为实现宫颈液基细胞图像中异常细胞核的准确分割,提出一种新的自适应局部细胞核分割方法。在自适应阶段,采用一种利用灰度和纹理信息的快速自适应阈值算法大致检测出细胞核区域;在局部阶段,对每一个粗分割得到的连通区域,在其局部邻域内,使用一种利用边界和区域信息的、基于泊松概率分布的图割法修正分割结果。将此方法用于苏木素&伊红染色的宫颈液基细胞图像,结果显示,本文方法的平均计算时间为1.6 s/幅,且比2012年Li等人提出的宫颈细胞分割方法在细胞核检测率、和异常细胞核分割精度上均提高了19.7%。

For accurate segmentation of abnormal nuclei in liquid-based cervical cell images, a new nuclei segmentation method is proposed, which uses adaptive and local strategies. The adaptive stage detects each nucleus region approximately by applying an efficient adaptive thresholding algorithm that uses intensity and texture information. The local stage refines each coarse segment within its local neighborhood by using a Poisson distribution based graph cuts, which utilizes boundary and region information. The proposed method is applied to Hematoxylin & Eosin stained liquid-based cervical cell images. The results show that the proposed method achieves a speed of 1.6 s per image, and significantly outperforms a state-of-the-art method by Li et al in 2012 in terms of nuclei detection rate and abnormal nuclei segmentation accuracy, both with a 19.7% improvement.