U-Net CSF Cells Segmentation Based on Attention Mechanism

doi:10.12068/j.issn.1005-3026.2022.07.005

Abstract

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

CLC Number:

TP391.5

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.

References

[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.