您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（医学版）》

山东大学学报 (医学版) ›› 2020, Vol. 58 ›› Issue (8): 42-49, 73.doi: 10.6040/j.issn.1671-7554.0.2020.0391

•   • 上一篇    下一篇

基于深度学习的脑肿瘤图像分割

刘琚1,2,*(),吴强1,2,于璐跃1,林枫茗1   

  1. 1. 山东大学信息科学与工程学院, 山东 青岛 266237
    2. 山东大学脑与类脑科学研究院, 山东 济南 250012
  • 收稿日期:2020-03-20 出版日期:2020-08-07 发布日期:2020-08-07
  • 通讯作者: 刘琚 E-mail:juliu@sdu.edu.cn
  • 作者简介:刘琚，工学博士，教授、博士研究生导师。现任中国电子学会高级会员、IEEE高级会员，《电子与信息学报》《数据采集与处理》和《山东大学学报(理学版)》等编委，《International Journal of Digital Crime and Forensics》等副编辑；曾获批教育部“新世纪优秀人才支持计划”、济南市优秀创新团队领军人物和海信数字多媒体技术国家重点实验室特聘教授。曾作为访问教授或高级研究学者在西班牙、美国、英国、德国和日本等国的不同大学进行通信信号处理和医学图像处理等方面的合作研究。主要研究方向包括“智能信号处理理论与应用”、“无线通信中空时信号处理技术”、“多媒体通信与网络传输技术”等。先后主持承担了国家重点研发计划、国家自然科学基金、高等学校科技创新工程重大项目培育资金项目和山东省重大科技创新工程项目等课题。获省部级科技进步奖4项、授权发明专利20余项、学术专著2部，在国内外核心期刊或重要学术会议上发表学术论文200余篇
  • 基金资助:
    山东省自主创新及成果转化专项计划(2015ZDXX0801A01);山东省重点研发计划(2017CXGC1504);山东大学自主创新基金(自然科学专项);山东大学自主创新基金(2015QY001-05)

Brain tumor image segmentation based on deep learning techniques

Ju LIU1,2,*(),Qiang WU1,2,Luyue YU1,Fengming LIN1   

  1. 1. School of Information Science and Engineering, Shandong University, Qingdao 266237, Shandong, China
    2. Institute of Brain and Brain-Inspired Science, Shandong University, Jinan 250012, Shandong, China
  • Received:2020-03-20 Online:2020-08-07 Published:2020-08-07
  • Contact: Ju LIU E-mail:juliu@sdu.edu.cn

RichHTML

108

PDF (PC)

942

摘要：

人工智能技术在计算机视觉与深度学习领域的应用逐渐增多，自动驾驶、无人机、医学临床诊疗等行业都需要基于深度学习的图像分割技术做支撑。本文对近年来脑肿瘤图像分割方法进行综述：首先介绍了图像分割的传统方法和基于深度学习的方法，然后概述了目前几种典型的针对脑肿瘤图像分割方法，描述其主要进展与可借鉴之处，总结了我们在基于深度学习的脑肿瘤图像分割方面的研究结果，并与典型方法的性能进行对比，最后讨论未来研究方向及面临的挑战。

关键词: 人工智能, 深度学习, 图像分割, 脑肿瘤图像, 神经网络

Abstract:

Artificial intelligence technology is widely applied in the field of computer vision and deep learning. Image segmentation technology based on deep learning is essential in industries such as autonomous driving, drones, and clinical diagnosis and treatment. This paper reviews the methods of brain tumor image segmentation, including the traditional methods of image segmentation and methods based on deep learning and some typical methods. The paper also compares our research advances with the typical methods and discusses future research directions and challenges.

