基于注意力机制的U-Net脑脊液细胞分割

doi:10.12068/j.issn.1005-3026.2022.07.005

东北大学学报（自然科学版） ›› 2022, Vol. 43 ›› Issue (7): 944-950.DOI: 10.12068/j.issn.1005-3026.2022.07.005

基于注意力机制的U-Net脑脊液细胞分割

代茵^1,2，刘维宾^1,2，董昕阳³，宋雨朦^1,2

(1.东北大学医学与生物信息工程学院，辽宁沈阳110169; 2.东北大学教育部医学影像与智能分析工程中心，辽宁沈阳110169; 3.约克大学计算机学院，英国约克郡YO10 5DD)

发布日期:2022-08-02
通讯作者: 代茵
作者简介:代茵(1982-)，女，黑龙江齐齐哈尔人，东北大学副教授.
基金资助:
国家自然科学基金青年基金资助项目(61902058); 中央高校基本科研业务费专项资金资助项目(N2019002).

U-Net CSF Cells Segmentation Based on Attention Mechanism

DAI Yin^1,2， LIU Wei-bin^1,2， DONG Xin-yang³， SONG Yu-meng^1,2

1. College of Medicine and Biological Information Engineering， Northeastern University， Shenyang 110169， China; 2. Engineering Center on Medical Imaging and Intelligent Analysis， Ministry of Education， Northeastern University， Shenyang 110169， China; 3.School of Computing， University of York， Yorkshire YO10 5DD， UK.

Published:2022-08-02
Contact: DAI Yin
About author:-
Supported by:
-

摘要/Abstract

摘要： 为解决脑脊液病理图像中部分细胞膜较为模糊，与图像背景难以区分的问题，采用了基于注意力机制的U-Net深度学习方法对脑脊液病理图像做全自动分割.在深度学习网络中加入注意力机制对细胞进行定位，抑制无关信息，提高语义的特征表达，提高对细胞整体分割的精确性.通过镜像、旋转等操作对数据集进行扩充预处理.采用VGG16预训练模型进行迁移学习，交叉熵与Dice损失相结合作为损失函数，分别在脑脊液临床图像与公开数据集2018 Data Science Bowl上进行验证；并与Otsu， PSPnet， Segnet， DeeplabV3+， U-Net进行对比，结果表明，本文方法在各项指标上均优于其他分割方法.

关键词: 脑脊液检测；细胞分割；注意力机制；深度学习；U-Net模型

Abstract: In order to solve the problem that part of the cell membrane in the pathological images of CSF (cerebrospinal fluid) is blurred and this is difficult to be distinguished from the image background. The U-Net based on attention mechanism is proposed to segment pathological images of CSF automatically. Attention mechanism is added to deep learning network to locate cells， suppress irrelevant information， improve semantic feature expression， and further improve the accuracy of cell segmentation. The datasets are preprocessed by mirroring and rotation. VGG16 pre-training model is used for transfer learning. Cross entropy is combined with Dice loss as Loss function which is validated in CSF clinical images and open dataset 2018 Data Science Bowl and compared with Otsu， PSPnet， Segnet， DeeplabV3+， U-Net. The results show that the proposed method is superior to other segmentation methods in all indexes.

Key words: CSF test; cell segmentation; attention mechanism; deep learning; U-Net model

中图分类号:

TP391.5

代茵，刘维宾，董昕阳，宋雨朦. 基于注意力机制的U-Net脑脊液细胞分割[J]. 东北大学学报（自然科学版）, 2022, 43(7): 944-950.

DAI Yin， LIU Wei-bin， DONG Xin-yang， SONG Yu-meng. U-Net CSF Cells Segmentation Based on Attention Mechanism[J]. Journal of Northeastern University(Natural Science), 2022, 43(7): 944-950.

