An Accurate Nuclei Segmentation Algorithm in Pathological Image Based on Deep Semantic Network
An Accurate Nuclei Segmentation Algorithm in Pathological Image Based on Deep Semantic Network
复制标题
一种基于深度语义网络的病理图像细胞核精确分割算法
DOI：
10.1109/access.2019.2934486
复制
发表时间：
2019-01-01
期刊：
影响因子：
3.9
通讯作者：
Yang, Huihua
中科院分区：
文献类型：
--
作者：
Pan, Xipeng;Li, Lingqiao;Yang, Huihua
细胞（核）分割是病理图像分析的基础和关键步骤。然而，由于染色、细胞大小、形态和细胞粘附或重叠的巨大变化，稳健且准确的细胞（细胞核）分割是一个难题。在本文中，我们使用带孔深度可分离卷积（AS-UNet）扩展 U-Net，用于细胞（细胞核）分割。 AS-UNet由三部分组成：编码器模块、解码器模块和空洞卷积模块。编码器模块逐层获取细胞图像的高层语义信息，而解码器模块逐渐恢复空间信息。空洞卷积模块由级联和并行空洞卷积运算组成。它可以提取并组合多尺度特征，使模型对小细胞和大细胞都具有较强的感知能力。同时，空洞卷积可以显着增加网络模型的感受野，而不会损害分割性能或增加计算成本。训练期间，结合Log-Dice损失和Focal损失，同时采用Adam优化方法来优化网络。为了增加对Dice系数较小的预测结果的惩罚，将其进行对数运算，将负值作为Log-Dice损失。上述优化有利于收敛速度。此外，还应用了一些数据增强技术来增加在线数据，这有助于提高模型的鲁棒性。与几种最先进的语义分割算法相比，我们的方法在两个最新发布的病理图像数据集上实现了有希望的性能。
Cell (nuclei) segmentation is the basic and key step of pathological image analysis. However, robust and accurate cell (nuclei) segmentation is a difficult problem due to the enormous variability of staining, cell sizes, morphologies and cell adhesion or overlapping. In this paper, we extend U-Net with atrous depthwise separable convolution (AS-UNet) for cell (nuclei) segmentation. AS-UNet consists of three parts: encoder module, decoder module and atrous convolution module. The encoder module obtains the high-level semantic information of the cell image layer by layer, while the decoder module gradually recovers the spatial information. The atrous convolution module is composed of cascade and parallel atrous convolution operations. It can extract and combine multi-scale features so that the model can get strong perception ability for both small and large cells. At the same time, the atrous convolution can significantly increase the receptive field of the network model without hurting the segmentation performance or increasing the computational cost. During the training period, Log-Dice loss and Focal loss are combined, while Adam optimization method is employed to optimize the network. In order to increase the penalty for the smaller prediction result of the Dice coefficient, which is carried out by logarithmic operation and the negative value is taken as the Log-Dice loss. The above optimization is beneficial for the convergence speed. Additionally, some data augmentation techniques are applied to increase online data, which contribute to improving the robustness of the model. Compared with several state-of-the-art semantic segmentation algorithms, our method achieves the promising performance on two latest released pathological image datasets.