论文标题
Convoher2：HER2乳腺癌多阶段分类的深神经网络
convoHER2: A Deep Neural Network for Multi-Stage Classification of HER2 Breast Cancer
论文作者
论文摘要
通常，人表皮生长因子2（HER2）乳腺癌比其他类型的乳腺癌更具侵略性。目前，使用昂贵的医疗测试检测到HER2乳腺癌是最昂贵的。因此，这项研究的目的是开发一种名为Convoher2的计算模型，用于使用卷积神经网络（CNN）检测使用图像数据的HER2乳腺癌。苏木精和曙红（H＆E）以及免疫组织化学（IHC）染色图像已被用作贝叶斯信息标准（BIC）基准数据集的原始数据。该数据集由H＆E和IHC的4873张图像组成。在数据集的所有图像中，分别应用3896和977图像来训练和测试Convoher2模型。由于所有图像都处于高分辨率，因此我们调整了它们的大小，以便我们可以在Convoher2模型中喂食它们。根据癌症的阶段（0+，1+，2+，3+）将癌性样品图像分为四类。 Convoher2模型能够分别使用H＆E图像和IHC图像，以85％和88％的精度检测HER2癌症及其等级。这项研究的结果确定，Concoher2模型的HER2癌症检测率足以为患者提供更好的诊断，以便将来恢复其HER2乳腺癌。
Generally, human epidermal growth factor 2 (HER2) breast cancer is more aggressive than other kinds of breast cancer. Currently, HER2 breast cancer is detected using expensive medical tests are most expensive. Therefore, the aim of this study was to develop a computational model named convoHER2 for detecting HER2 breast cancer with image data using convolution neural network (CNN). Hematoxylin and eosin (H&E) and immunohistochemical (IHC) stained images has been used as raw data from the Bayesian information criterion (BIC) benchmark dataset. This dataset consists of 4873 images of H&E and IHC. Among all images of the dataset, 3896 and 977 images are applied to train and test the convoHER2 model, respectively. As all the images are in high resolution, we resize them so that we can feed them in our convoHER2 model. The cancerous samples images are classified into four classes based on the stage of the cancer (0+, 1+, 2+, 3+). The convoHER2 model is able to detect HER2 cancer and its grade with accuracy 85% and 88% using H&E images and IHC images, respectively. The outcomes of this study determined that the HER2 cancer detecting rates of the convoHER2 model are much enough to provide better diagnosis to the patient for recovering their HER2 breast cancer in future.
