Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (6): 1856-1862.DOI: 10.11772/j.issn.1001-9081.2019101863

• Frontier & interdisciplinary applications • Previous Articles    

Hierarchical segmentation of pathological images based on self-supervised learning

WU Chongshu1,2, LIN Lin3, XUE Yunjing3, SHI Peng1,2   

  1. 1. College of Mathematics and Informatics, Fujian Normal University, Fuzhou Fujian 350117, China
    2. Digit Fujian Internet-of-Things Laboratory of Environmental Monitoring (Fujian Normal University), Fuzhou Fujian 350117, China
    3. Radiology Department, Fujian Medical University Union Hospital, Fuzhou Fujian 350001, China
  • Received:2019-10-31 Revised:2020-01-17 Online:2020-06-10 Published:2020-06-18
  • Contact: SHI Peng, born in 1980, Ph. D., associate professor. His research interests include pattern recognition, medical image processing, artificial intelligence, machine learning.
  • About author:WU Chongshu, born in 1996, M. S. candidate. His research interests include medical image processing, machine learning.LIN Lin, born in 1988, Ph. D. candidate, chief physician. His research interests include central neuroradiology, radiomics, artificial intelligence, molecular imaging.XUE Yunjing, born in 1971, Ph. D., professor. Her research interests include central nervous imaging, cardiovascular imaging, artificial intelligence.SHI Peng, born in 1980, Ph. D., associate professor. His research interests include pattern recognition, medical image processing, artificial intelligence, machine learning.
  • Supported by:
    National Natural Science Foundation of China (61672157), the Science and Technology Innovation Joint Foundation of Fujian Province (2018Y9112,2018Y9044), the Development Program of Young and Middle-aged Talents of Health of Fujian Province (2019-ZQN-17).


吴崇数1,2, 林霖3, 薛蕴菁3, 时鹏1,2   

  1. 1.福建师范大学 数学与信息学院,福州 350117
    2.数字福建环境监测物联网实验室(福建师范大学),福州 350117
    3.福建医科大学附属协和医院 放射科,福州 350001
  • 通讯作者: 时鹏(1980—)
  • 作者简介:吴崇数(1996—),男,浙江瑞安人,硕士研究生,主要研究方向:医学图像处理、机器学习.林霖(1988—),男,福建泉州人,主治医师,博士研究生,主要研究方向:中枢神经放射学、影像组学、人工智能、分子影像.薛蕴菁(1971—),女,浙江江阴人,教授,博士,主要研究方向:中枢神经影像、心血管影像、人工智能.时鹏(1980—),男,河南许昌人,副教授,博士,CCF会员,主要研究方向:模式识别、医学图像处理、人工智能、机器学习
  • 基金资助:

Abstract: The uneven distribution of cell staining and the diversity of tissue morphologies bring challenges to the automatic segmentation of Hematoxylin-Eosin (HE) stained pathological images. In order to solve the problem, a three-step hierarchical segmentation method of pathological images based on self-supervised learning was proposed to automatically segment the tissues in the pathological images layer-by-layer from coarse to fine. Firstly, feature selection was performed in the RGB color space based on the calculation result of mutual information. Secondly, the image was initially segmented into stable and fuzzy color regions of each tissue structure based on K-means clustering. Thirdly, the stable color regions were taken as training datasets for further segmentation of fuzzy color regions by naive Bayesian classification, and the three complete tissue structures including nucleus, cytoplasm and extracellular space were obtained. Finally, precise boundaries between nuclei were obtained by performing the mixed watershed classification considering both shape and color intensities to the nucleus part, so as to quantitatively calculate the indicators such as the number of nuclei, nucleus proportion, and nucleus-cytoplasm ratio. Experimental results of HE stained meningioma pathological image segmentation show that, the proposed method is highly robust to the difference of staining and cell morphologies, the error of issue area segmentation is within 5%, and the average accuracy of the proposed method in nucleus segmentation accuracy experiment is above 96%, which means that the proposed method can meet the requirements of automatic analysis of clinical images and its quantitative results can provide references for quantitative pathological analysis.

Key words: pathological image, image segmentation, self-supervised learning, K-means clustering, naive Bayesian classification

摘要: 在苏木精-伊红(HE)染色病理图像中,细胞染色分布的不均匀和各类组织形态的多样性给病理图像的自动分割带来极大挑战。为解决该问题,提出了一种基于自监督学习的病理图像三步层次分割方法,对病理图像中各类组织进行由粗略到精细的全自动逐层分割。首先,根据互信息的计算结果在RGB色彩空间中进行特征选择;其次,采用K-means聚类将图像初步分割为各类组织结构的色彩稳定区域与模糊区域;然后,以色彩稳定区域为训练集采用朴素贝叶斯分类对模糊区域进行进一步分割,得到完整的细胞核、细胞质和胞外间隙这三类组织结构;最后,对细胞核部分进行结合形状和色彩强度的混合分水岭分割得到细胞核间的精确边界,进而量化计算细胞核个数、核占比、核质比等指标。对脑膜瘤HE染色病理图像的分割实验结果表明,所提方法对于染色和细胞形态差异保持较高的鲁棒性,各类组织区域分割误差在5%以内,在细胞核分割精度的对比实验中平均正确率在96%以上,满足临床自动图像分析的要求,其量化结果可以为定量病理分析提供依据。

关键词: 病理图像, 图像分割, 自监督学习, K-means聚类, 朴素贝叶斯分类

CLC Number: