注意力驱动的细胞团簇细胞核分割算法

doi:10.19665/j.issn1001-2400.2022.02.023

摘要/Abstract

摘要：

胸腔积液细胞团簇的细胞核形态为肺癌诊断、肿瘤转移及治疗效果评价提供了重要途径,而对其细胞核进行精准分割是肺癌病理诊断工作的基础。由于胸腔积液肿瘤细胞团簇复杂的生成背景,以及细胞核特征的不均匀性(特征信息分散)和团簇内部重叠细胞中的触核情况(特征不明显),使细胞团簇分割仍然是一个具有挑战性的问题。提出了基于注意力机制的改进U-Net模型,从空间注意力和通道注意力两方面来增强对细胞核非显著特征的学习;并改进U-Net的跳跃连接,融合U-Net中深层和浅层特征,解决语义间隙的问题。实验结果表明,与最新的其他方法相比,CRUNet能够在所建立的胸水细胞团簇数据集上取得更好的分割效果。为了进一步说明该网络的有效性,在公共数据集BBBC020上也与其他网络进行了对比。

关键词: 胸腔积液细胞团簇, 图像分割, 注意力机制, U-Net

Abstract:

Nuclei morphology of pleural effusion cell clusters provides an essential way for the diagnosis,metastasis,and treatment evaluation of the lung cancer.Accurate segmentation of the nuclei is the basis of pathological diagnosis of the lung cancer.Because of the complex background of tumor cell clusters in pleural effusion,the inhomogeneity of nuclei features (scattered feature information),and nuclei overlapping within clusters (whose characteristics are not prominent),the segmentation of tumor cell clusters is still a challenging problem.In this paper,an improved U-Net model,named CRUNet,based on the attention mechanism is proposed.With the attention module,the CRUNet can enhance the learning of non-salient features of the nucleus from spatial attention and channel attention,and improve the jumping connection of the U-Net to integrate the deep and shallow features of the U-Net to solve the problem of the semantic gap.Experimental results show that compared with other state-of-the-art methods,the CRUNet can achieve a better segmentation performance on our self-established pleural effusion cell cluster dataset.To further illustrate the effectiveness of the proposed network,the CRUNet is also compared with other networks on a public cell dataset-BBBC020.

Key words: pleural effusion cell clusters, segmentation, attention mechanism, U-Net

中图分类号:

TP391

马思珂,赵萌,石凡,孙续国,陈胜勇. 注意力驱动的细胞团簇细胞核分割算法[J]. 西安电子科技大学学报, 2022, 49(2): 198-206.

MA Sike,ZHAO Meng,SHI Fan,SUN Xuguo,CHEN Shengyong. Attention driven nuclei segmentation method for cell clusters[J]. Journal of Xidian University, 2022, 49(2): 198-206.

