To determine the feasibility of using a deep learning (DL) approach to identify benign and malignant BI-RADS 4 lesions with preoperative breast DCE-MRI images and compare two 3D segmentation methods. The patients admitted from January 2014 to October 2020 were retrospectively analyzed. Breast MRI examination was performed before surgical resection or biopsy, and the masses were classified as BI-RADS 4. The first postcontrast images of DCE-MRI T1WI sequence were selected. There were two 3D segmentation methods for the lesions, one was manual segmentation along the edge of the lesion slice by slice, and the other was the minimum bounding cube of the lesion. Then, DL feature extraction was carried out; the pixel values of the image data are normalized to 0-1 range. The model was established based on the blueprint of the classic residual network ResNet50, retaining its residual module and improved 2D convolution module to 3D. At the same time, an attention mechanism was added to transform the attention mechanism module, which only fit the 2D image convolution module, into a 3D-Convolutional Block Attention Module (CBAM) to adapt to 3D-MRI. After the last CBAM, the algorithm stretches the output high-dimensional features into a one-dimensional vector and connects 2 fully connected slices, before finally setting two output results (P1, P2), which, respectively, represent the probability of benign and malignant lesions. Accuracy, sensitivity, specificity, negative predictive value, positive predictive value, the recall rate and area under the ROC curve (AUC) were used as evaluation indicators. A total of 203 patients were enrolled, with 207 mass lesions including 101 benign lesions and 106 malignant lesions. The data set was divided into the training set (), the validation set (), and the test set () at the ratio of 7 : 1 : 2; fivefold cross-validation was performed. The mean AUC based on the minimum bounding cube of lesion and the 3D-ROI of lesion itself were 0.827 and 0.799, the accuracy was 78.54% and 74.63%, the sensitivity was 78.85% and 83.65%, the specificity was 78.22% and 65.35%, the NPV was 78.85% and 71.31%, the PPV was 78.22% and 79.52%, the recall rate was 78.85% and 83.65%, respectively. There was no statistical difference in AUC based on the lesion itself model and the minimum bounding cube model (, ). The minimum bounding cube based on the edge of the lesion showed higher accuracy, specificity, and lower recall rate in identifying benign and malignant lesions. Based on the lesion 3D-ROI segmentation using a minimum bounding cube can more effectively reflect the information of the lesion itself and the surrounding tissues. Its DL model performs better than the lesion itself. Using the DL approach with a 3D attention mechanism based on ResNet50 to identify benign and malignant BI-RADS 4 lesions was feasible.

中文翻译：

---

使用改进的卷积神经网络对 BI-RADS 进行分类的可行性 4 乳腺病变：比较病变本身的深度学习特征和病变的最小边界立方

确定使用深度学习 (DL) 方法通过术前乳房 DCE-MRI 图像识别良恶性 BI-RADS 4 病变的可行性，并比较两种 3D 分割方法。对2014年1月至2020年10月收治的患者进行回顾性分析。手术切除或活检前行乳腺MRI检查，肿块分级为BI-RADS 4级。选取DCE-MRI T1WI序列的第一张增强后图像。病灶的3D分割方法有两种，一种是沿病灶边缘逐片手动分割，另一种是病灶最小边界立方。然后，进行DL特征提取；图像数据的像素值归一化为 0-1 范围。该模型基于经典残差网络ResNet50的蓝图建立，保留其残差模块并将2D卷积模块改进为3D。同时加入了attention机制，将只适合2D图像卷积模块的attention机制模块转化为3D-Convolutional Block Attention Module（CBAM），以适应3D-MRI。最后一次CBAM之后，算法将输出的高维特征拉伸成一维向量，连接2个全连接切片，最后设置两个输出结果（P1，P2），分别代表良恶性概率病变。以准确率、敏感性、特异性、阴性预测值、阳性预测值、召回率和ROC曲线下面积（AUC）为评价指标。共纳入203例患者，其中包块病变207个，其中良性病变101个，恶性病变106个。将数据集划分为训练集（），验证集（)和测试集 ()的比例为 7 : 1 : 2; 进行了五重交叉验证。基于病灶最小边界立方和病灶本身3D-ROI的平均AUC分别为0.827和0.799，准确度分别为78.54%和74.63%，敏感性为78.85%和83.65%，特异性为78.22%和65.35%。 ，NPV分别为78.85%和71.31%，PPV分别为78.22%和79.52%，召回率分别为78.85%和83.65%。基于病变本身模型和最小边界立方模型的AUC没有统计学差异（, ）。基于病变边缘的最小边界立方体在识别良恶性病变方面表现出更高的准确性、特异性和更低的召回率。基于病灶的3D-ROI分割使用最小边界立方体可以更有效地反映病灶本身和周围组织的信息。它的 DL 模型比病变本身表现更好。使用具有基于 ResNet50 的 3D 注意机制的 DL 方法来识别良性和恶性 BI-RADS 4 病变是可行的。