面神经序列图像感兴趣区域识别

doi:10.3969/j.issn.1006-2475.2017.11.010

计算机与现代化

面神经序列图像感兴趣区域识别

(1.广东工业大学自动化学院，广东广州 510006; 2.广东省第二人民医院神经外科，广东广州 510317)

收稿日期:2017-02-24 出版日期:2017-11-21 发布日期:2017-11-21
作者简介:通信作者：林钦壮(1994-)，男，广东揭阳人，广东工业大学自动化学院本科生，研究方向：图像理解; 钟映春(1973-)，男，江西赣州人，副教授，博士，研究方向：模式识别与图像理解; 罗唯师(1982-)，男，广东梅州人，广东省第二人民医院神经外科主治医师，硕士，研究方向：神经外科与图像理解。
基金资助:
广东省高性能计算重点实验室开放项目(TH1528)

Recognition of Region of Interest from Facial Nerve Image Sequences

(1. School of Automation, Guangdong University of Technology, Guangzhou 510006, China; 2. Department of Neurosurgery, Guangdong 2nd Provincial General Hospital, Guangzhou 510317, China)

Received:2017-02-24 Online:2017-11-21 Published:2017-11-21

摘要/Abstract

摘要： 通过计算机识别面神经序列图像中的感兴趣区域，可以在手术规划过程中辅助医生辨别具体的功能区域，使医生进行手术时更有针对性，避免对面部神经区域的额外伤害。将面神经图像处理并划分成不同的功能区域，利用卷积神经网络对大量病例样本进行学习，得到具有较高准确率的感兴趣区域识别模型。实验结果表明，该卷积神经网络模型可以有效地对面神经序列图像识别出感兴趣区域，具有一定的医疗辅助作用。

关键词: 面神经序列图像, 卷积神经网络(CNN), 图像处理, 感兴趣区域识别

Abstract: The computer recognition of facial nerve MR image sequences in the region of interest, can help doctors identify specific functional areas in the surgical planning process and performe the operation more targeted to avoid additional damage of facial nerve area. In this paper, facial nerve MR images are segmented into different functional areas, and a large number of case samples are studied by convolutional neural network, and the recognition model with high accuracy is obtained. The experimental results show that the convolutional neural network model can effectively recognize the region of interest in the image recognition of facial nerve, and it has a certain medical assistant effect.

Key words: facial nerve MR image sequences, convolutional neural network, image processing, region of interest in image recognition

中图分类号:

TP391.41

林钦壮1，钟映春1，罗唯师2. 面神经序列图像感兴趣区域识别[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2017.11.010.

LIN Qin-zhuang1, ZHONG Ying-chun1, LUO Wei-shi2. Recognition of Region of Interest from Facial Nerve Image Sequences[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2017.11.010.

参考文献

[1] Heaton J T, Knox C J, Malo J S, et al. A system for delivering mechanical stimulation and robot-assisted therapy to the rat whisker pad during facial nerve regeneration[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2013,21(6):928-937.

[2] May M, Schaitkin B M. History of facial nerve surgery[J]. Facial Plastic Surgery, 2000,16(4):301-307.

[3] Lu Ping, Barazzetti L, Chandran V, et al. Facial nerve image enhancement from CBCT using supervised learning technique[C]// Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2015:2964-2967.

[4] Bengio Y, Delalleau O. On the expressive power of deep architectures[C]// Proceedings of the 2011 International Conference on Algorithmic Learning Theory. 2011:18-36.

[5] 吕国豪,罗四维,黄雅平,等. 基于卷积神经网络的正则化方法[J]. 计算机研究与发展, 2014,51(9):1891-1900.

[6] Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998,86(11):2278-2324.

[7] Yang Weixin, Jin Lianwen, Liu Manfei. Chinese character-level writer identification using path signature feature, DropStroke and deep CNN[C]// Proceedings of the 13th International Conference on Document Analysis and Recognition. 2015:546-550.

[8] 蔡娟,蔡坚勇,廖晓东,等. 基于卷积神经网络的手势识别初探[J]. 计算机系统应用, 2015,24(4):113-117.

[9] 李岳云,许悦雷,马时平,等. 深度卷积神经网络的显著性检测[J]. 中国图象图形学报, 2016,21(1):53-59.

