School of Computer Science, Zhongyuan University of Technology, Zhengzhou 450007, China.
School of Information Engineering, Zhengzhou University, Zhengzhou 450001, China.
J Healthc Eng. 2020 Dec 22;2020:8860011. doi: 10.1155/2020/8860011. eCollection 2020.
Prompt diagnosis of benign and malignant breast masses is essential for early breast cancer screening. Convolutional neural networks (CNNs) can be used to assist in the classification of benign and malignant breast masses. A persistent problem in current mammography mass classification via CNN is the lack of local-invariant features, which cannot effectively respond to geometric image transformations or changes caused by imaging angles. In this study, a novel model that trains both texton representation and deep CNN representation for mass classification tasks is proposed. Rotation-invariant features provided by the maximum response filter bank are incorporated with the CNN-based classification. The fusion after implementing the reduction approach is used to address the deficiencies of CNN in extracting mass features. This model is tested on public datasets, CBIS-DDSM, and a combined dataset, namely, mini-MIAS and INbreast. The fusion after implementing the reduction approach on the CBIS-DDSM dataset outperforms that of the other models in terms of area under the receiver operating curve (0.97), accuracy (94.30%), and specificity (97.19%). Therefore, our proposed method can be integrated with computer-aided diagnosis systems to achieve precise screening of breast masses.
对乳腺良恶性肿块进行准确诊断是早期乳腺癌筛查的关键。卷积神经网络（CNN）可用于辅助乳腺良恶性肿块的分类。目前，通过 CNN 对乳腺钼靶肿块进行分类的一个突出问题是缺乏局部不变特征，无法有效应对几何图像变换或成像角度变化。在这项研究中，提出了一种用于肿块分类任务的新型模型，该模型同时训练纹理特征和深度 CNN 表示。最大响应滤波器组提供的旋转不变特征与基于 CNN 的分类相结合。在实施降维方法后进行融合，以解决 CNN 在提取肿块特征方面的不足。该模型在公共数据集 CBIS-DDSM 以及 mini-MIAS 和 INbreast 联合数据集上进行了测试。在 CBIS-DDSM 数据集上实施降维方法后的融合在接收者操作曲线下面积（0.97）、准确性（94.30%）和特异性（97.19%）方面均优于其他模型。因此，我们提出的方法可以与计算机辅助诊断系统集成，实现对乳腺肿块的精确筛查。
