Saccenti Laetitia, Ben Jedida Bilel, Minssen Lise, Nouri Refaat, Bejjani Lina El, Remili Haifa, Voquang An, Tacher Vania, Kobeiter Hicham, Luciani Alain, Deux Jean Francois, Dao Thu Ha
Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France; Henri Mondor Institute of Biomedical Research -Inserm, U955 Team N 18, Paris Est Creteil University, 94000, Creteil, France.
Department of Medical Imaging, Hopital Henri Mondor, Assistance Publique-Hopitaux de Paris, 94000, Creteil, France.
Diagn Interv Imaging. 2025 Mar;106(3):98-104. doi: 10.1016/j.diii.2024.10.001. Epub 2024 Oct 26.
The purpose of this study was to evaluate an artificial intelligence (AI) software that automatically detects and quantifies breast arterial calcifications (BAC).
Women who underwent both mammography and thoracic computed tomography (CT) from 2009 to 2018 were retrospectively included in this single-center study. Deep learning-based software was used to automatically detect and quantify BAC with a BAC AI score ranging from 0 to 10-points. Results were compared using Spearman correlation test with a previously described BAC manual score based on radiologists' visual quantification of BAC on the mammogram. Coronary artery calcification (CAC) score was manually scored using a 12-point scale on CT. The diagnostic performance of the marked BAC AI score (defined as BAC AI score ≥ 5) for the detection of marked CAC (CAC score ≥ 4) was analyzed in terms of sensitivity, specificity, accuracy and area under the receiver operating characteristic curve (AUC).
A total of 502 women with a median age of 62 years (age range: 42-96 years) were included. The BAC AI score showed a very strong correlation with the BAC manual score (r = 0.83). Marked BAC AI score had 32.7 % sensitivity (37/113; 95 % confidence interval [CI]: 24.2-42.2), 96.1 % specificity (374/389; 95 % CI: 93.7-97.8), 71.2 % positive predictive value (37/52; 95 % CI: 56.9-82.9), 83.1 % negative predictive value (374/450; 95 % CI: 79.3-86.5), and 81.9 % accuracy (411/502; 95 % CI: 78.2-85.1) for the diagnosis of marked CAC. The AUC of the marked BAC AI score for the diagnosis of marked CAC was 0.64 (95 % CI: 0.60-0.69).
The automated BAC AI score shows a very strong correlation with manual BAC scoring in this external validation cohort. The automated BAC AI score may be a useful tool to promote the integration of BAC into mammography reports and to improve awareness of a woman's cardiovascular risk status.
本研究旨在评估一种能自动检测和量化乳腺动脉钙化（BAC）的人工智能（AI）软件。
回顾性纳入2009年至2018年期间同时接受了乳腺X线摄影和胸部计算机断层扫描（CT）的女性，进行这项单中心研究。使用基于深度学习的软件自动检测和量化BAC，BAC人工智能评分范围为0至10分。使用Spearman相关性检验将结果与先前描述的基于放射科医生对乳腺X线摄影上BAC的视觉量化得出的BAC手动评分进行比较。在CT上使用12分制手动对冠状动脉钙化（CAC）评分。根据敏感性、特异性、准确性和受试者操作特征曲线下面积（AUC）分析标记的BAC人工智能评分（定义为BAC人工智能评分≥5）对检测标记的CAC（CAC评分≥4）的诊断性能。
共纳入502名女性，中位年龄62岁（年龄范围：42 - 96岁）。BAC人工智能评分与BAC手动评分显示出非常强的相关性（r = 0.83）。标记的BAC人工智能评分对诊断标记的CAC的敏感性为32.7%（37/113；95%置信区间[CI]：24.2 - 42.2），特异性为96.1%（374/389；95% CI：93.7 - 97.8），阳性预测值为71.2%（37/52；95% CI：56.9 - 82.9），阴性预测值为83.1%（374/450；95% CI：79.3 - 86.5），准确性为81.9%（411/502；95% CI：78.2 - 85.1）。标记的BAC人工智能评分对诊断标记的CAC的AUC为0.64（95% CI：0.60 - 0.69）。
在这个外部验证队列中，自动的BAC人工智能评分与手动BAC评分显示出非常强的相关性。自动的BAC人工智能评分可能是促进将BAC纳入乳腺X线摄影报告并提高对女性心血管风险状况认识的有用工具。
