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): 81-87.doi: 10.6040/j.issn.1671-7554.0.2020.0598

• 脑科学与类脑智能研究专题 • 上一篇    下一篇

基于机器学习的脑胶质瘤多模态影像分析

吴强1,2,*(),何泽鲲1,刘琚1,2,崔晓萌1,孙双1,石伟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:2020-04-15 出版日期:2020-08-07 发布日期:2020-08-07
  • 通讯作者: 吴强 E-mail:wuqiang@sdu.edu.cn
  • 作者简介:吴强，工学博士，硕士研究生导师，现任山东大学信息科学与工程学院副教授、脑与类脑科学研究院副院长、中国计算机学会人工智能与模式识别专业委员会通讯委员、山东省人工智能学会理事。主要研究兴趣包括大数据环境下的机器学习理论与应用、医学影像处理、生物医学信号处理、仿脑计算理论。近年来在国际期刊和会议上共发表SCI/EI论文20余篇，申请发明专利10余项，授权3项，先后主持和参与国家自然科学基金、科技部重点研发计划及省部级课题10余项。曾担任多个国际重要期刊和会议论文的评阅人，国家自然科学基金通讯评审专家
  • 基金资助:
    山东大学基本科研业务费专项资金(2017JC013);山东省重大创新工程(2017CXGC1504)

A research on multi-modal MRI analysis based on machine learning for brain glioma

Qiang WU1,2,*(),Zekun HE1,Ju LIU1,2,Xiaomeng CUI1,Shuang SUN1,Wei SHI1   

  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:2020-04-15 Online:2020-08-07 Published:2020-08-07
  • Contact: Qiang WU E-mail:wuqiang@sdu.edu.cn

RichHTML

38

PDF (PC)

567

摘要：

脑部胶质瘤是临床中常见的一种原发性脑肿瘤，具有复发率高、死亡率高以及治愈率低的特点。常规临床诊断主要依靠计算机断层扫描(CT)和磁共振成像(MRI)检查技术进行鉴别。随着成像技术和机器学习方法的不断发展，多模态影像智能分析技术已经逐步成为研究热点，在脑胶质瘤的病灶分割测量、肿瘤分级、预后生存周期预测和基因型辨别等方面具有重要的应用前景。本文重点介绍基于机器学习和多模态影像在脑胶质瘤临床辅助诊断和预后评估中的应用进展。

关键词: 脑部胶质瘤, 机器学习, 多模态磁共振影像, 影像病灶分割, 生存周期预测, 基因型预测

Abstract:

Brain glioma, a common primary brain tumor, has characteristics of high recurrence rate, high death rate and low cure rate. Conventional clinical diagnosis mainly depends on CT and MRI. With the development of imaging technology and machine learning methods, multi-modal image intelligent analysis technology has gradually become a research hotspot, which has an important application prospect in brain glioma lesion segmentation and measurement, tumor classification, overall survival prediction and genotype identification. This paper updates the application of machine learning and multi-modal imaging in the clinical diagnosis and prognosis of brain glioma.

Key words: Brain Glioma, Machine Learning, Multi-modal MRI, Image lesion segmentation, Survival prediction, Genotype prediction

中图分类号: 

  • R574

图1

U-Net网络结构示意图[13]"

图2

多特征提取网络结构示意图[14]"

图3

多特征提取单元、注意力单元、跨层连接等结构示意图[14]"

