计算机应用 ›› 2020, Vol. 40 ›› Issue (5): 1453-1459.DOI: 10.11772/j.issn.1001-9081.2019091683

• 虚拟现实与多媒体计算 • 上一篇    下一篇

基于深度学习的秀丽隐杆线虫显微图像分割方法

曾招鑫1,2, 刘俊1,2   

  1. 1.武汉科技大学 计算机科学与技术学院,武汉 430065
    2.智能信息处理与实时工业系统湖北省重点实验室(武汉科技大学),武汉 430065
  • 收稿日期:2019-10-08 修回日期:2019-11-01 出版日期:2020-05-10 发布日期:2020-05-15
  • 通讯作者: 曾招鑫(1995—)
  • 作者简介:曾招鑫(1995—),男,江西赣州人,硕士研究生,主要研究方向:深度学习、计算机视觉; 刘俊(1977—),男,河南南阳人,教授,博士,CCF会员,主要研究方向:图像处理、医学图像分析、机器学习。
  • 基金资助:

    国家自然科学基金面上项目(31600975)。

Microscopic image segmentation method of C.elegans based on deep learning

ZENG Zhaoxin1,2, LIU Jun1,2   

  1. 1.College of Computer Science and Technology, Wuhan University of Science and Technology, WuhanHubei 430065, China
    2.Hubei Provincial Key Laboratory of Intelligent Information Processing and Real-time Industrial System (Wuhan University of Science and Technology), WuhanHubei 430065, China
  • Received:2019-10-08 Revised:2019-11-01 Online:2020-05-10 Published:2020-05-15
  • Contact: ZENG Zhaoxin, born in 1995, M. S. candidate. His research interests include deep learning, computer vision.
  • About author:ZENG Zhaoxin, born in 1995, M. S. candidate. His research interests include deep learning, computer vision.LIU Jun, born in 1977, Ph. D., professor. His research interests include image processing, medical image analysis, machine learning.
  • Supported by:

    This work is partially supported by the Surface Program of National Natural Science Foundation of China (31600975).

摘要:

利用计算机实现自动、准确的秀丽隐杆线虫(C.elegans)的各项形态学参数分析,至关重要的是从显微图像上分割出线虫体态,但由于显微镜下的图像噪声较多,线虫边缘像素与周围环境相似,而且线虫的体态具有鞭毛和其他附着物需要分离,多方面因素导致设计一个鲁棒性的C.elegans分割算法仍然面临着挑战。针对这些问题,提出了一种基于深度学习的线虫分割方法,通过训练掩模区域卷积神经网络(Mask R-CNN)学习线虫形态特征实现自动分割。首先,通过改进多级特征池化将高级语义特征与低级边缘特征融合,结合大幅度软最大损失(LMSL)损失算法改进损失计算;然后,改进非极大值抑制;最后,引入全连接融合分支等方法对分割结果进行进一步优化。实验结果表明,相比原始的Mask R-CNN,该方法平均精确率(AP)提升了4.3个百分点,平均交并比(mIOU)提升了4个百分点。表明所提出的深度学习分割方法能够有效提高分割准确率,在显微图像中更加精确地分割出线虫体。

关键词: 秀丽隐杆线虫, 图像分割, 深度学习, 掩模区域卷积神经网络, 特征融合, 大幅度软最大损失

Abstract:

To analyze the morphological parameters of Caenorhabditis elegans (C.elegans) automatedly and accurately by computers, the critical step is the segmentation of nematode body shape from the microscopic image. However, the design of C.elegans segmentation algorithm with robustness is still facing challenges because of a lot of noise in the microscopic image, the similarity between the pixels of the nematode edge with the surrounding environment, and the flagella and other attachments of the nematode body shape which need to be separated. Aiming at these problems, a method based on deep learning for nematode segmentation was proposed, in which the morphological features of nematodes were studied by training Mask Region-Convolutional Neural Network (Mask R-CNN) to realize automatic segmentation. Firstly, the high-level semantic features were combined with the low-level edge features by improving the multi-level feature pooling, and Large-Margin Softmax Loss (LMSL) algorithm was combined to improve the loss calculation. Then, the non-maximum suppression was improved. Finally, the methods such as fully connected fusion branch were added to further optimize the segmentation results. Experimental results show that compared to original Mask R-CNN, the proposed method has Average Precision (AP) increased by 4.3 percentage points, and the mean Intersection Over Union (mIOU) increased by 4 percentage points, which means that the proposed deep learning segmentation method can improve the segmentation accuracy effectively and segment the nematodes from the microscopic images more accurately.

Key words: Caenorhabditis elegans (C.elegans), image segmentation, deep learning, Mask Region-Convolutional Neural Network (Mask R-CNN), feature fusion, Large-Margin Softmax Loss (LMSL)

中图分类号: