基于空间通道挤压激励模块的肝硬化识别

doi:10.19678/j.issn.1000-3428.0058866

摘要/Abstract

摘要： 针对卷积神经网络对特征信息学习不全面、识别准确率和分类精度不高的问题，提出一种采用空间通道挤压激励模块的scSE_MVGG网络，将其应用于肝硬化识别。对肝硬化图像进行数据增强，以避免深度学习训练出现过拟合现象，改进VGG网络使其适应不同实验样本尺寸，同时将scSE模块与改进的MVGG网络相融合，通过提高网络提取特征的指向性增强肝硬化识别效果。实验结果表明，该网络对肝硬化图像的识别率达到98.78%，较scSE_VGG、scSE_AlexNet等网络识别效果更优。

关键词: 肝硬化识别, 空间通道挤压激励模块, 卷积神经网络, VGG网络, 空间通道关系

Abstract: The existing Convolutional Neural Networks(CNN) fail to fully learn the feature information, and provides low accuracy in recognition as well as classification. To address the problem, a scSE_MVGG network using spatial channel squeeze excitation module is proposed and applied to liver cirrhosis recognition. The liver cirrhosis images are enhanced to avoid over fitting phenomenon in deep learning training, and the VGG network is improved to adapt to experimental samples of different sizes. At the same time, the scSE module is fused with the improved MVGG network to assist the CNN in the learning of channel information and spatial feature information. So the directivity of extracted network features is enhanced, and thus the performance of CNN in liver cirrhosis recognition is improved. Experimental results show that the accuracy of the proposed network in liver cirrhosis image recognition reaches 98.78%, higher than that of scSE_VGG, scSE_AlexNet and other networks.

Key words: liver cirrhosis recognition, spatial channel squeeze excitation module, Convolutional Neural Network(CNN), VGG network, spatial channel relation

中图分类号:

TP391.41

王倩, 赵希梅. 基于空间通道挤压激励模块的肝硬化识别[J]. 计算机工程, 2021, 47(8): 308-314.

WANG Qian, ZHAO Ximei. Liver Cirrhosis Recognition Based on Spatial Channel Squeeze Excitation Module[J]. Computer Engineering, 2021, 47(8): 308-314.

