基于稠密块和注意力机制的肺部病理图像异常细胞分割

doi:10.11959/j.issn.2096-6652.202210

智能科学与技术学报 ›› 2023, Vol. 5 ›› Issue (4): 525-534.doi: 10.11959/j.issn.2096-6652.202210

基于稠密块和注意力机制的肺部病理图像异常细胞分割

崔文成, 王可丽(), 邵虹

沈阳工业大学信息科学与工程学院，辽宁沈阳 110870

收稿日期:2021-07-12 修回日期:2021-08-27 出版日期:2023-12-15 发布日期:2023-12-15
通讯作者: 王可丽 E-mail:3254589937@qq.com
作者简介:崔文成（1973- ），男，沈阳工业大学信息科学与工程学院副教授，主要研究方向为智能信息处理。
王可丽（1993- ），女，沈阳工业大学信息学院硕士生，主要研究方向为智能信息处理。
邵虹（1974- ），女，博士，沈阳工大学信息科学与工程学院教授，主要研究方向为图像处理与模式识别、智能信息处理。

Abnormal cell segmentation for lung pathological image based on denseblock and attention mechanism

Wencheng CUI, Keli WANG(), Hong SHAO

School of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, China

Received:2021-07-12 Revised:2021-08-27 Online:2023-12-15 Published:2023-12-15
Contact: Keli WANG E-mail:3254589937@qq.com

摘要/Abstract

摘要：

针对肺部细胞病理图像亮度不均衡、异常细胞轮廓精准分割难以实现的问题，提出一种以U-Net为基本框架，结合稠密块以及注意力机制的异常细胞分割模型。首先，利用具有编码器-解码器结构的U-Net对异常细胞进行分割；然后，在U-Net中引入稠密块，以提高特征之间的传播能力，提取更多异常细胞的特征信息；最后，利用注意力机制提高异常细胞区域的权重，降低亮度不均衡对模型的干扰。实验结果表明，该方法的IoU和Dice相似系数值分别为0.6928和0.8060，与其他模型相比，提出的方法能够分割出低对比度区域和形状多样的异常细胞。

关键词: 肺部细胞病理图像, 细胞分割, U-Net, 稠密块, 注意力机制

Abstract:

Aiming at the problems of unbalanced brightness of lung cell images and achieving accurate segmentation of abnormal cell contour difficultly, an abnormal cell segmentation model based on U-Net was proposed, which combined the dense connection mechanism and attention mechanism. Firstly, U-Net with encoder-decoder structure was used to segment abnormal cells. Secondly, the dense block was introduced into U-Net to improve the propagation ability between features and extract more characteristic information of abnormal cells. Finally, the attention mechanism was used to increase the weight of abnormal cell regions and reduce the interference of the imbalance of brightness to the model. The experimental results show that the IoU value and Dice similarity coefficient achieved by this method are 0.6928 and 0.8060, respectively. Compared with other models, this proposed method is able to segment low-contrast regions and abnormal cells with diverse shapes.

Key words: lung cell pathology image, cell segmentation, U-Net, dense block, attention mechanism

中图分类号:

TP391

崔文成,王可丽,邵虹. 基于稠密块和注意力机制的肺部病理图像异常细胞分割[J]. 智能科学与技术学报, 2023, 5(4): 525-534.

Wencheng CUI,Keli WANG,Hong SHAO. Abnormal cell segmentation for lung pathological image based on denseblock and attention mechanism[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(4): 525-534.