参考文献

[1]Graus F，Titulaer M J，Balu R，et al.A clinical approach to diagnosis of autoimmune encephalitis ［J］.The Lancet Neurology，2016，15(4):391-404.
[2]Kra B，Blf B，Hka B，et al.An observational study investigating cytokine levels in the cerebrospinal fluid of patients with schizophrenia spectrum disorders［J］.Schizophrenia Research，2021，231:205-213.
[3]Tamam Y，Gunes B，Akbayir E，et al.CSF levels of HoxB3 and YKL-40 may predict conversion from clinically isolated syndrome to relapsing remitting multiple sclerosis［J］.Multiple Sclerosis and Related Disorders，2021，48:102697.
[4]Xu X，Li F，Wang S，et al.Hierarchy-NMS:merging candidate bounding boxes for cerebrospinal fluid cell image segmentation［J］.Journal of Physics:Conference Series，2020，1693:012140-012144.
[5]Jiang Y，Chen W，Liu M，et al.3D neuron microscopy image segmentation via the Ray-Shooting model and a DC-BLSTM network［J］.IEEE Transactions on Medical Imaging，2020，40(1): 26-37.
[6]赵宝奇，尉飞，孙军梅，等.结合密集连接块和自注意力机制的腺体细胞分割方法［J］.计算机辅助设计与图形学学报，2021，33(7):991-999.(Zhao Bao-qi，Wei Fei，Sun Jun-mei，et al.Glandular cell segmentation method combined with dense connective block and self-attention mechanism［J］.Journal of Computer-Aided Design & Computer Graphics，2021，33(7) :991-999.)
[7]张文秀，朱振才，张永合，等.基于残差块和注意力机制的细胞图像分割方法［J］.光学学报，2020，40(17):70-77.(Zhang Wen-xiu，Zhu Zhen-cai，Zhang Yong-he，et al.Cell image segmentation method based on residual block and attention mechanism ［J］.Acta Optica Sinica，2020，40(17):70-77.)
[8]Ma H，Zou Y，Liu P X.MHSU-Net:a more versatile neural network for medical image segmentation［J］.Computer Methods and Programs in Biomedicine，2021，208:106230-106239.
[9]Chen J，Lu Y，Yu Q，et al.TransUNet:transformers make strong encoders for medical image segmentation［EB/OL］.(2021-02-08)［2021-11-21］.https://arxiv.org/abs/2102.04306v1.
[10]Chan S X，Huang C，Bai C，et al.Res2-UNeXt:a novel deep learning framework for few-shot cell image segmentation［J］.Multimedia Tools and Applications，2022，81:13275-13288.
[11]Vaswani A，Shazeer N，Parmar N，et al.Attention is all you need［EB/OL］.(2017-12-06)［2021-12-23］.https://arxiv.org/abs/1706.03762v5.
[12]Zhang Y，Liu M，Yu F，et al. An O-shape neural network with attention modules to detect junctions in biomedical images without segmentation［J］.IEEE Journal of Biomedical and Health Informatics， 2022，26(2):774-785.
[13]刘珍梅.基于BTTFA和迁移学习的宫颈细胞图像分割算法研究［D］.广州:华南理工大学，2020.(Liu Zhen-mei.Nuclear segmentation based on BTTFA and transfer learning for cevicl cell images［D］.Guangzhou:South China University of Technology，2020.)
[14]Weiss K，Khoshgoftaar T M，Wang D D.A survey of transfer learning［J］.Journal of Big Data，2016，3(1):1-40.
[15]Woo S，Park J，Lee J Y，et al.CBAM:convolutional block attention module［C］//European Conference on Computer Vision.Berlin: Springer，2018:3-19.
[16]Simonyan K，Zisserman A.Very deep convolutional networks for large-scale image recognition［EB/OL］.(2015-04-10)［2021-11-24］.https://arxiv.org/abs/1409.1556v1.
[17]Ronneberger O，Fischer P，Brox T.U-Net:convolutional networks for biomedical image segmentation［C］//International Conference on Medical Image Computing & Computer-Assisted Intervention.Munich:Springer，2015:234-241.
[18]Oktay O，Schlemper J，Folgoc L L，et al.Attention U-Net:learning where to look for the pancreas［EB/OL］.(2018-05-20)［2021-12-01］.https://arxiv.org/abs/1804.03999v1.
[19]Jaderberg M，Simonyan K，Zisserman A.Spatial transformer networks［C］//Neural Information Processing Systems.Cambridge:MIT Press，2015:2017-2025.
[20]Hu J，Li S，Gang S，et al.Squeeze-and-excitation networks［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42(8):2011-2023.
[21]Ma J，Nie Z，Wang C，et al.Active contour regularized semi-supervised learning for COVID-19 CT infection segmentation with limited annotations［J］.Physics in Medicine and Biology，2020，65(22):225034-225047.
[22]Kingma D P，Ba J.Adam:a method for stochastic optimization［EB/OL］.(2017-01-30)［2021-12-22］.https://arxiv.org/abs/1412.6980v2.

基于注意力机制的U-Net脑脊液细胞分割

U-Net CSF Cells Segmentation Based on Attention Mechanism

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	鲍喜荣，沈晓燕，张石，苏婷. 基于改进DMAS的平面波超声成像算法及其GPU实现[J]. 东北大学学报:自然科学版, 2019, 40(7): 925-931.
[2]	鲍喜荣，李玉珍，苏婷，张石. 医疗超声成像自适应波束形成算法[J]. 东北大学学报:自然科学版, 2018, 39(4): 468-473.
[3]	鲍喜荣，高浩森，历正双，张石. 基于PDChirp-Golay信号的编码激励算法[J]. 东北大学学报（自然科学版）, 2021, 42(2): 208-212.
[4]	李鸿儒，任子洋，黄友鹤，于霞. 基于变权重奇异谱分析的心律不齐识别方法[J]. 东北大学学报（自然科学版）, 2022, 43(3): 305-312.