BackgroundThis study aims to explore the accuracy of Convolutional Neural Network (CNN) models in predicting malignancy in Dynamic Contrast-Enhanced Breast Magnetic Resonance Imaging (DCE-BMRI).MethodsA total of 273 benign lesions (benign group) and 274 malignant lesions (malignant group) were collected and randomly divided into a training set (246 benign and 245 malignant lesions) and a testing set (28 benign and 28 malignant lesions) in a 9:1 ratio. An additional 53 lesions from 53 patients were designated as the validation set. Five models-VGG16, VGG19, DenseNet201, ResNet50, and MobileNetV2-were evaluated. Model performance was assessed using accuracy (Ac) in the training and testing sets, and precision (Pr), recall (Rc), F1 score (F1), and area under the receiver operating characteristic curve (AUC) in the validation set.ResultsThe accuracy of VGG19 on the test set (0.96) is higher than that of VGG16 (0.91), DenseNet201 (0.91), ResNet50 (0.67), and MobileNetV2 (0.88). For the validation set, VGG19 achieved higher performance metrics (Pr 0.75, Rc 0.76, F1 0.73, AUC 0.76) compared to the other models, specifically VGG16 (Pr 0.73, Rc 0.75, F1 0.70, AUC 0.73), DenseNet201 (Pr 0.71, Rc 0.74, F1 0.69, AUC 0.71), ResNet50 (Pr 0.65, Rc 0.68, F1 0.60, AUC 0.65), and MobileNetV2 (Pr 0.73, Rc 0.75, F1 0.71, AUC 0.73). S4 model achieved higher performance metrics (Pr 0.89, Rc 0.88, F1 0.87, AUC 0.89) compared to the other four fine-tuned models, specifically S1 (Pr 0.75, Rc 0.76, F1 0.74, AUC 0.75), S2 (Pr 0.77, Rc 0.79, F1 0.75, AUC 0.77), S3 (Pr 0.76, Rc 0.76, F1 0.73, AUC 0.75), and S5 (Pr 0.77, Rc 0.79, F1 0.75, AUC 0.77). Additionally, S4 model showed the lowest loss value in the testing set. Notably, the AUC of S4 for BI-RADS 3 was 0.90 and for BI-RADS 4 was 0.86, both significantly higher than the 0.65 AUC for BI-RADS 5.ConclusionsThe S4 model we propose has demonstrated superior performance in predicting the likelihood of malignancy in DCE-BMRI, making it a promising candidate for clinical application in patients with breast diseases. However, further validation is essential, highlighting the need for additional data to confirm its efficacy.

In order to achieve better performance, artificial intelligence is used in breast cancer diagnosis. In this study, we evaluated the efficacy of different fine-tuning strategies of deep transfer learning (DTL) based on the DenseNet201 model to differentiate malignant from benign lesions on breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). We collected 4260 images of benign lesions and 4140 images of malignant lesions of the breast pertaining to pathologically confirmed cases. The benign and malignant groups was randomly divided into a training set and a testing set at a ratio of 9:1. A DTL model based on the DenseNet201 model was established, and the effectiveness of 4 fine-tuning strategies (S0: strategy 0, S1: strategy; S2: strategy; and S3: strategy) was compared. Additionally, DCE-MRI images of 48 breast lesions were selected to verify the robustness of the model. Ten images were obtained for each lesion. The classification was considered correct if more than 5 images were correctly classified. The metrics for model performance evaluation included accuracy (Ac) in the training and testing sets, precision (Pr), recall rate (Rc), f1 score (f1), and area under the receiver operating characteristic curve (AUROC) in the validation set. The Ac of the 4 fine-tuning strategies reached 100.00% in the training set. The S2 strategy exhibited good convergence in the testing set. The Ac of S2 was 98.01% in the testing set, which was higher than those of S0 (93.10%), S1 (90.45%), and S3 (93.90%). The average classification Pr, Rc, f1, and AUROC of S2 in the validation set were (89.00%, 80.00%, 0.81, and 0.79, respectively) higher than those of S0 (76.00%, 67.00%, 0.69, and 0.65, respectively), S1 (60.00%, 60.00%, 0.60, 0.66, and respectively), and S3 (77.00%, 73.00%, 0.74, 0.72, respectively). The degree of coincidence between S2 and the histopathological method for differentiating between benign and malignant breast lesions was high (κ = 0.749). The S2 strategy can improve the robustness of the DenseNet201 model in relatively small breast DCE-MRI datasets, and this is a reliable method to increase the Ac of discriminating benign from malignant breast lesions on DCE-MRI.

目的:评价基于CT双期增强图像的不同深度迁移学习(DTL)模型对甲状腺良恶性结节的分类效能.方法:采用相同程序架构和相同数据集对3种DTL模型(VGG19、ResNet50和DenseNet201)的分类诊断效能进行测试和评估.以不同模型在训练集和测试集中的最高预测符合率和在验证集中的符合率、召回率、F1评分和受试者工作特性曲线(ROC)下面积作为评估模型效能的指标.结果:DenseNet201模型获得了最好的训练和测试结果,在训练集和测试集中的最高预测符合率分别为1.00和0.98;VGG19模型用时最长,其在训练集和测试集中的预测符合率分别为0.99和0.98,较DenseNet201略差;ResNet50模型用时最短,但测试结果最差,在训练集和测试集中的最高符合率分别为0.93和0.92.VGG19、ResNet50和DenseNet201模型在验证集中的平均符合率为0.96、0.92和0.98),召回率分别为0.96、0.91和0.98,F1评分分别为0.96、0.91和0.98.DenseNet201模型的ROC曲线下面积为0.98,高于VGG19模型(0.95)和ResNet50模型(0.91).结论:基于DenseNet201的DTL模型对甲状腺CT良恶性结节具有较高的分类效能,有助于提高影像诊断准确性.