Automatic Segmentation of Cervical Nuclei Based on Deep learning and a Conditional Random Field
Automatic Segmentation of Cervical Nuclei Based on Deep learning and a Conditional Random Field
复制标题
DOI：
10.1109/access.2018.2871153
复制
发表时间：
2018-01-01
期刊：
影响因子：
3.9
通讯作者：
Gui, Zhiguo
中科院分区：
文献类型：
--
作者：
Liu, Yiming;Zhang, Pengcheng;Gui, Zhiguo
自动且准确的宫颈细胞核分割是重要的，因为细胞核携带用于自动计算机辅助宫颈癌筛查和诊断系统的大量诊断信息。本文提出了一种颈髓核分割方法，利用像素级先验信息为训练掩码区域卷积神经网络（Mask-RCNN）提供监督信息，然后利用该网络提取核的多尺度特征，通过Mask-RCNN的前向传播得到核的粗分割和边界框。为了改进分割，采用了包含一元和成对能量项的局部全连接条件随机场（LFCCRF）。通过扩展包围盒确定感兴趣的核区域，利用核区域中的粗分割构造一元能量，利用核区域中所有像素的位置和强度信息来贡献成对能量。通过最小化LFCCRF的能量，实现最终的分割。我们使用本文中的Herlev巴氏涂片数据集的颈核来评估我们的方法，并且发现精确度、召回率和Zijdenbos相似性指数都大于0.95，标准差较低，表明我们的方法比当前最先进的方法能够更准确和稳定地分割颈核。
Automatic and accurate cervical nucleus segmentation is important because nuclei carry substantial diagnostic information for automatic computer-assisted cervical cancer screening and diagnosis systems. In this paper, we propose a cervical nucleus segmentation method in which pixel-level prior information is utilized to provide the supervisory information for the training of a mask regional convolutional neural network (Mask-RCNN), which is then employed to extract the multi-scale features of the nuclei, and the coarse segmentation and bounding box of the nuclei are obtained by forward propagation of the Mask-RCNN. To refine the segmentation, a local fully connected conditional random field (LFCCRF) that contains unary and pairwise energy terms is employed. The nuclear region of interest is determined by extending the bounding box, the coarse segmentation in the nuclear region is used to construct the unary energy, and the pairwise energy is contributed by the position and intensity information of all of the pixels in the nuclear region. By minimizing the energy of the LFCCRF, the final segmentation is realized. We evaluated our method by using cervical nuclei from the Herlev Pap smear data set in this paper, and the precision, recall, and Zijdenbos similarity index were all found to be greater than 0.95 with low standard deviations, demonstrating that our method enables more accurate and stable cervical nucleus segmentation than the current state-of-the-art methods.