基于深度学习的秀丽隐杆线虫显微图像分割方法

doi:10.11772/j.issn.1001-9081.2019091683

摘要
图/表
参考文献(25)
相关文章 (15)

全文: PDF (2638 KB) HTML
输出: BibTeX | EndNote (RIS)

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。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	曾招鑫
	刘俊

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)

收稿日期: 2019-10-08

中图分类号:

TP183

基金资助:

国家自然科学基金面上项目(31600975)。

通讯作者: 曾招鑫(1995—) E-mail: 493952184@qq.com

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。

引用本文:

曾招鑫, 刘俊. 基于深度学习的秀丽隐杆线虫显微图像分割方法[J]. 计算机应用, 2020, 40(5): 1453-1459. ZENG Zhaoxin, LIU Jun. Microscopic image segmentation method of C.elegans based on deep learning. Journal of Computer Applications, 2020, 40(5): 1453-1459.

链接本文:

http://www.joca.cn/CN/10.11772/j.issn.1001-9081.2019091683 或 http://www.joca.cn/CN/Y2020/V40/I5/1453

1 杰里米·伯格 . 单细胞尺度的生命探索[J]. 思羽,译. 世界科学, 2019(1):1. (BERG J. Life exploration on a single cell scale[J]. SI Y, translated. World Science, 2019(1):1.)
2 翟畅,叶波平 . 秀丽隐杆线虫与药物筛选[J]. 药物生物技术, 2017, 24(5):464-467. (ZHAI C, YE B P. Caenorhabditis elegans in drug screening[J]. Pharmaceutical Biotechnology, 2017, 24(5): 464-467.)
3 田华洁,黄晓星,孙海燕,等 . 秀丽隐杆线虫用于帕金森病及其治疗药物的分子生物学研究[J]. 世界临床药物, 2013, 34(7) :436-438, 446. TIAN H J , HUANG X X , SUN H Y , et al . Caenorhabditis Elegans: a model organism of molecular biology for Parkinson’s disease and its drug evaluation[J]. World Clinical Drugs, 2013, 34(7): 436-438, 446.
4 罗山,张冬梅 . 基于自适应阈值和形态学的改进分水岭分割算法[J].山西电子技术, 2018(6):3-5. (LUO S, ZHANG D M. Improved watershed segmentation algorithm based on adaptive threshold and morphology[J]. Shanxi Electronic Technology, 2018(6):3-5.)
5 张雯柏,柴晓冬,郑树彬,等 . 基于二值形态学算子的轨道图像分割新算法[J]. 测控技术, 2018, 37(10):10-13, 21. ZHANG W B , CHAI X D , ZHENG S B , et al . A new algorithm for orbital image segmentation based on binary morphological operator[J]. Measurement and Control Technology, 2018, 37(10):10-13, 21.
6 LIU G H , DONG F , FU C H , et al . Automated morphometry toolbox for analysis of microscopic model organisms using simple bright-field imaging[J]. Biology Open, 2019, 8(3):No.bio037788.
7 LECUN Y , BENGIO Y , HINTON G . Deep learning[J]. Nature, 2015, 521(7553): 436-444.
8 RAZAVIAN A S , AZIZPOUR H , SULLIVAN J , et al . CNN features off-the-shelf: an astounding baseline for recognition[C]// Proceedings of the 2014 IEEE Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2014: 512-519.
9 GIRSHICK R , DONAHUE J , DARRELL T , et al . Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 580-587.
10 HE K , ZHANG X , REN S , et al . Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9):1904-1916.
11 GIRSHICK R . Fast R-CNN[C]// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015:1440-1448.
12 REN S , HE K , GIRSHICK R , et al . Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
13 HE K , GKIOXARI G , DOLLáR P , et al . Mask R-CNN[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017:2980-2988.
14 LIU W , WEN Y , YU Z , et al . Large-margin softmax loss for convolutional neural networks[C]// Proceedings of the 33rd International Conference on International Conference on Machine Learning. New York: JMLR.org, 2016:507-516.
15 LI Y , QI H , DAI J , et al . Fully convolutional instance-aware semantic segmentation[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017:4438-4446.
16 HE K , ZHANG X , REN S , et al . Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778.
17 SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition[EB/OL]. [2019-03-20].https://arxiv.org/pdf/1409.1556.pdf.
18 SZEGEDY C , LIU W , JIA Y , et al . Going deeper with convolutions[C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015:1-9.
19 RAFFERTY J , SHELLITO P , HYMAN N H , et al . Practice parameters for sigmoid diverticulitis[J]. Diseases of the Colon and Rectum, 2006, 49(7):939-944.
20 VINCENT P , LAROCHELLE H , LAJOIE I , et al . Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010, 11:3371-3408.
21 MARTINS A F , ASTUDILLO R , et al . From softmax to sparsemax: a sparse model of attention and multi-label classification[C]// Proceedings of the 33rd International Conference on International Conference on Machine Learning. New York: JMLR.org, 2016:1614-1623.
22 LIANG X , WEI Y , SHEN X , et al . Reversible recursive instance-level object segmentation[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Computer Society, 2016:633-641.
23 LIU S , QI X , SHI J , et al . Multi-scale Patch Aggregation (MPA) for simultaneous detection and segmentation[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016:3141-3149.
24 常颖 . 基于Curvelet变换的图像增强算法研究[D]. 长春:长春理工大学, 2011: 176-214. CHANG Y.Curvelet transform based on the image enhancement algorithms[D]. Changchun: Changchun University of Science and Technology, 2011: 176-214.
25 葛阳,杨瑞峰,张鹏 . 基于改进的二维Otsu分割算法及其应用研究[J]. 核电子学与探测技术, 2012, 32(1):115-118. GE Y, YANG R F, ZHANG P.Research on improved two-dimensional Otsu segmentation algorithm and its application[J]. Nuclear Electronics and Detection Technology, 2012, 32(1):115-118.