图/表 8

图1

图2

图3

表1

图4

图5

表2

表3

参考文献 37

[1]	SIEGEL R L, MILLER K D, JEMAL A. Cancer Statistics,2020[J]. CA:A Cancer Journal for Clinicians, 2020, 70(1):7-30. doi: 10.3322/caac.21590
[2]	BRAY F, FERLAY J, SOERJOMATARAM I, et al. Global Cancer Statistics 2018:GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries[J]. CA:A Cancer Journal for Clinicians, 2018, 68(6):394-424. doi: 10.3322/caac.21492
[3]	赵晶, 梁隆恺, 何勇军, 等. 复杂背景下的宫颈细胞核分割方法[J]. 哈尔滨理工大学学报, 2019, 24(3):22-28.
	ZHAO Jing, LIANG Longkai, HE Yongjun, et al. The Method of Segmentation of Cervical Nuclei in Complex Background[J]. Journal of Harbin University of Science and Technology, 2019, 24(3):22-28.
[4]	闫欢兰, 陆慧娟, 叶敏超, 等. 结合Sobel算子和Mask R-CNN的肺结节分割[J]. 小型微型计算机系统, 2020, 41(1):161-165.
	YAN Huanlan, LU Huijuan, YE Minchao, et al. Lung Nodule Segmentation Combining Sobel Operator and Mask R-CNN[J]. Journal of Chinese Computer Systems, 2020, 41(1):161-165.
[5]	SHAHUL HAMEED K A, BANUMATHI A, ULAGANATHAN G. P53immunostained Cell Nuclei Segmentation in Tissue Images of Oral Squamous Cell Carcinoma[J]. Signal,Image and Video Processing, 2017, 11:363-370. doi: 10.1007/s11760-016-0953-y
[6]	GAMARRA M, ZUREK E, ESCALANTE H J, et al. Split and Merge Watershed:A Two-Step Method for Cell Segmentation in Fluorescence Microscopy Images[J]. Biomedical Signal Processing and Control, 2019, 53:101575. doi: 10.1016/j.bspc.2019.101575
[7]	王娅. 血液红细胞图像自适应标记分水岭分割算法[J]. 中国图象图形学报, 2017, 22(12):1779-1787.
	WANG Ya. Adaptive Marked Watershed Segmentation Algorithm for Red Blood Cell Images[J]. Journal of Image and Graphics, 2017, 22(12):1779-1787.
[8]	冯飞, 刘培学, 李丽, 等. FCM融合改进的GSA算法在医学图像分割中的研究[J]. 计算机科学, 2018, 45(A1):252-254.
	FENG Fei, LIU Peixue, LI Li, et al. Study of FCM Fusing Improved Gravitational Search Algorithm in Medical Image Segmentation[J]. Computer Science, 2018, 45(A1):252-254.
[9]	BAI X, SUN C, SUN C, et al. Cell Segmentation Based on FOPSO Combined with Shape Information Improved Intuitionistic FCM[J]. IEEE Journal of Biomedical and Health Informatics, 2019, 23(1):449-459. doi: 10.1109/JBHI.2018.2803020
[10]	王莹, 于晓升, 迟剑宁, 等. 双层水平集描述眼底图像视杯视盘分割[J]. 中国图象图形学报, 2020, 25(6):1260-1270.
	WANG Ying, YU Xiaosheng, CHI Jianning, et al. Segmentation of Optic Cup and Disc Based on Two-Layer Level Set Describer in Retinal Fundus Images[J]. Journal of Image and Graphics, 2020, 25(6):1260-1270.
[11]	YU S, LU Y, MOLLOY D. A Dynamic-Shape-Prior Guided Snake Model with Application in Visually Tracking Dense Cell Populations[J]. IEEE Transactions on Image Processing, 2019, 28(3):1513-1527. doi: 10.1109/TIP.2018.2878331
[12]	陈红, 吴成东, 于晓升, 等. 多描述子活动轮廓模型的医学图像分割[J]. 中国图象图形学报, 2018, 23(3):434-441
	CHEN Hong, WU Chengdong, YU Xiaosheng, et al. Active Contour Model for Medical Image Segmentation Based on Multiple Descriptors[J]. Journal of Image and Graphics, 2018, 23(3):434-441.
[13]	ZHAO M, WANG H, HAN Y, et al. SEENS:Nuclei Segmentation in Pap Smear Images with Selective Edge Enhancement[J]. Future Generation Computer Systems, 2021, 114:185-194. doi: 10.1016/j.future.2020.07.045
[14]	NAYLOR P, LAE M, REYAL F, et al. Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map[J]. IEEE Transactions on Medical Imaging, 2019, 38(2):448-459. doi: 10.1109/TMI.2018.2865709
[15]	ZHAO M, WU A, SONG J, et al. Automatic Screening of Cervical Cells Using Block Image Processing[J]. BioMedical Engineering Online, 2016, 15(1):14. doi: 10.1186/s12938-016-0131-z
[16]	CHAURASIA A, CULURCIELLO E. LinkNet:Exploiting Encoder Representations for Efficient Semantic Segmentation[C]// 2017 IEEE Visual Communications and Image Processing (VCIP).Piscataway:IEEE, 2017:1-4.
[17]	BADRINARAYANAN V, HANDA A, CIPOLLA R. SegNet:A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling (2015)[J/OL].[2015-05-27]. https://arxiv.org/abs/1505.07293.
[18]	PASZKE A, CHAURASIA A, KIM S, et al. ENet:A Deep Neural Network Architecture for Real-Time Semantic Segmentation (2016)[J/OL].[2016-06-07]. https://arxiv.org/abs/1606.02147.
[19]	RONNEBERGER O, FISCHER P, BROX T. U-Net:Convolutional Networks for Biomedical Image Segmentation[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention.Heidelberg:Springer, 2015:234-241.
[20]	MEHTA S, RASTEGARI M, CASPI A, et al. ESPNet:Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation[C]// European Conference on Computer Vision.Heidelberg:Springer, 2018:561-580.
[21]	MEHTA S, RASTEGARI M, SHAPIRO L, et al. ESPNetv2:A Light-Weight,Power Efficient,and General Purpose Convolutional Neural Network[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway:IEEE, 2019:9182-9192.
[22]	MEHTA S, MERCAN E, BARTLETT J, et al. Y-Net:Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention.Heidelberg:Springer, 2018:893-901.
[23]	LI X, ZHONG Z, WU J, et al. Expectation-Maximization Attention Networks for Semantic Segmentation[C]// 2019 IEEE/CVF International Conference on Computer Vision (ICCV).Piscataway:IEEE, 2019:9166-9175.
[24]	杨晓莉, 蔺素珍. 一种注意力机制的多波段图像特征级融合方法[J]. 西安电子科技大学学报, 2020, 47(1):120-127.
	YANG Xiaoli, LIN Suzhen. Method for Multi-Band Image Feature-Level Fusion Based on the Attention Mechanism[J]. Journal of Xidian University, 2020, 47(1):120-127.
[25]	LIAN S, LUO Z, ZHONG Z, et al. Attention Guided U-Net for Accurate Iris Segmentation[J]. Journal of Visual Communication and Image Representation, 2018, 56:296-304. doi: 10.1016/j.jvcir.2018.10.001
[26]	WANG W, YE C, ZHANG S, et al. Improving Whole-Heart CT Image Segmentation by Attention Mechanism[J]. IEEE Access, 2019, 8:14579-14587. doi: 10.1109/ACCESS.2019.2961410
[27]	BUI TD, WANG L, CHEN J, et al. Multi-Task Learning for Neonatal Brain Segmentation Using 3D Dense-Unet with Dense Attention Guided by Geodesic Distance[C]// International Workshop on Medical Image Learning with Less Labels and Imperfect Data.Heidelberg:Springer, 2019:243-251.
[28]	AMER A, YE X, ZOLGHARNI M, et al. ResDUnet:Residual Dilated UNet for Left Ventricle Segmentation from Echocardiographic Images[C]// 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).Piscataway:IEEE, 2020:2019-2022.
[29]	WOO S, PARK J, LEE J Y, et al. CBAM:Convolutional Block Attention Module[C]// European Conference on Computer Vision.Heidelberg:Springer, 2018:3-19.
[30]	IBTEHAZ N, RAHMAN M S. MultiResU-Net:Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation[J]. Neural Networks, 2020, 121:74-87. doi: 10.1016/j.neunet.2019.08.025
[31]	TRAN D, RANGANATH R, BLEI D M. The Variational Gaussian Process (2015)[J/OL].[2015-11-20]. https://arxiv.org/abs/1511.06499.
[32]	LI X, CHANG D, TIANT, et al. Large-Margin Regularized Softmax Cross-Entropy Loss[J]. IEEE Access, 2019, 7:19572-19578. doi: 10.1109/ACCESS.2019.2897692
[33]	HU J, SHEN L, ALBANIE S, et al. Squeeze-and-Excitation Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 42(8):2011-2023. doi: 10.1109/TPAMI.2019.2913372
[34]	CAO Y, XU J, LIN S, et al. GCNet:Non-Local Networks MeetSqueeze-Excitation Networks and Beyond[C]// Proceedings of the IEEE International Conference on Computer Vision Workshop.Piscataway:IEEE, 2019:1971-1980.
[35]	LJOSA V, SOKOLNICKI K L, CARPENTER A E. Annotated High-Throughput Microscopy Image Sets for Validation[J]. Nature Methods, 2013, 10(5):445.
[36]	ZHANG S, FU H, YAN Y, et al. Attention Guided Network for Retinal Image Segmentation[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention.Heidelberg:Springer, 2019:797-805.
[37]	DIAKOGIANNIS F I, WALDNER F, CACCETTA P, et al. ResUNet-a:A Deep Learning Framework for Semantic Segmentation of Remotely Sensed Data[J]. Journal of Photogrammetry and Remote Sensing, 2019, 162:94-114. doi: 10.1016/j.isprsjprs.2020.01.013

