计算机应用 ›› 2018, Vol. 38 ›› Issue (11): 3348-3354.DOI: 10.11772/j.issn.1001-9081.2018050988

• 应用前沿、交叉与综合 • 上一篇    

基于全卷积网络和条件随机场的宫颈癌细胞学图像的细胞核分割

刘一鸣, 张鹏程, 刘祎, 桂志国   

  1. 中北大学 生物医学成像与影像大数据山西省重点实验室, 太原 030051
  • 收稿日期:2018-05-11 修回日期:2018-06-14 出版日期:2018-11-10 发布日期:2018-11-10
  • 通讯作者: 桂志国
  • 作者简介:刘一鸣(1994-),男,山西忻州人,硕士研究生,主要研究方向:神经网络、图像处理;张鹏程(1984-),男,内蒙古巴彦淖尔人,讲师,博士,主要研究方向:精准放射治疗剂量计算及方案优化;刘祎(1987-),女,河南睢县人,讲师,博士,主要研究方向:图像处理、图像重建;桂志国(1972-),男,天津蓟县人,教授,博士,主要研究方向:三维CT、医学图像处理与重建、模式识别。
  • 基金资助:
    国家自然科学基金资助项目(61671413,11605160);国家重大科学仪器设备开发专项(2014YQ24044508);山西省回国留学人员科研资助项目(2016-089)。

Segmentation of cervical nuclei based on fully convolutional network and conditional random field

LIU Yiming[Author]) AND 1[Journal]) AND year[Order])" target="_blank">LIU Yiming, ZHANG Pengcheng, LIU Yi, GUI Zhiguo   

  1. Shanxi Provincial Key Laboratory for Biomedical Imaging and Big Data, North University of China, Taiyuan Shanxi 030051, China
  • Received:2018-05-11 Revised:2018-06-14 Online:2018-11-10 Published:2018-11-10
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61671413, 11605160), the National Key Scientific Instrument and Equipment Development Project of China (2014YQ24044508), the Research Project Supported by Shanxi Scholarship Council of China (2016-089).

摘要: 针对宫颈癌细胞学筛查中由于宫颈细胞核形状复杂多样等因素而导致分割不够精确的问题,提出了一种结合了全卷积网络(FCN)和全连接条件随机场(CRF)的细胞核分割方法。首先,根据Herlev数据集的特点搭建微型全卷积网络(T-FCN),利用细胞核区域像素级别的类别先验信息,自主学习多层次特征来获取细胞核的粗分割结果;然后,通过最小化包含有整幅细胞图像中所有像素类别、像素色彩值与位置等信息的全连接CRF的能量函数来剔除粗分割结果中微小的误分割,并细化分割边缘。在Herlev数据集上的实验结果显示,提出的方法在查准率(Precision)、查全率(Recall)与Zijdenbos相似性指数(ZSI)上均有高于0.9的表现,表明得到的细胞核分割结果与其真实轮廓高度匹配,分割精确。相较于传统方法中对异常细胞核的分割精度较正常细胞核低的情况,提出的方法在异常细胞核的分割指标上普遍优于正常细胞核。

关键词: 全卷积网络, 密集条件随机场, 细胞核分割, 巴氏涂片

Abstract: Aiming at the problem of inaccurate cervical nuclei segmentation due to complex and diverse shape in cervical cancer screening, a new method that combined Fully Convolutional Network (FCN) and dense Conditional Random Field (CRF) was proposed for nuclei segmentation. Firstly, a Tiny-FCN (T-FCN) was built according to the characteristics of the Herlev data set. Utilizing the priori information at the pixel level of the nucleus region, the multi-level features were learned autonomously to obtain the rough segmentation of the cell nucleus. Then, the small incorrect segmentation regions in the rough segmentation were eliminated and the segmentation was refined, by minimizing the energy function of the dense CRF that contains the label, intensity and position information of all pixels in a cell image. The experiment results on Herlev Pap smear dataset show that the precision, recall and Zijdenbos Similarity Index (ZSI) are all higher than 0.9, indicating that the nuclei segmentation boundary obtained by the proposed method is matched excellently with the ground truth, and the segmentation is accurate. Compared to the traditional method in which the indexes of segmentation of abnormal nuclei are lower than those of normal nuclei, the segmentation indexes of abnormal nuclei are superior to those of normal nulei by the proposed method.

Key words: Fully Convolutional Network (FCN), Dense Conditional Random Field (DCRF), nuclei segmentation, Pap smear

中图分类号: