Department of Radiology, Yongin Severance Hospital, Research Institute of Radiological Science, Yonsei University College of Medicine, Seoul, Korea.
Department of Computational Science and Engineering, Yonsei University, Seoul, Korea.
J Digit Imaging. 2022 Dec;35(6):1699-1707. doi: 10.1007/s10278-022-00680-1. Epub 2022 Jul 28.
As thyroid and breast cancer have several US findings in common, we applied an artificial intelligence computer-assisted diagnosis (AI-CAD) software originally developed for thyroid nodules to breast lesions on ultrasound (US) and evaluated its diagnostic performance. From January 2017 to December 2017, 1042 breast lesions (mean size 20.2 ± 11.8 mm) of 1001 patients (mean age 45.9 ± 12.9 years) who underwent US-guided core-needle biopsy were included. An AI-CAD software that was previously trained and validated with thyroid nodules using the convolutional neural network was applied to breast nodules. There were 665 benign breast lesions (63.0%) and 391 breast cancers (37.0%). The area under the receiver operating characteristic curve (AUROC) of AI-CAD to differentiate breast lesions was 0.678 (95% confidence interval: 0.649, 0.707). After fine-tuning AI-CAD with 1084 separate breast lesions, the diagnostic performance of AI-CAD markedly improved (AUC 0.841). This was significantly higher than that of radiologists when the cutoff category was BI-RADS 4a (AUC 0.621, P < 0.001), but lower when the cutoff category was BI-RADS 4b (AUC 0.908, P < 0.001). When applied to breast lesions, the diagnostic performance of an AI-CAD software that had been developed for differentiating malignant and benign thyroid nodules was not bad. However, an organ-specific approach guarantees better diagnostic performance despite the similar US features of thyroid and breast malignancies.
由于甲状腺癌和乳腺癌有一些美国的发现共同的，我们应用人工智能计算机辅助诊断（AI-CAD）软件最初是为甲状腺结节开发的，应用于超声（US）上的乳腺病变，并评估其诊断性能。从 2017 年 1 月至 2017 年 12 月，纳入了 1001 例患者（平均年龄 45.9±12.9 岁）的 1042 个乳腺病变（平均大小 20.2±11.8mm），这些患者均接受了超声引导下的核心针活检。应用了一种以前使用甲状腺结节的卷积神经网络进行训练和验证的 AI-CAD 软件来诊断乳腺结节。其中 665 个良性乳腺病变（63.0%）和 391 个乳腺癌（37.0%）。AI-CAD 区分乳腺病变的受试者工作特征曲线（ROC）下面积（AUROC）为 0.678（95%置信区间：0.649，0.707）。在使用 1084 个独立的乳腺病变对 AI-CAD 进行微调后，AI-CAD 的诊断性能明显提高（AUC 0.841）。当截止类别为 BI-RADS 4a 时，这明显高于放射科医生的诊断性能（AUC 0.621，P<0.001），但当截止类别为 BI-RADS 4b 时，AI-CAD 的诊断性能（AUC 0.908，P<0.001）较低。当应用于乳腺病变时，用于区分良恶性甲状腺结节的 AI-CAD 软件的诊断性能不差。然而，尽管甲状腺和乳腺癌的 US 特征相似，器官特异性方法可确保更好的诊断性能。