Key words: Artificial intelligence, Deep learning, Image segmentation, Brain tumor image, Neural network

中图分类号: 

  • R574

图1

空洞卷积结构[13]"

图2

特征金字塔结构[15]"

图3

DANet的模块结构[17]"

图4

使用生成对抗结构的分割网络[24]"

图5

ShuffleSeg网络架构[28]"

图6

U-Net用于脑瘤数据分割"

图7

Attention R2U-Net的网络结构[33]"

图8

网络结构可视化示意图[35]"

表1

与BRATS2018测试集的现状比较[40]"

BraTS2018Dice
WT TC ET
VGG 0.872 4 0.693 3 0.659 8
DUNet 0.863 1 0.688 4 0.620 5
FCNN 0.868 7 0.653 7 0.582 8
HPUNet 0.893 0 0.810 8 0.755 8
baseline(HPUNet+ResNet) 0.892 5 0.781 1 0.746 3
baseline+FCU 0.895 4 0.809 1 0.778 3
baseline+FCU+MIMU 0.895 6 0.831 3 0.806 7
baseline+FCU+MIMU+SIMU 0.901 9 0.837 4 0.817 6
1 李伟峰. 一种新的PSO优化FCM方法在图像分类中的应用[J]. 软件导刊, 2013, 12 (8): 72- 75.
LI Weifeng . Application of web data ming on accurate prediction of susceptible populations of acute mountain sickness[J]. Software Guide, 2013, 12 (8): 72- 75.
2 张长水. 机器学习面临的挑战[J]. 中国科学:信息科学, 2013, 43 (12): 1612- 1623.
3 林正春, 王知衍, 张艳青. 最优进化图像阈值分割算法[J]. 计算机辅助设计与图形学学报, 2010, 22 (7): 1201- 1206.
LIN Zhengchun , WANG Zhiyan , ZHANG Yanqing . Optimal evolution algorithm for image thresholding[J]. Journal of Computer-aided Design & Computer Graphics, 2010, 22 (7): 1201- 1206.
4 陆剑锋, 林海, 潘志庚. 自适应区域生长算法在医学图像分割中的应用[J]. 计算机辅助设计与图形学学报, 2005, 17 (10): 2168- 2173.
LU Jianfeng , LIN Hai , PAN Zhigeng . Adaptive region growing algorithm in medical images segmentation[J]. Journal of Computer-aided Design & Computer Graphics, 2005, 17 (10): 2168- 2173.
5 Boykov YY, Jolly MP. Interactive graph cuts for optimal boundary & region segmentation of objects in ND images [C]. Proceedings 8th IEEE International Conference on Computer Vision, 2001: 105-112.
6 Wang Y , Loe KF , Wu JK . A dynamic conditional random field model for foreground and shadow segmentation[J]. IEEE Trans Pattern Anal Mach Intell, 2006, 28 (2): 279- 289.
doi: 10.1109/TPAMI.2006.25
7 Masooleh MG , Ali S , Moosavi S . An improved fuzzy algorithm for image segmentation[J]. World Academy of Science, Engineering and Technology, 2008, 1 (40): 400- 404.
8 Mostajabi M, Yadollahpour P, Shakhnarovich G. Feedforward semantic segmentation with zoom-out features [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 3376-3385.
9 Shelhamer E , Long J , Darrell T . Fully convolutional networks for semantic segmentation[J]. IEEE Trans Pattern Anal Mach Intell, 2015, 39 (4): 640- 651.
10 Badrinarayanan V , Kendall A , Cipolla R . SegNet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Trans Pattern Anal Mach Intell, 2017, 39 (12): 2481- 2495.
doi: 10.1109/TPAMI.2016.2644615
11 Noh H, Hong S, Han B. Learning deconvolution network for semantic segmentation [C]. Proceedings of the IEEE International Conference on Computer Vision, 2015: 1520-1528.
12 Chen LC , Papandreou G , Kokkinos I , et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Trans Pattern Anal Mach Intell, 2018, 40 (4): 834- 848.
doi: 10.1109/TPAMI.2017.2699184
