Accurate Segmentation of Cervical Cytoplasm and Nuclei Based on Multiscale Convolutional Network and Graph Partitioning

• Published in: IEEE transactions on biomedical engineering 2015-10, Vol.62 (10), p.2421-2433
• Main Authors: Song, Youyi, Zhang, Ling, Chen, Siping, Ni, Dong, Lei, Baiying, Wang, Tianfu
• Format: Article
• Language: English
• Subjects: Cell Nucleus - chemistry; Cervical segmentation; Cervix Uteri - cytology; Cervix Uteri - pathology; coarse to fine; Computer architecture; Cytoplasm - chemistry; Feature extraction; Female; graph-partitioning; Histocytochemistry; Humans; Image color analysis; Image edge detection; Image Processing, Computer-Assisted - methods; Image segmentation; Microprocessors; Microscopy; multi-scale convolutional network; Shape; touching-cell splitting
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2015.2430895

In this paper, a multiscale convolutional network (MSCN) and graph-partitioning-based method is proposed for accurate segmentation of cervical cytoplasm and nuclei. Specifically, deep learning via the MSCN is explored to extract scale invariant features, and then, segment regions centered at each pixel. The coarse segmentation is refined by an automated graph partitioning method based on the pretrained feature. The texture, shape, and contextual information of the target objects are learned to localize the appearance of distinctive boundary, which is also explored to generate markers to split the touching nuclei. For further refinement of the segmentation, a coarse-to-fine nucleus segmentation framework is developed. The computational complexity of the segmentation is reduced by using superpixel instead of raw pixels. Extensive experimental results demonstrate that the proposed cervical nucleus cell segmentation delivers promising results and outperforms existing methods.