An important indicator of cervical cancer diagnosis is to calculate the proportion of diseased cells and cancer cells, so it is necessary to segment cells and judge the cell status. The existing methods are difficult to deal with the segmentation of overlapping cells. In order to solve this problem, we put forward such a hypothesis by reading a large number of literature, that is, image segmentation and edge measurement tasks have unity in high-level features. To prove this hypothesis, in this paper, we focus on the complementary between overlapping cervical cell edge information and cell object information to get higher accuracy cell edge detection results. Specifically, we present a joint multi-task learning framework for overlapping cell edge detection by the mask guidance pyramid network. The main component of the framework is the Mask Guidance Module (MGM), which integrates two tasks and stores the shared latent semantics to interact in the two tasks. For semantic edge detection, we propose the novel Refinement Aggregated Module (RAM) fusion to promote semantic edges. Finally, to improve the edge pixel accuracy, the edge consistency constraint loss function is introduced to our model training. Our extensive experiments have proved that our method outperforms other edge detection efforts.

In this paper, we apply kernel methods to deep convolutional neural network (DCNN) to improve its nonlinear ability. DCNNs have achieved significant improvement in many computer vision tasks. For an image classification task, the accuracy comes to saturation when the depth and width of network are enough and appropriate. The saturation accuracy will not rise even by increasing the depth and width. We find that improving nonlinear ability of DCNNs can break through the saturation accuracy. In a DCNN, the former layer is more inclined to extract features and the latter layer is more inclined to classify features. Therefore, we apply kernel methods at the last fully connected layer to implicitly map features to a higher-dimensional space to improve nonlinear ability so that the network achieves better linear separability. Also, we name the network as fully kernected neural networks (fully connected neural networks with kernel methods). Our experiment result shows that fully kernected neural networks achieve higher classification accuracy and faster convergence rate than baseline networks.