数据集	模型	D	P	R	F1
胸水细胞团簇数据集	U-Net	0.759 0	0.525 9	0.714 7	0.605 9
	U-Net+Res路径+SE	0.798 1	0.717 9	0.696 7	0.707 1
	U-Net+Res路径+GC	0.815 3	0.669 0	0.700 7	0.684 5
	CRUNet	0.823 5	0.750 5	0.697 3	0.722 9
BBBC020数据集	U-Net	0.830 8	0.584 6	0.715 2	0.643 3
	U-Net+Res路径+SE	0.837 4	0.698 6	0.695 7	0.697 1
	U-Net+Res路径+GC	0.842 0	0.691 5	0.697 4	0.694 4
	CRUNet	0.864 1	0.752 8	0.692 9	0.721 4

数据集	模型	D	P	R	F1
胸水细胞团簇数据集	U-Net	0.759 0	0.525 9	0.714 7	0.605 9
	AGNet	0.714 2	0.944 9	0.574 1	0.714 2
	ResUNet	0.644 4	0.705 4	0.636 3	0.669 2
	CRUNet	0.823 5	0.750 5	0.697 3	0.722 9

BACKBONE	CBAM	RES-PATH	D	P	R	F
U-Net			0.759 0	0.525 9	0.714 7	0.605 9
		√	0.775 9	0.541 5	0.717 2	0.617 1
	√		0.810 6	0.746 5	0.690 7	0.717 5
	√	√	0.823 5	0.750 5	0.697 3	0.722 9