Breast cancer has high incidences and mortality rates in women worldwide. Malignancy could be detected manually by experienced pathologists based on Hematoxylin and Eosin (H&E) stained images. However, it is time-consuming and experience-dependent, making early diagnosis a big challenge. In this paper, a methodology for breast cancer classification based on histopathological images with deep learning was described. A residual learning-based convolutional neural network named myResNet-34 was designed for malignancy-and-benign classification. In addition, an algorithm automatically generating the target image for stain normalization was proposed, which eliminated the bias caused by manual selection of the reference image. Elastic distortion was introduced and combined with affine transformation for data augmentation considering the characteristics of the H&E images. Experiments were conducted on BreakHis dataset with the proposed framework. Promising results were achieved with an average classification accuracy of around 91% on image-level classification. Results indicated that both our data augmentation and stain normalization effectively improved the classification accuracy by 2-3%.

中文翻译：

---

基于深度残差学习的乳腺癌组织病理图像分类

乳腺癌在全世界女性中的发病率和死亡率都很高。经验丰富的病理学家可以根据苏木精和曙红 (H&E) 染色图像手动检测恶性肿瘤。然而，它耗时且依赖经验，使得早期诊断成为一大挑战。在本文中，描述了一种基于深度学习的组织病理学图像的乳腺癌分类方法。一个名为 myResNet-34 的基于残差学习的卷积神经网络被设计用于恶性和良性分类。此外，提出了一种自动生成污点归一化目标图像的算法，消除了人工选择参考图像造成的偏差。考虑到 H&E 图像的特性，引入弹性失真并结合仿射变换进行数据增强。使用建议的框架在 BreakHis 数据集上进行了实验。取得了有希望的结果，图像级分类的平均分类准确率约为 91%。结果表明，我们的数据增强和染色归一化都有效地将分类准确度提高了 2-3%。