生物医学工程学杂志

生物医学工程学杂志

卷积神经网络及其在医学图像分析中的应用研究

查看全文

卷积神经网络(CNN)是机器学习研究中的热点,在医学图像应用中具有一定价值。本文首先介绍了 CNN 基本原理,其次综述了其在网络结构的改进:在模型结构方面,总结了 CNN 的 11 种经典模型,并以时间顺序梳理发展进程;在结构优化方面,从 CNN 的 5 个方面(输入层、卷积层、下采样层、全连接层以及整个网络)总结研究进展。然后,对学习算法从优化和融合两个方面进行归纳:优化算法方面,根据优化目的(提高准确率、防止过拟合、防止局部最值、提高收敛速度)梳理算法的进展;方法融合方面,分别从输入层、卷积层、下采样层、全连接层和输出层共 5 个角度进行归纳。最后,将 CNN 映射到医学图像领域,结合计算机辅助诊断探讨 CNN 在医学图像中的应用。本文对 CNN 进行了较为全面系统地总结,对 CNN 的研究发展具有积极意义。

Recent years, convolutional neural network (CNN) is a research hot spot in machine learning and has some application value in computer aided diagnosis. Firstly, this paper briefly introduces the basic principle of CNN. Secondly, it summarizes the improvement on network structure from two dimensions of model and structure optimization. In model structure, it summarizes eleven classical models about CNN in the past 60 years, and introduces its development process according to timeline. In structure optimization, the research progress is summarized from five aspects (input layer, convolution layer, down-sampling layer, full-connected layer and the whole network) of CNN. Thirdly, the learning algorithm is summarized from the optimization algorithm and fusion algorithm. In optimization algorithm, it combs the progress of the algorithm according to optimization purpose. In algorithm fusion, the improvement is summarized from five angles: input layer, convolution layer, down-sampling layer, full-connected layer and output layer. Finally, CNN is mapped into the medical image domain, and it is combined with computer aided diagnosis to explore its application in medical images. It is a good summary for CNN and has positive significance for the development of CNN.

关键词: 卷积神经网络; 网络结构; 学习算法; 医学图像

Key words: convolutional neural network; network structure; learning algorithm; medical image

引用本文: 梁蒙蒙, 周涛, 张飞飞, 杨健, 夏勇. 卷积神经网络及其在医学图像分析中的应用研究. 生物医学工程学杂志, 2018, 35(6): 977-985. doi: 10.7507/1001-5515.201710060 复制

登录后 ,请手动点击刷新查看全文内容。 没有账号,
登录后 ,请手动点击刷新查看图表内容。 没有账号,
1. Guo Yanming, Liu Yu, Oerlemans A, et al. Deep learning for visual understanding: A review. Neurocomputing, 2016, 187: 27-48.
2. Hayman S. The McCulloch-Pitts model//International Joint Conference on Neural Networks. Washington, USA: IEEE, 1999: 4438-4439.
3. Lécun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
4. Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks//International Conference on Neural Information Processing Systems. Lake Tahoe, USA: Curran Associates, 2012: 1097-1105.
5. Gökhan. Hazim K E. Initialization of convolutional neural networks by Gabor filters//26th Signal Processing and Communications Applications Conference (SIU), Izmir, 2018: 1-4.
6. 杨格兰, 邓晓军, 刘琮. 基于深度时空域卷积神经网络的表情识别模型. 中南大学学报:自然科学版, 2016, 47(7): 2311-2319.
7. 杜昌顺, 黄磊. 分段卷积神经网络在文本情感分析中的应用. 计算机工程与科学, 2017, 39(1): 173-179.
8. 张力, 张洞明, 郑宏. 基于联合层特征的卷积神经网络在车标识别中的应用. 计算机应用, 2016, 36(2): 444-448.
9. 王伟凝, 王励, 赵明权, 等. 基于并行深度卷积神经网络的图像美感分类. 自动化学报, 2016, 42(6): 904-914.
10. 刘占文, 赵祥模, 李强, 等. 基于图模型与卷积神经网络的交通标志识别方法. 交通运输工程学报, 2016, 16(5): 122-131.
11. 邬美银, 陈黎, 田菁. 基于卷积神经网络的视频图像失真检测及分类. 计算机应用研究, 2016, 33(9): 2827-2830.
12. 陈耀丹, 王连明. 基于卷积神经网络的人脸识别方法. 东北师大学报:自然科学版, 2016, 48(2): 70-76.
13. 刘冶, 潘炎, 夏榕楷, 等. FP-CNNH: 一种基于深度卷积神经网络的快速图像哈希算法. 计算机科学, 2016, 43(9): 39-46, 51.
14. 李寰宇, 毕笃彦, 查宇飞, 等. 一种易于初始化的类卷积神经网络视觉跟踪算法. 电子与信息学报, 2016, 38(1): 1-7.
15. Guan Sheng, Chen Min, Ha H Y, et al. Deep learning with MCA-based instance selection and bootstrapping for imbalanced data classification//2015 IEEE Conference On Collaboration And Internet Computing (CIC), Hangzhou, China: IEEE, 2015: 288-295.
16. 吴素雯, 战荫伟. 基于选择性搜索和卷积神经网络的人脸检测. 计算机应用研究, 2017, 34(9): 2854-2857, 2876.
17. 刘万军, 梁雪剑, 曲海成. 不同池化模型的卷积神经网络学习性能研究. 中国图象图形学报, 2016, 21(9): 1178-1190.
18. Huang Zhen, Siniscalchi S M, Lee C H. A unified approach to transfer learning of deep neural networks with applications to speaker adaptation in automatic speech recognition. Neurocomputing, 2016, 218: 448-459.
19. 李雯. 基于深度卷积神经网络的 CT 图像肝脏肿瘤分割方法研究. 中国科学院大学, 深圳: 中国科学院深圳先进技术研究院, 2016.
20. Shen Wei, Zhou Mu, Yang Feng, et al. Multi-scale convolutional neural networks for lung nodule classification. Inf Process Med Imaging, 2015, 24: 588-599.
21. 郝占龙, 罗晓曙, 赵书林. 基于同层多尺度核 CNN 的单细胞图像分类. 计算机工程与应用, 2018, 54(15): 181-184.
22. Gao X W, Hui Rui, Tian Zengmin. Classification of CT brain images based on deep learning networks. Comput Methods Programs Biomed, 2017, 138: 49-56.
23. Mishra M, Schmitt S, Wang Lichao, et al. Structure-based assessment of cancerous mitochondria using deep networks//2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), Prague: Czech Republic, 2016: 545-548.
24. 秦志光, 陈浩, 丁熠, 等. 基于多模态卷积神经网络的脑血管提取方法研究. 电子科技大学学报, 2016, 45(4): 573-581.
25. Chen J, Qi X, Tervonen O, et al. Thorax disease diagnosis using deep convolutional neural network//38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society(EMBC). Orlando, USA, 2016: 2287-2290.