Department of Radiology, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin, Republic of Korea.
Korean J Radiol. 2024 Apr;25(4):343-350. doi: 10.3348/kjr.2023.0907.
Artificial intelligence-based computer-aided diagnosis (AI-CAD) is increasingly used in mammography. While the continuous scores of AI-CAD have been related to malignancy risk, the understanding of how to interpret and apply these scores remains limited. We investigated the positive predictive values (PPVs) of the abnormality scores generated by a deep learning-based commercial AI-CAD system and analyzed them in relation to clinical and radiological findings.
From March 2020 to May 2022, 656 breasts from 599 women (mean age 52.6 ± 11.5 years, including 0.6% [4/599] high-risk women) who underwent mammography and received positive AI-CAD results (Lunit Insight MMG, abnormality score ≥ 10) were retrospectively included in this study. Univariable and multivariable analyses were performed to evaluate the associations between the AI-CAD abnormality scores and clinical and radiological factors. The breasts were subdivided according to the abnormality scores into groups 1 (10-49), 2 (50-69), 3 (70-89), and 4 (90-100) using the optimal binning method. The PPVs were calculated for all breasts and subgroups.
Diagnostic indications and positive imaging findings by radiologists were associated with higher abnormality scores in the multivariable regression analysis. The overall PPV of AI-CAD was 32.5% (213/656) for all breasts, including 213 breast cancers, 129 breasts with benign biopsy results, and 314 breasts with benign outcomes in the follow-up or diagnostic studies. In the screening mammography subgroup, the PPVs were 18.6% (58/312) overall and 5.1% (12/235), 29.0% (9/31), 57.9% (11/19), and 96.3% (26/27) for score groups 1, 2, 3, and 4, respectively. The PPVs were significantly higher in women with diagnostic indications (45.1% [155/344]), palpability (51.9% [149/287]), fatty breasts (61.2% [60/98]), and certain imaging findings (masses with or without calcifications and distortion).
PPV increased with increasing AI-CAD abnormality scores. The PPVs of AI-CAD satisfied the acceptable PPV range according to Breast Imaging-Reporting and Data System for screening mammography and were higher for diagnostic mammography.
基于人工智能的计算机辅助诊断（AI-CAD）在乳腺 X 线摄影中越来越多地被使用。虽然 AI-CAD 的连续评分与恶性肿瘤风险有关，但对于如何解释和应用这些评分的理解仍然有限。我们研究了一种基于深度学习的商业 AI-CAD 系统生成的异常评分的阳性预测值（PPV），并分析了它们与临床和影像学发现之间的关系。
从 2020 年 3 月至 2022 年 5 月，回顾性纳入了 656 例 599 名女性（平均年龄 52.6±11.5 岁，包括 0.6%[4/599]的高危女性）的乳腺 X 线摄影和接受阳性 AI-CAD 结果（Lunit Insight MMG，异常评分≥10）的乳腺 X 线摄影。采用单变量和多变量分析评估 AI-CAD 异常评分与临床和影像学因素之间的关系。采用最佳分组方法，根据异常评分将乳腺分为 4 组：1 组（10-49 分）、2 组（50-69 分）、3 组（70-89 分）和 4 组（90-100 分）。计算所有乳腺和亚组的 PPV。
在多变量回归分析中，放射科医生的诊断指征和阳性影像学发现与较高的异常评分相关。AI-CAD 的总体 PPV 为 32.5%（213/656），包括 213 例乳腺癌、129 例良性活检结果和 314 例随访或诊断研究中良性结果的乳腺。在筛查性乳腺 X 线摄影亚组中，总体 PPV 为 18.6%（58/312），评分组 1、2、3 和 4 的 PPV 分别为 5.1%（12/235）、29.0%（9/31）、57.9%（11/19）和 96.3%（26/27）。有诊断指征（45.1%[155/344]）、可触及（51.9%[149/287]）、脂肪性乳房（61.2%[60/98]）和特定影像学发现（肿块伴或不伴钙化和变形）的女性的 PPV 显著更高。
PPV 随 AI-CAD 异常评分的增加而增加。AI-CAD 的 PPV 满足了筛查性乳腺 X 线摄影的可接受 PPV 范围，且对诊断性乳腺 X 线摄影的 PPV 更高。