1 Holland EC . Progenitor cells and glioma formation[J]. Curr Opin Neurol, 2011, 14 (6): 683- 688.
doi: 10.1097/00019052-200112000-00002
2 国家卫生健康委员会医政医管局. 脑胶质瘤诊疗规范(2018年版)[J]. 中华神经外科杂志, 2019, 35 (3): 217.
3 Menze BH, Van Leemput K, Lashkari D, et al. A generative model for brain tumor segmentation in multi-modal images[C]. Medical Image Computing and Computer-Assisted Intervention, 2010: 151-159.
4 Kaus MR , Warfield SK , Nabavi A , et al. Automated segmentation of MR images of brain tumors[J]. Radiology, 2001, 218 (2): 586- 591.
doi: 10.1148/radiology.218.2.r01fe44586
5 Prastawa M , Bullitt E , Moon N , et al. Automatic brain tumor segmentation by subject specific modification of atlas priors1[J]. Acad Radiol, 2003, 10 (12): 1341- 1348.
doi: 10.1016/S1076-6332(03)00506-3
6 Corso JJ , Sharon E , Dube S , et al. Efficient multilevel brain tumor segmentation with integrated bayesian model classification[J]. IEEE Trans Med Imaging, 2008, 27 (5): 629- 640.
doi: 10.1109/TMI.2007.912817
7 Gering DT, Grimson WE, Kikinis R, et al. Recognizing deviations from normalcy for brain tumor segmentation[C]. Medical Image Computing and Computer-Assisted Intervention, 2002: 388-395.
8 Lee C, Schmidt M, Murtha A, et al. Segmenting brain tumors with conditional random fields and support vector machines[C]. International Conference on Computer Vision, 2005: 469-478.
9 李晓龙, 帅仁俊. 一种基于形态学的脑肿瘤分割[J]. 液晶与显示, 2014, 30 (1): 157- 162.
LI Xiaolong , SHUAI Renjun . One kind of segmentation of brain tumors based on morphology[J]. Chinese Journal of Liquid Crystals and Displays, 2014, 30 (1): 157- 162.
10 Pereira S , Pinto A , Alves V , et al. Brain tumor segmentation using convolutional neural networks in MRI images[J]. IEEE Trans Med Imaging, 2016, 35 (5): 1240- 1251.
doi: 10.1109/TMI.2016.2538465
11 Havaei M , Davy A , Warde-Farley D , et al. Brain tumor segmentation with deep neural networks[J]. Med Image Anal, 2017, 35: 18- 31.
doi: 10.1016/j.media.2016.05.004
12 李健, 罗蔓, 罗晓, 等. 基于多尺度卷积神经网络的磁共振成像脑肿瘤分割研究[J]. 中国医学装备, 2016, 13 (2): 25- 28.
LI Jian , LUO Man , LUO Xiao , et al. Research on the application of brain tumor segmentation of MRI based on multi-scale convolutional neural networks[J]. China Medical Equipment, 2016, 13 (2): 25- 28.
13 Ronneberger O, Fischer P, Brox T, et al. U-Net: Convolutional Networks for Biomedical Image Segmentation[C]. Medical Image Computing and Computer-Assisted Intervention, 2015: 234-241.
14 Shi W, Pang ES, Wu Q, et al. Brain tumor segmentation using dense channels 2D U-net and Multiple Feature Extraction Network[C]. MICCAI BrainLes, 2020: 273-283.
15 Dempsey MF , Condon B , Hadley DM , et al. Measurement of tumor "size" in recurrent malignant glioma: 1D, 2D, or 3D?[J]. AJNR Am J Neuroradiol, 2005, 26 (4): 770- 776.
16 Joe BN , Fukui MB , Meltzer CC , et al. Brain tumor volume measurement: comparison of manual and semiautomated methods[J]. Radiology, 1999, 212 (3): 811- 816.
17 Ge C, Qu Q, Gu I Y, et al. 3D Multi-scale convolutional networks for glioma grading using MR images[C]. International Conference on Image Processing, 2018: 141-145.
18 Al-Zurfi AN, Meziane F, Aspin R. A computer-aided diagnosis system for glioma grading using three dimensional texture analysis and machine learning in MRI brain tumour [C]. International Conference on Bio-engineering for Smart Technologies, 2019: 1-5.
19 Lin Y, Wu Y, Pang H, et al. A precise grading method for glioma based on radiomics[C]. Ubiquitous Intelligence and Computing, 2017: 1-6.