13 Chen LC, Papandreou G, Schroff F, et al. Rethinking atrous convolution for semantic image segmentation [EB/OL]. (2017-12-5) [2020-3-19]. https://arxiv.org/abs/1706.05587.
14 Liu W, Rabinovich A, Berg AC. ParseNet: Looking Wider to See Better [EB/OL]. (2015-11-19) [2020-3-19]. https://arxiv.org/abs/1506.04579.
15 Ghiasi G, Fowlkes CC. Laplacian pyramid reconstruction and refinement for semantic segmentation [C]. European Conference on Computer Vision, Springer, Cham, 2016: 519-534.
16 Lin TY, Dollár P, Girshick R, et al. Feature pyramid networks for object detection [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2117-2125.
17 Fu J, Liu J, Tian H, et al. Dual attention network for scene segmentation [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019: 3146-3154.
18 Hong S, Noh H, Han B. Decoupled deep neural network for semi-supervised semantic segmentation [C]. Advances in Neural Information Processing Systems, 2015: 1495-1503.
19 Kolesnikov A, Lampert CH. Seed, expand and constrain: Three principles for weakly-supervised image segmentation [C]. European Conference on Computer Vision, Springer, Cham, 2016: 695-711.
20 Zhou B, Khosla A, Lapedriza A, et al. Learning deep features for discriminative localization [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 2921-2929.
21 Lin D, Dai J, Jia J, et al. Scribblesup: Scribble-supervised convolutional networks for semantic segmentation [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 3159-3167.
22 Cheplygina V , de BM , Pluim JPW . Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis[J]. MedIA, 2019, 54 (1): 280- 296.
doi: 10.1016/j.media.2019.03.009
23 Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets [C]. Advances in Neural Information Processing Systems, 2014: 2672-2680.
24 Luc P, Couprie C, Chintala S, et al. Semantic Segmentation using Adversarial Networks [EB/OL]. (2016-11-25) [2020-3-19]. https://arxiv.org/abs/1611.08408.
25 Hoffman J, Wang D, Yu F, et al. FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation [EB/OL]. (2016-12-8) [2020-3-19]. https://arxiv.org/abs/1612.02649.
26 Souly N, Spampinato C, Shah M. Semi supervised semantic segmentation using generative adversarial network [C]. 2017 IEEE International Conference on Computer Vision, 2017: 5689-5697.
27 Tsai YH, Hung WC, Schulter S, et al. Learning to adapt structured output space for semantic segmentation [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 7472-7481.
28 Gamal M, Siam M, Abdel-Razek M. ShuffleSeg: Real-time Semantic Segmentation Network [EB/OL]. (2018-3-15) [2020-3-19]. https://arxiv.org/abs/1803.03816.
29 田娟秀, 刘国才, 谷珊珊, 等. 医学图像分析深度学习方法研究与挑战[J]. 自动化学报, 2018, 44 (3): 401- 424.
TIAN Xiujuan , LIU Guocai , GU Shanshan , et al. Deep learning in medical image analysis and its challenges[J]. Acta Automatica Sinica, 2018, 44 (3): 401- 424.
30 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, Springer, Cham, 2015: 234-241.
31 He K, Zhang X, Ren S, et al. Deep residual learning for image recognition [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
