Pathological Image Classification Based on Hard Example Guided CNN
Pathological Image Classification Based on Hard Example Guided CNN
复制标题
DOI：
10.1109/access.2020.3003070
复制
发表时间：
2020
期刊：
影响因子：
3.9
通讯作者：
Ying Wang;T. Peng;Jiajia Duan;Chuang Zhu;Jun Liu;Jiandong Ye;M. Jin
中科院分区：
文献类型：
--
作者：
Ying Wang;T. Peng;Jiajia Duan;Chuang Zhu;Jun Liu;Jiandong Ye;M. Jin
病理学家广泛使用苏木精和伊红 (H&E) 染色图像对活检组织进行诊断，以检测病变并评估恶性肿瘤。然而，诊断结果依赖于病理学家的目视观察，在不同情况下，诊断结果可能因人而异。凭借在多个抽象层次上自动自适应学习特征的优势，卷积神经网络（CNN）已迅速成为病理图像分析的有前途的替代方案。因此，在本文中，我们提出了一种有效的肿瘤分类方法，称为 Hard Examples Guided CNN。我们的贡献是双重的：首先，为了优化图像表示，我们将 CNN 架构设计为双分支，用于同时提取全局特征和局部特征。其次，我们提出了一种重新权重训练算法，通过增加困难示例的权重来提高学习精度并加速收敛。对多个数据集的大量实验证明了我们提出的分类方法的优越性。
The diagnosis of biopsy tissue with hematoxylin and eosin (H&E) stained images has been widely used by pathologists to detect the lesions and assess the malignancy. Nevertheless, the diagnostic result relies on the visual observation of pathologists which may vary from person to person under different circumstances. With the advantage of automatically and adaptively learning features at multiple levels of abstraction, Convolutional Neural Networks (CNNs) have rapidly become promising alternatives for pathological image analysis. Therefore, in this paper, we propose an effective method for tumor classification called Hard Example Guided CNN. Our contribution is twofold: firstly, to optimize image representation, we design the CNN architecture as dual-branch, used for extracting global features and local features simultaneously. Secondly, we propose a re-weight training algorithm, which improves learning accuracy and accelerates the convergence by increasing the weight of hard examples. Extensive experiments on multiple datasets demonstrate the superiority of our proposed classification method.