20 Alzurfi AN, Meziane F, Aspin R, et al. Automated glioma grading based on an efficient ensemble design of a multiple classifier system using deep iteration neural networks matrix[C]. International Conference on Automation and Computing, 2018: 1-6.
21 Bi X, Liu JG, Cao YS. Classification of low-grade and high-grade glioma using multiparametric radiomics model [C]. Information Technology, Networking, Electronic and Automation Control Conference, 2019: 574-577.
22 Sun P , Wang D , Mok V , et al. Comparison of feature selection methods and machine learning classifiers for radiomics analysis in glioma grading[J]. IEEE Access, 2019, 7: 102010- 102020.
doi: 10.1109/ACCESS.2019.2928975
23 Ge C, Gu IY, Jakola AS, et al. Deep Learning and multi-sensor fusion for glioma classification using multistream 2D convolutional networks[C]. International Conference of the IEEE Engineering in Medicine and Biology Society, 2018: 5894-5897.
24 Wu Y , Hao H , Li J , et al. Four-sequence maximum entropy discrimination algorithm for glioma grading[J]. IEEE Access, 2019, 7: 52246- 52256.
doi: 10.1109/ACCESS.2019.2910849
25 Ye F, Pu J, Wang J, et al. Glioma grading based on 3D multimodal convolutional neural network and privileged learning[C]. Bioinformatics and Biomedicine, 2017: 759-763.
26 Pang H, Liu C, Zhao Z, et al. Glioma grading based on gentle-adaboost algorithm and radiomics[C]. Ubiquitous Intelligence and Computing, 2017: 1-5.
27 Bonte S, Goethals I, Van Holen R, et al. Individual Prediction of brain tumor histological grading using radiomics on structural MRI[C]. Nuclear Science Symposium and Medical Imaging Conference, 2017: 1-3.
28 Latif G, Butt MM, Khan AH, et al. Multiclass brain Glioma tumor classification using block-based 3D Wavelet features of MR images [C]. International Conference on Electrical and Electronic Engineering, 2017: 333-337.
29 Er FC, Firat Z, Kovanlikaya I, et al. Multivariate discriminant analysis of multiparametric brain MRI to differentiate high grade and low grade gliomas—A computer-aided diagnosis development study[C]. Bioinformatics and Bioengineering, 2013: 1-5.
30 张原理, 程豫菲, 崔振杰, 等. 磁共振成像分级胶质瘤的新方法及结果[J]. 现代肿瘤医学, 2017, 25 (24): 4054- 4058.
ZHANG Yuanli , CHENG Yufei , CUI Zhenjie , et al. Ti A new method of magnetic resonance imaging in grading of gliomas and the results[J]. Journal of Modern Oncology, 2017, 25 (24): 4054- 4058.
31 吴聪, 黄中勇, 殷浩, 等. 基于卷积神经网络的脑胶质瘤分级[J]. 湖北工业大学学报, 2017, 32 (4): 60- 64.
32 Wangaryattawanich P, Wang J, Thomas G, et al. Survival analysis of pre-operative GBM patients by using quantitative image features[C]. International Conference on Control Decision and Information Technologies, 2014: 625-627.
33 Agravat R, Raval MS. Prediction of overall survival of brain tumor patients [C]. 2019 IEEE Region 10 Conference, 2019: 31-35.
34 欧阳一彬, 莫业和, 何青龙, 等. 影响脑胶质瘤患者生存和预后的相关因素分析[J]. 河北医药, 2018, 40 (10): 1524- 1526.
doi: 10.3969/j.issn.1002-7386.2018.10.019
OUYANG Yibing , MO Yehe , HE Qinglong , et al. Analysis for related factors influencing the survival and prognosis of patients with brain glioma[J]. Hebei Medical Journal, 2018, 40 (10): 1524- 1526.
doi: 10.3969/j.issn.1002-7386.2018.10.019
35 彭世义, 李艳萍, 陈志萍, 等. WHOⅡ级脑胶质瘤预后影响因素分析[J]. 中国肿瘤临床, 2018, 45 (8): 402- 407.
36 葛培林, 钟云萍. 低级别脑胶质瘤预后分析[J]. 肿瘤防治研究, 2005, 32 (7): 438- 439.
