Cervical nucleus segmentation is a crucial and challenging issue in automatic pathological diagnosis due to uneven staining, blurry boundaries, and adherent or overlapping nuclei in nucleus images. To overcome the limitation of current methods, we propose a multi-task network based on U-Net for cervical nucleus segmentation. This network consists of a primary task and an auxiliary task. The primary task is employed to predict nuclei regions. The auxiliary task, which predicts the boundaries of nuclei, is designed to improve the feature extraction of the main task. Furthermore, a context encoding layer is added behind each encoding layer of the U-Net. The output of each context encoding layer is processed by an attention learning module and then fused with the features of the decoding layer. In addition, a codec block is used in the attention learning module to obtain saliency-based attention and focused attention simultaneously. Experiment results show that the proposed network performs better than the state-of-the-art methods on the 2014 ISBI dataset, BNS, MoNuSeg, and our nucluesSeg dataset.

Cervical cell classification is a crucial technique for automatic screening of cervical cancer. Although deep learning has greatly improved the accuracy of cell classification, the performance still cannot meet the needs of practical applications. To solve this problem, we propose a multi-task feature fusion model that consists of one auxiliary task of manual feature fitting and two main classification tasks. The auxiliary task enhances the main tasks in a manner of low-layer feature fusion. The main tasks, i.e., a 2-class classification task and a 5-class classification task, are learned together to realize their mutual reinforcement and alleviate the influence of unreliable labels. In addition, a label smoothing method based on cell category similarity is designed to bring inter-cell class information into the label. Comparative experimental results with other state-of-the-art models on the HUSTC and SIPaKMeD datasets prove the effectiveness of the proposed method. With a high sensitivity of 99.82% and a specificity of 98.12% for the 2-class classification task on the HUSTC dataset, our method shows potential to reduce cytologist workload.

The segmentation of cervical cell in liquid-based smear image plays an important role in cervical cancer detection. Despite of research for many years, it is still a challenge for the complexity of cell images such as poor contrast, cell irregularity, and overlapping. To solve this problem, a novel method is proposed based on Cell-GAN - a generative adversarial network. Firstly, the Cell-GAN is trained to learn a probability distribution of cell morphology by comparing the difference between the generated single-cell images and annotated single-cell images. Thus, the Cell-GAN has the ability to judge the integrity of a cell and treat other cellular information of a cell image, except for overlapping parts, as the background. Then, a complete single-cell image is generated by the trained Cell-GAN for each cell, which is located by a guide factor. The guide factor is constructed by a part of the cell to be segmented, such as the nucleus, to help Cell-GAN locate the cell and avoid generating a multi-cell image in the presence of overlapping, which means the contours of cells still cannot be distinguished. Finally, the segmentation line is defined by the contour of the generated cell, and the input image is cropped using the cell size information. The cropped image is reused for image generation until the area of generated cell varies within a small range.The proposed method is evaluated on the segmentation of single-cell images and overlapping cell images and obtained significant values of 94.3% DC, 7.9% FNR _o for single-cell images and 89.9% DC, 6.4% FNR _o for overlapping cell images respectively. The experimental results indicate that the proposed method can adaptively approach the boundary lines of cells to handle with different cases of overlapping in cervical cell images through what learned by the Cell-GAN. The proposed method outperforms most current methods in both segmentation accuracy and robustness.

In cervical cancer screening, accurate segmentation of cervical nucleus is a key part in the early diagnosis of cervical cancer. However, the cervical nucleus segmentation faces many great challenges owing to the overlapping cervical cells, uneven staining and poor contrast of cervical cytology smear images. In this paper, a tree domain structure and screening algorithm based on depth-first searching strategy are proposed to obtain candidate nucleus regions according to the annular clustering characteristics of nucleus depth information in cervical cytology images. Then, the candidate nucleus regions are finely segmented with an iterative level set algorithm based on adaptive radius morphological dilation. Experimental results are evaluated on the ISBI2015 public dataset. The performance of the proposed nucleus segmentation algorithm is higher than that of the state-of-the-art methods in terms of positive predictive value, negative predictive value, precision, recall of the cervical nucleus segmentation.

Emotion-cause pair extraction (ECPE), which aims to extract emotions and the corresponding causes in documents, has a wide range of applications in network public opinion analysis. Current two-stage methods first extract emotion and cause clauses, and then pair them. However, there are two problems in these methods: 1) the unidirectional enhancement between emotion and cause extraction fails to make full use of the correlation between them; 2) the errors from the first stage directly degrade the performance of the second stage. To address these problems, we firstly propose a mutually auxiliary multitask model to promote the extraction of emotion and cause clauses by adding two auxiliary tasks which are identical to the original tasks. The proposed model uses the predicted results generated by the two auxiliary tasks as extra features of each other’s main tasks, so as to establish the bidirectional correlation between emotion and cause extraction. Secondly, to reduce the influence of error propagation on the second stage, we design a self-distillation method for pairwise tasks to train the proposed model, which further improve the accuracy of emotion and cause extraction. Experimental results on the ECPE benchmark dataset show that the proposed model has achieved good performance on emotion-cause pair extraction, outperforming the baseline models by 1.92% in F1 score.