Li Siqi, Jiang Huiyan, Pang Wenbo
Software College, Northeastern University, Shenyang 110819, China.
Comput Biol Med. 2017 May 1;84:156-167. doi: 10.1016/j.compbiomed.2017.03.017. Epub 2017 Mar 22.
Accurate cell grading of cancerous tissue pathological image is of great importance in medical diagnosis and treatment. This paper proposes a joint multiple fully connected convolutional neural network with extreme learning machine (MFC-CNN-ELM) architecture for hepatocellular carcinoma (HCC) nuclei grading. First, in preprocessing stage, each grayscale image patch with the fixed size is obtained using center-proliferation segmentation (CPS) method and the corresponding labels are marked under the guidance of three pathologists. Next, a multiple fully connected convolutional neural network (MFC-CNN) is designed to extract the multi-form feature vectors of each input image automatically, which considers multi-scale contextual information of deep layer maps sufficiently. After that, a convolutional neural network extreme learning machine (CNN-ELM) model is proposed to grade HCC nuclei. Finally, a back propagation (BP) algorithm, which contains a new up-sample method, is utilized to train MFC-CNN-ELM architecture. The experiment comparison results demonstrate that our proposed MFC-CNN-ELM has superior performance compared with related works for HCC nuclei grading. Meanwhile, external validation using ICPR 2014 HEp-2 cell dataset shows the good generalization of our MFC-CNN-ELM architecture.
癌组织病理图像的准确细胞分级在医学诊断和治疗中具有重要意义。本文提出了一种用于肝细胞癌（HCC）细胞核分级的联合多重全连接卷积神经网络与极限学习机（MFC-CNN-ELM）架构。首先，在预处理阶段，使用中心增殖分割（CPS）方法获取具有固定大小的每个灰度图像块，并在三位病理学家的指导下标记相应的标签。接下来，设计一个多重全连接卷积神经网络（MFC-CNN）来自动提取每个输入图像的多形式特征向量，该网络充分考虑了深层图的多尺度上下文信息。之后，提出了一种卷积神经网络极限学习机（CNN-ELM）模型对HCC细胞核进行分级。最后，利用一种包含新的上采样方法的反向传播（BP）算法来训练MFC-CNN-ELM架构。实验比较结果表明，我们提出的MFC-CNN-ELM在HCC细胞核分级方面与相关工作相比具有优越的性能。同时，使用ICPR 2014 HEp-2细胞数据集进行的外部验证表明了我们的MFC-CNN-ELM架构具有良好的泛化能力。
