School of Information and Communications Engineering, Xi'an Jiaotong University, Xi'an, 710049, Shaanxi, People's Republic of China.
Department of Radiology, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, Guangdong, People's Republic of China.
Phys Med Biol. 2023 Sep 1;68(17). doi: 10.1088/1361-6560/acf092.
Classification of benign and malignant tumors is important for the early diagnosis of breast cancer. Over the last decade, digital breast tomosynthesis (DBT) has gradually become an effective imaging modality for breast cancer diagnosis due to its ability to generate three-dimensional (3D) visualizations. However, computer-aided diagnosis (CAD) systems based on 3D images require high computational costs and time. Furthermore, there is considerable redundant information in 3D images. Most CAD systems are designed based on 2D images, which may lose the spatial depth information of tumors. In this study, we propose a 2D/3D integrated network for the diagnosis of benign and malignant breast tumors.We introduce a correlation strategy to describe feature correlations between slices in 3D volumes, corresponding to the tissue relationship and spatial depth features of tumors. The correlation strategy can be used to extract spatial features with little computational cost. In the prediction stage, 3D spatial correlation features and 2D features are both used for classification.Experimental results demonstrate that our proposed framework achieves higher accuracy and reliability than pure 2D or 3D models. Our framework has a high area under the curve of 0.88 and accuracy of 0.82. The parameter size of the feature extractor in our framework is only 35% of that of the 3D models. In reliability evaluations, our proposed model is more reliable than pure 2D or 3D models because of its effective and nonredundant features.This study successfully combines 3D spatial correlation features and 2D features for the diagnosis of benign and malignant breast tumors in DBT. In addition to high accuracy and low computational cost, our model is more reliable and can output uncertainty value. From this point of view, the proposed method has the potential to be applied in clinic.
良性和恶性肿瘤的分类对于乳腺癌的早期诊断非常重要。在过去的十年中，数字乳腺断层合成术（DBT）由于能够生成三维（3D）可视化图像，已逐渐成为一种有效的乳腺癌诊断成像方式。然而，基于 3D 图像的计算机辅助诊断（CAD）系统需要较高的计算成本和时间。此外，3D 图像中存在大量冗余信息。大多数 CAD 系统是基于 2D 图像设计的，这可能会丢失肿瘤的空间深度信息。在本研究中，我们提出了一种用于诊断良性和恶性乳腺肿瘤的 2D/3D 集成网络。我们引入了一种相关策略来描述 3D 体积中切片之间的特征相关性，这对应于肿瘤的组织关系和空间深度特征。该相关策略可以用于以较低的计算成本提取空间特征。在预测阶段，同时使用 3D 空间相关特征和 2D 特征进行分类。实验结果表明，与纯 2D 或 3D 模型相比，我们提出的框架具有更高的准确性和可靠性。我们的框架的曲线下面积为 0.88，准确率为 0.82。我们的框架中的特征提取器的参数大小仅为 3D 模型的 35%。在可靠性评估中，由于其有效且非冗余的特征，我们提出的模型比纯 2D 或 3D 模型更可靠。本研究成功地将 3D 空间相关特征和 2D 特征结合起来，用于 DBT 中良性和恶性乳腺肿瘤的诊断。除了具有较高的准确性和较低的计算成本外，我们的模型更可靠，并且可以输出不确定性值。从这一点来看，所提出的方法具有在临床上应用的潜力。