图/表 15

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

表1

图12

图13

表2

参考文献 25

1	FENG R M, ZONG Y N, CAO S M, et al. Current cancer situation in China: good or bad news from the 2018 global cancer statistics? [J]. Cancer Communications (London, England), 2019, 39(1): 22.
2	刘树范, 阚秀. 细胞病理学[M]. 北京: 中国协和医科大学出版社, 2011.
	LIU S F, KAN X. Cytopathology[M]. Beijing: Peking Union Medical College Press, 2011.
3	卞修武, 平轶芳. 我国病理学科发展面临的挑战和机遇[J]. 第三军医大学学报, 2019, 41(19): 1815-1817.
	BIAN X W, PING Y F. Pathology in China: challenges and opportunities[J]. Journal of Third Military Medical University, 2019, 41(19): 1815-1817.
4	王丽会, 秦永彬. 深度学习在医学影像中的研究进展及发展趋势[J]. 大数据, 2020, 6(6): 83-104.
	WANG L H, QIN Y B. State of the art and future perspectives of the applications of deep learning in the medical image analysis[J]. Big Data Research, 2020, 6(6): 83-104.
5	TERAMOTO A, TSUKAMOTO T, KIRIYAMA Y, et al. Automated classification of lung cancer types from cytological images using deep convolutional neural networks[J]. BioMed Research International, 2017.
6	TERAMOTO A, YAMADA A, KIRIYAMA Y, et al. Automated classification of benign and malignant cells from lung cytological images using deep convolutional neural network[J]. Informatics in Medicine Unlocked, 2019, 16: 100205.
7	TERAMOTO A, TSUKAMOTO T, YAMADA A, et al. Deep learning approach to classification of lung cytological images: two-step training using actual and synthesized images by progressive growing of generative adversarial networks[J]. PLoS One, 2020, 15(3): e0229951.
8	ZHU H Z, ZHANG Y Y, LI M, et al. Exploring deep learning for efficient and reliable mobile sensing[J]. IEEE Network, 2018, 32(4): 6-7.
9	SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 640-651.
10	RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of 2015 Medical Image Computing and Computer-Assisted Intervention. [S.l.:s.n.], 2015.
11	崔文成, 张鹏霞, 邵虹. 基于深度可分离卷积网络的皮肤镜图像病灶分割方法[J]. 智能科学与技术学报, 2020, 2(4): 385-393.
	CUI W C, ZHANG P X, SHAO H. Dermoscopic image lesion segmentation method based on deep separable convolutional network[J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(4): 385-393.
12	ROY A G, NAVAB N, WACHINGER C. Concurrent spatial and channel 'squeeze & excitation' in fully convolutional networks[C]//Proceedings of 2018 Medical Image Computing and Computer Assisted Intervention. [S.l.:s.n.], 2018.
13	OKTAY O, SCHLEMPER J, FOLGOC L L, et al. Attention U-Net: learning where to look for the pancreas[EB]. arXiv preprint, 2018, arXiv:1804.03999.
14	WANG W, YU K C, HUGONOT J, et al. Recurrent U-Net for resource-constrained segmentation[C]//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE Press, 2019: 2142-2151.
15	CHEN W L, ZHANG Y, HE J J, et al. Prostate segmentation using 2D bridged U-Net[C]//Proceedings of 2019 International Joint Conference on Neural Networks. Piscataway: IEEE Press, 2019: 1-7.
16	ORLANDO J I, SEEB?CK P, BOGUNOVI? H, et al. U2-Net: a Bayesian U-Net model with epistemic uncertainty feedback for photoreceptor layer segmentation in pathological OCT scans[C]//Proceedings of 2019 IEEE 16th International Symposium on Biomedical Imaging. Piscataway: IEEE Press, 2019: 1441-1445.
17	LI X M, CHEN H, QI X J, et al. H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes[J]. IEEE Transactions on Medical Imaging, 2018, 37(12): 2663-2674.
18	GUAN S, KHAN A A, SIKDAR S, et al. Fully dense UNet for 2-D sparse photoacoustic tomography artifact removal[J]. IEEE Journal of Biomedical and Health Informatics, 2020, 24(2): 568-576.
19	HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2017: 2261-2269.
20	IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[EB]. arXiv preprint,2015, arXiv:1502.03167.
21	HE K M, ZHANG X Y, REN S Q, et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification[C]// Proceedings of 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 2015: 1026-1034.
22	MILLETARI F, NAVAB N, AHMADI S A. V-Net: fully convolutional neural networks for volumetric medical image segmentation[C]//Proceedings of 2016 4th International Conference on 3D Vision. Piscataway: IEEE Press, 2016: 565-571.
23	KINGMA D P, BA J. Adam: a method for stochastic optimization[EB].arXiv preprint, 2014, arXiv:1412.6980.
24	LEVANDOWSKY M, WINTER D. Distance between sets[J]. Nature, 1971, 234(5323): 34-35.
25	DICE L R. Measures of the amount of ecologic association between species[J]. Ecology, 1945, 26(3): 297-302.

模型	IoU	DSC
FCN-8s	0.6231	0.7480
U-Net	0.6519	0.7743
R2U-Net	0.6598	0.7762
本文模型	0.6928	0.8070

模型	IoU	DSC
U-Net	0.6519	0.7743
Dense-UNet	0.6624	0.7773
Attention-UNet	0.6748	0.7875
本文模型	0.6928	0.8070

[1]	邵虹, 左常升, 张萍. 结合Attention U-Net与瓶颈检测的肺部细胞图像分割方法[J]. 智能科学与技术学报, 2022, 4(4): 610-616.
[2]	陈妍, 罗雪琴, 梁伟, 谢永芳. 基于情感信息融合注意力机制的抑郁症识别[J]. 智能科学与技术学报, 2022, 4(4): 600-609.
[3]	尹开石, 杨萌, 顾曦, 王志成. 基于角度敏感的空间注意力机制的轻量型旋转目标检测器[J]. 智能科学与技术学报, 2021, 3(3): 322-333.
[4]	沈继锋, 刘岳, 韦浩, 左欣, 杨万扣. 基于差分特征注意力机制的无锚框多光谱行人检测算法[J]. 智能科学与技术学报, 2021, 3(3): 294-303.

基于稠密块和注意力机制的肺部病理图像异常细胞分割

Abnormal cell segmentation for lung pathological image based on denseblock and attention mechanism

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 25

相关文章 4

Metrics

推荐阅读 0