32 Huang G, Liu Z, Van DML, et al. Densely connected convolutional networks [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4700-4708.
33 Alom MZ , Yakopcic C , Hasan M , et al. Recurrent residual U-Net for medical image segmentation[J]. Journal of Medical Imaging, 2019, 6 (1): 345- 350.
doi: 10.1117/1.JMI.6.1.014006
34 Oktay O, Schlemper J, Folgoc LL, et al. Attention u-net: Learning where to look for the pancreas[EB/OL]. (2018-5-20) [2020-3-19]. https://arxiv.org/abs/1804.03999.
35 Myronenko A. 3D MRI brain tumor segmentation using autoencoder regularization[C]. International MICCAI Brainlesion Workshop, Springer, Cham, 2018: 311-320.
36 Zhou C, Chen S, Ding C, et al. Learning contextual and attentive information for brain tumor segmentation[C]. International MICCAI Brainlesion Workshop, Springer, Cham, 2018: 497-507.
37 McKinley R, Meier R, Wiest R. Ensembles of densely-connected CNNs with label-uncertainty for brain tumor segmentation[C]. International MICCAI Brainlesion Workshop, Springer, Cham, 2018: 456-465.
38 Kong X, Sun G, Wu Q, et al. Hybrid pyramid U-Net model for brain tumor segmentation[C]. International Conference on Intelligent Information Processing, Springer, Cham, 2018: 346-355.
39 Lin F, Wu Q, Liu J, et al. Path aggregation U-Net model for brain tumor segmentation[EB/OL]. (2020-03-19) [2020-03-19]. https://doi.org/10.1007/s11042-020-08795-9.
40 Lin F, Liu J, Wu Q, et al. FMNet: Feature mining networks for brain tumor segmentation[C]. IEEE 31st International Conference on Tools with Artificial Intelligence, IEEE Computer Society, 2019: 555-560.
[1] 赵继宗. 神经外科学是脑科学研究的一支主力军[J]. 山东大学学报 (医学版), 2020, 58(8): 1-4.
[2] 李新钢,张鑫,陈安静. 当代脑计划研究进展[J]. 山东大学学报 (医学版), 2020, 58(8): 5-9, 21.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 索东阳,申飞,郭皓,刘力畅,杨惠敏,杨向东. Tim-3在药物性急性肾损伤动物模型中的表达及作用机制[J]. 山东大学学报 (医学版), 2020, 58(7): 1 -6 .
[2] 张宝文,雷香丽,李瑾娜,罗湘俊,邹容. miR-21-5p靶向调控TIMP3抑制2型糖尿病肾病小鼠肾脏系膜细胞增殖及细胞外基质堆积[J]. 山东大学学报 (医学版), 2020, 58(7): 7 -14 .
[3] 龙婷婷,谢明,周璐,朱俊德. Noggin蛋白对小鼠脑缺血再灌注损伤后学习和记忆能力与齿状回结构的影响[J]. 山东大学学报 (医学版), 2020, 58(7): 15 -23 .
[4] 付洁琦,张曼,张晓璐,李卉,陈红. Toll样受体4抑制过氧化物酶体增殖物激活受体γ加重血脂蓄积的分子机制[J]. 山东大学学报 (医学版), 2020, 58(7): 24 -31 .
[5] 马青源,蒲沛东,韩飞,王超,朱洲均,王维山,史晨辉. miR-27b-3p调控SMAD1对骨肉瘤细胞增殖、迁移和侵袭作用的影响[J]. 山东大学学报 (医学版), 2020, 58(7): 32 -37 .
[6] 李宁,李娟,谢艳,李培龙,王允山,杜鲁涛,王传新. 长链非编码RNA AL109955.1在80例结直肠癌组织中的表达及对细胞增殖与迁移侵袭的影响[J]. 山东大学学报 (医学版), 2020, 58(7): 38 -46 .
[7] 史爽,李娟,米琦,王允山,杜鲁涛,王传新. 胃癌miRNAs预后风险评分模型的构建与应用[J]. 山东大学学报 (医学版), 2020, 58(7): 47 -52 .
[8] 肖娟,肖强,丛伟,李婷,丁守銮,张媛,邵纯纯,吴梅,刘佳宁,贾红英. 两种甲状腺超声数据报告系统诊断效能的比较[J]. 山东大学学报 (医学版), 2020, 58(7): 53 -59 .
[9] 丁祥云,于清梅,张文芳,庄园,郝晶. 胰岛素样生长因子II在84例多囊卵巢综合征患者颗粒细胞中的表达和促排卵结局的相关性[J]. 山东大学学报 (医学版), 2020, 58(7): 60 -66 .
[10] 徐玉香,刘煜东,张蓬,段瑞生. 101例脑小血管病患者脑微出血危险因素的回顾性分析[J]. 山东大学学报 (医学版), 2020, 58(7): 67 -71 .
版权所有 © 2018 《山东大学学报(医学版)》编辑部　
地址:山东大学科技期刊社（济南市历城区山大南路27号山东大学中心校区明德楼B座721室） 电话: 0531-88366918 E-mail: xbyxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发