https://www.ecice06.com/CN/Y2021/V47/I8/308

图/表 15

20210819202754

20210819202758

20210819202802

20210819202806

20210819202810

20210819202814

20210819202818

20210819202823

20210819202827

20210819202831

20210819202835

20210819202838

20210819202843

20210819202848

20210819202853

参考文献

[1] XU Z, XIANG L, XI E, et al. Diagnosis of cirrhosis stage via deep neural network[C]//Proceedings of 2017 IEEE International Conference on Bioinformatics and Biomedicine.Washington D.C., USA:IEEE Press, 2017:745-749.
[2] TREA D, LUPSOR M P, NEDEVSCHI S, et al. Discovering the cirrhosis grades from ultrasound images by using textural features and clustering methods[C]//Proceedings of 2013 International Conference on Telecommunications and Signal Processing.Washington D.C., USA:IEEE Press, 2013:633-637.
[3] SHIN H C, ROTH H R, GAO M C, et al. Deep convolutional neural networks for computer-aided detection:CNN architectures, dataset characteristics and transfer learning[J]. IEEE Transactions on Medical Imaging, 2016, 35(5): 1285-1298.
[4] CHEN T, TU S X, WANG H L, et al. Computer-aided diagnosis of gallbladder polyps based on high resolution ultrasonography[J]. Computer Methods and Programs in Biomedicine, 2020, 185(3): 105-118.
[5] YANG J F, QIAO P R, LI Y M, et al. Review of machine learning classification problems and algorithms research[J]. Statistics and Decision, 2019, 35(6): 36-40.
[6] NANDA A S, SWARNKAR T.Deep learning approach for image classification[C]//Proceedings of the 2nd International Conference on Data Science and Business Analytics.Washington D.C., USA:IEEE Press, 2018:97-101.
[7] 常炳国, 李玉琴, 冯志超.基于主成分机器学习算法的慢性肝病的智能预测新方法[J]. 计算机科学, 2017(S2): 75-77, 101. CHANG B G, LI Y Q, FENG Z C.New intelligent prediction method for chronic liver disease based on principal component machine learning algorithm[J]. Computer Science, 2017(S2): 75-77, 101.(in Chinese)
[8] 雷一鸣, 赵希梅, 王国栋, 等. 基于一种改进的LBP算法和超限学习机的肝硬化识别[J]. 计算机科学, 2017, 44(10): 45-50. LEI Y M, ZHAO X M, WANG G D, et al. Identification of liver cirrhosis based on an improved LBP algorithm and over-limit learning machine[J]. Computer Science, 2017, 44(10): 45-50.(in Chinese)
[9] 韩秀芝.赵希梅, 于可歆.一种基于LBP特征提取和稀疏表示的肝病识别算法[J]. 中国生物医学工程学报, 2017, 36(6): 647-653. HAN X Z, ZHAO X M, YU K X.A liver disease recognition algorithm based on LBP feature extraction and sparse representation[J]. Chinese Journal of Biomedical Engineering, 2017, 36(6): 647-653.(in Chinese)
[10] ZHAI S, OU W, YANG Y, et al. Hepatic lesion recognition based on deep visual feature learning[C]//Proceedings of 2019 Photonics and Electromagnetics Research Symposium Fall.Xiamen, China:[s.n.], 2019:1744-1748.
[11] 张顺, 龚怡宏, 王进军.深度卷积神经网络的发展及其在计算机视觉领域的应用[J]. 计算机学报, 2019, 42(3): 453-482. ZHANG S, GONG Y H, WANG J J.Development of deep convolutional neural networks and its application in computer vision[J]. Chinese Journal of Computers, 2019, 42(3): 453-482.(in Chinese)
[12] SIMONYAN K, ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL]. [2020-05-23]. https://www.researchgate.net/publication/319770291_Very_Deep_Convolutional_Networks_for_Large-Scale_Image_Recognition.
[13] KRIZHEVSKY A, SUTSKEVER I, HINTON G.ImageNet classification with deep convolutional neural networks[EB/OL]. [2020-05-23]. https://www.researchgate.net/publication/267960550_ImageNet_Classification_with_Deep_Convolutional_Neural_Networks.
[14] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:770-778.
[15] HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 214-232.
[16] ROY A G, NAVAB N, WACHINGER C.Recalibrating fully convolutional networks with spatial and channel "squeeze and excitation" blocks[J]. IEEE Transactions on Medical Imaging, 2019, 38(2): 540-549.
[17] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3): 211-252.
[18] HARYANTO T, SUHARTANTO H, MURNI A, et al. Strategies to improve performance of convolutional neural network on histopathological images classification[EB/OL]. [2020-05-23]. https://www.researchgate.net/publication/339100825_Strategies_to_Improve_Performance_of_Convolutional_Neural_Network_on_Histopathological_Images_Classification.
[19] LU H M, ZHAO D, CHI X B.Early diagnosis of Alzheimer's disease based on deep learning enhanced by AlexNet[J]. Computer Science, 2017(S1): 50-60.
[20] 李钢, 李海芳, 尚方信, 等. 基于梯度信息的自适应邻域噪声图像分割模型[J]. 计算机工程, 2018, 44(5): 227-233, 239. LI G, LI H F, SHANG F X, et al. Noise image segmentation model with adaptive neighborhood based on gradient information[J]. Computer Engineering, 2018, 44(5): 227-233, 239. (in Chinese).
[21] 张欢, 赵希梅.基于STN和异构卷积滤波器的肝硬化识别[J]. 计算机工程, 2021, 47(5): 301-307, 315. ZHANG H, ZHAO X M.Identification of liver cirrhosis based on STN and heterogeneous convolution filter[J]. Computer Engineering, 2021, 47(5): 301-307, 315.(in Chinese)

选择文件类型/文献管理软件名称

选择包含的内容