我们检查了基于计算机断层扫描 (CT) 的深度学习 (DL) 模型在区分良恶性肺实性结节 (SPN) ≤ 8 毫米方面的有效性。研究患者 (n = 719) 分为内部训练组、内部验证组、内部训练组和内部验证组。和外部验证队列；所有患者的 SPN 均较小，并接受了术前胸部 CT 检查和手术切除。我们开发了五个深度学习模型，结合了结节和五个不同结节周围区域的特征，并使用多尺度双重注意网络（MDANet）来区分良性和恶性 SPN。我们选择了性能最佳的模型，然后将其与四种传统算法（VGG19、ResNet50、ResNeXt50 和 DenseNet121）进行比较。此外，使用 MDANet 构建了另外 5 个 DL 模型来区分良性肿瘤和炎性结节，并选出表现最好的一个。模型 4 包含结节和 15 mm 结节周围区域，最能区分良性和恶性 SPN。在外部验证队列中，该模型的曲线下面积 (AUC)、准确度、召回率、精确度和 F1 分数分别为 0.730、0.724、0.711、0.705 和 0.707。模型 4 的表现也优于其他四种传统算法。模型 8 包含结节和 10 毫米结节周围区域，是区分良性肿瘤和炎性结节的最佳模型。该模型在外部验证队列中的 AUC、准确度、召回率、精确度和 F1 分数分别为 0.871、0.938、0.863、0.904 和 0.882。该研究得出的结论是，使用 MDANet 构建的基于 CT 的 DL 模型可以准确地区分小样本。良性和恶性 SPN、良性肿瘤和炎性结节。版权所有 © 2024 大学放射科医生协会。由爱思唯尔公司出版。保留所有权利。

We examined the effectiveness of computed tomography (CT)-based deep learning (DL) models in differentiating benign and malignant solid pulmonary nodules (SPNs) ≤ 8 mm.The study patients (n = 719) were divided into internal training, internal validation, and external validation cohorts; all had small SPNs and had undergone preoperative chest CTs and surgical resection. We developed five DL models incorporating features of the nodule and five different peri-nodular regions with the Multiscale Dual Attention Network (MDANet) to differentiate benign and malignant SPNs. We selected the best-performing model, which was then compared to four conventional algorithms (VGG19, ResNet50, ResNeXt50, and DenseNet121). Furthermore, another five DL models were constructed using MDANet to distinguish benign tumors from inflammatory nodules and the one performed best was selected out.Model 4, which incorporated the nodule and 15 mm peri-nodular region, best differentiated benign and malignant SPNs. The model had an area under the curve (AUC), accuracy, recall, precision, and F1-score of 0.730, 0.724, 0.711, 0.705, and 0.707 in the external validation cohort. Model 4 also performed better than the other four conventional algorithms. Model 8, which incorporated the nodule and 10 mm peri-nodular region, was the best model for distinguishing benign tumors from inflammatory nodules. The model had an AUC, accuracy, recall, precision, and F1-score of 0.871, 0.938, 0.863, 0.904, and 0.882 in the external validation cohort.The study concludes that CT-based DL models built with MDANet can accurately discriminate among small benign and malignant SPNs, benign tumors and inflammatory nodules.Copyright © 2024 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.