焦艾米利亚乳腺筛查项目(REBSP)的89176例连续筛查检查,其中479例为活检证实癌。
  • 所提策略中,计算机辅助检测(CAD)作为阅片者(CR),召回AI-CMS高于预设阈值的女性,阈值范围为5%至25%。
  • 若第一放射科医生(HR1)不同意CR,病例转至第二放射科医生(HR2),若人类阅片者意见仍不一致,则转至第三放射科医生(HR3)。
  • 间期癌仅部分可得,因此真实筛查流程之外发现的假阴性无法评估。

诊断标准与关键数值

  • AI-CMS阈值5%、8%、10%、15%、20%、25%时,人工工作量降低13.4%至36.1%。
  • 最终召回率降至4.0%-4.3%,略低于当前人工双读的4.4%;阳性预测值12.6%-13.3%,高于当前12.2%;假阳性率3.5%-3.8%,低于当前3.9%。
  • 阈值≤5%时未漏诊真阳性病例,癌检出率维持当前双读检出的5.4‰。
  • CAD投资回收期按6年或8年计算时,该策略节省费用约17800至超过590000欧元。

临床应用与阅片要点

  • 原文未据此给出推荐。

局限性

  • 原文指出该研究受回顾性模拟设计限制。
  • 原文指出间期癌数据仅部分可得,因此真实筛查流程之外发现的假阴性无法评估。

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

AIM: The AI case malignancy score (AI-CMS) represents the AI algorithm's confidence (from 0 to 100%) that a mammography exam is malignant. This work aims to retrospectively evaluate, through simulation on real-world data, a strategy that integrates AI-CMS into a standard screening scenario to reduce the radiologists' workload.

METHODS: A total of 89176 consecutive screening exams from the 2023-2024 Reggio Emilia Breast Screening Program (REBSP) were retrospectively considered, which included 479 biopsy-proven cancers (interval cancers were only partially available, therefore false negatives beyond those detected in the real screening workflow could not be assessed). In the proposed strategy, computer-aided detection (CAD) acts as a reader (CR), recalling women with an AI-CMS greater than a predefined threshold (ranging from 5 to 25%). If the first radiologist (HR1) disagrees with CR, the case goes to a second radiologist (HR2) and, in case of human disagreement, to a third radiologist (HR3). For each threshold, final recall rate (RR), cancer detection rate (CDR), number of detected cancers (DC), predictive positive value (PPV) of recalls, false positive rate (FPR), human reading workload, and economic impact were estimated.

RESULTS: At AI-CMS thresholds of 5%, 8%, 10%, 15%, 20%, and 25%, human workload decrease ranged from 13.4% to 36.1%. The final RR decreased between 4.3% and 4.0%, slightly lower than the current 4.4% with human double reading. The PPV ranged from 12.6% to 13.3%, higher than the current PPV of 12.2%. The FPR ranged from 3.8% to 3.5%, down from the current 3.9%. With thresholds up to 5%, no true positive cases were missed, maintaining the CDR of 5.4‰ of those detected by current double reading. Considering CAD payback periods of either 6 or 8 years, financial savings from our strategy ranged from approximately 17800 to over 590,000€.

CONCLUSION: Integrating AI-CMS support into a standard screening scenario could substantially reduce the screen-reading workload and slightly reduce unnecessary ascertainments without affecting the cancer detection rate. This approach, although limited by its retrospective simulation design and the partial availability of interval cancer data, has also proven to be economically sustainable.

来源:Radiol Med,查看原文。版权归原作者所有。

引用

  1. Nitrosi A, Giorgi Rossi P, Verzellesi L, et al. Adding artificial intelligence case malignancy scoring to reduce screen-reading workload in breast screening program: results of the retrospective REAI program. Radiol Med. 2025. PMID: 41296250. doi:10.1007/s11547-025-02154-0

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。