[10] Tivive F H C, Bouzerdoum A. A new class of convolutional neural networks (SICoNNets) and their application of face detection[C]// Proceedings of the 2003 International Joint Conference on Neural Networks. 2003,3:2157-2162.

[11] Chen Ying-Nong, Han Chin-Chuan, Wang Cheng-Tzu, et al. The application of a convolution neural network on face and license plate detection[C]// Proceedings of the 18th International Conference on Pattern Recognition. 2006,3:552-555.

[12] Ji Shuiwang, Xu Wei, Yang Ming, et al. 3D convolutional neural networks for human action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35(1):221-231.

[13] 赵志宏,杨绍普,马增强. 基于卷积神经网络LeNet-5的车牌字符识别研究[J]. 系统仿真学报, 2010,22(3):638-641.

[14] 黄琳,张尤赛. 应用深层卷积神经网络的交通标志识别[J]. 现代电子技术, 2015,38(13):101-106.

[15] Sukittanon S, Surendran A C, Platt J C, et al. Convolutional networks for speech detection[C]// Proceedings of the 8th International Conference on Spoken Language Processing. 2004:1077-1080.

[16] Simard P Y, Steinkraus D, Platt J C. Best practices for convolutional neural networks applied to visual document analysis[C]// Proceedings of the 7th International Conference on Document Analysis and Recognition. 2003,2:958-962.

[17] Mobahi H, Collobert R, Weston J. Deep learning from temporal coherence in video[C]// Proceedings of the 26th Annual International Conference on Machine Learning. 2009:737-744.

面神经序列图像感兴趣区域识别

Recognition of Region of Interest from Facial Nerve Image Sequences

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	叶力鸣, 陈蔚文. 一种结合语义分割和目标检测的级联式绝缘子缺陷检测方法[J]. 计算机与现代化, 2023, 0(06): 82-88.
[2]	刘志飞, 朱尚超, 魏战红, 臧一鸣, 孙文韬, 胡冠时. 基于IBM Qiskit的量子图像伪彩色增强方法[J]. 计算机与现代化, 2023, 0(04): 47-55.
[3]	朱卓樾, 黄欢, 宋清玲, 侯居攀. 基于心血管核磁共振图像的房室平面位移检测与重建[J]. 计算机与现代化, 2023, 0(04): 78-82.
[4]	李四杰, 唐清善, 高英华. 基于GMS和改进最佳缝合线的视差图像拼接算法[J]. 计算机与现代化, 2022, 0(12): 95-101.
[5]	丁婉莹, 陈伟, 李昭慧. 基于编解码结构的多特征融合眼底图像分割[J]. 计算机与现代化, 2022, 0(07): 1-7.
[6]	金安安, 丁双双, 熊卿智, 许婷婷, 习淑萍, 马继忠. 基于SWOMP算法的EPMA影像优化重构[J]. 计算机与现代化, 2020, 0(12): 104-111.
[7]	冯洋. 基于小波包变换的红外弱小目标检测[J]. 计算机与现代化, 2020, 0(12): 112-115.
[8]	张辉, 余厚云, 李克斌. 基于机械臂的涡轮壳零件表面质量视觉检测[J]. 计算机与现代化, 2020, 0(07): 121-126.
[9]	付磊,任德均,胡云起,郜明,邱吕. 基于ResNet网络的医用塑瓶制造缺陷检测方法[J]. 计算机与现代化, 2020, 0(04): 104-.
[10]	卢爱平，李盼池. 基于混沌序列的量子图像加密方案[J]. 计算机与现代化, 2020, 0(03): 86-.
[11]	买尔孜燕古丽·阿不都拉，冯向萍. 基于机器视觉的非接触式马体尺测量方法[J]. 计算机与现代化, 2019, 0(10): 108-.
[12]	王伟. 非刚性三维点云配准方法[J]. 计算机与现代化, 2018, 0(12): 116-.
[13]	敖宇,杨健晟. 欧拉视频增强技术在火焰弱信号检测中的应用[J]. 计算机与现代化, 2018, 0(07): 73-.
[14]	范新南，薛瑞阳，史朋飞，李敏，倪建军. 基于非负矩阵分解与相似性分析的运动目标检测[J]. 计算机与现代化, 2018, 0(04): 37-.
[15]	刘青松，谢晓方，曹建，张龙杰. 基于OpenCV的导引头图像处理算法性能评估软件[J]. 计算机与现代化, 2017, 0(3): 80-.