GE Peilin , ZHONG Yunping . Prognosis analysis of low grade gliomas[J]. Cancer Research On Prevention and Treatment, 2005, 32 (7): 438- 439.
37 刘桂云, 江蓉, 徐晨阳, 等. 高级别脑胶质瘤综合治疗后生存分析[J]. 中南大学学报(医学版), 2018, 43 (4): 388- 393.
LIU Guiyun , JIANG Rong , XU Chenyang , et al. Survival analysis for high-grade glioma patients who received comprehensive treatment[J]. Journal of Central South University(Medical Science), 2018, 43 (4): 388- 393.
38 Diller EE, Cao S, Ey B, et al. Predicted disease compositions of human gliomas estimated from multiparametric MRI can predict endothelial proliferation, tumor grade, and overall survival[EB/OL]. [2019-08-06]. https: //arxiv.org/abs/1908.02334v1
39 Goyaouti J, Calmon R, Orlhac F, et al. Can structural MRI radiomics predict DIPG histone H3 mutation and patient overall survival at diagnosis time[C]. IEEE-EMBS International Conference on Biomedical and Health Informatics, 2019: 1-4.
40 Wang S, Dai C, Mo Y, et al. Automatic brain tumor segmentation and biophysics-guided survival prediction[C]. MICCAI BrainLes, 2020: 61-72.
41 Alex V, Safwan M, Krishnamurthi G, et al. Automatic segmentation and overall survival prediction in gliomas using fully convolutional neural network and texture analysis[C]. MICCAI BrainLes, 2017: 216-225.
42 Chaddad A, Desrosiers C, Toews M, et al. Radiomic analysis of multi-contrast brain MRI for the prediction of survival in patients with glioblastoma multiforme[C]. International Conference of the IEEE Engineering in Medicine and Biology Society, 2016: 4035-4038.
43 Agravat R, Raval MS. Brain tumor segmentation and survival prediction[C]. MICCAI BrainLes, 2020: 338-348.
44 Amian M, Soltaninejad M. Multi-Resolution 3D CNN for MRI brain tumor segmentation and survival prediction[C]. BrainLes, 2019, 2020: 221-230.
45 Chato L, Latifi S. Machine learning and deep learning techniques to predict overall survival of brain tumor patients using MRI images[C]. Bioinformatics and Bioengineering, 2017: 9-14.
46 Chato L, Chow E, Latifi S, et al. Wavelet transform to improve accuracy of a prediction model for overall survival time of brain tumor patients based on MRI images[C]. IEEE International Conference on Healthcare Informatics, 2018: 441-442.
47 熊正平, 杨树仁. 分子影像学[J]. 国际医学放射学杂志, 2002, 25 (3): 131- 134.
48 折刚刚, 郝文炯. 胶质母细胞瘤MGMT启动子甲基化的影像征象研究进展[J]. 中国微侵袭神经外科杂志, 2018, 23 (9): 428- 431.
49 魏炜, 崔洛, 解立志, 等. 基于MRI影像组学预测胶质母细胞瘤MGMT基因启动子甲基化状态的应用[J]. 影像诊断与介入放射学, 2018, 27 (3): 179- 184.
doi: 10.3969/j.issn.1005-8001.2018.03.001
WEI Wei , CUI Luo , XIE Lizhi , et al. MR-based radiomics method for prediction of MGMT promoter methylation in glioblastoma[J]. Diagnostic Imaging & Interventional Radiology, 2018, 27 (3): 179- 184.
doi: 10.3969/j.issn.1005-8001.2018.03.001
50 Mertz L . Molecular imaging probes spy on the body's inner workings: miniaturized microscopes, microbubbles, 7-and 15-T scanners, diffusion-tensor MRI, and other molecular-imaging technologies are pushing molecular imaging into the future[J]. IEEE Pulse, 2013, 4 (1): 18- 22.
doi: 10.1109/MPUL.2012.2228809
51 Liu T, Wu G, Yu J, et al. A mRMRMSRC feature selection method for radiomics approach[C]. International Conference of the IEEE Engineering in Medicine and Biology Society, 2017: 616-619.
52 Paech D , Windschuh J , Oberhollenzer J , et al. Assessing the predictability of IDH mutation and MGMT methylation status in glioma patients using relaxation-compensated multipool CEST MRI at 7.0 T[J]. Neuro Oncol, 2018, 20 (12): 1661- 1671.
doi: 10.1093/neuonc/noy073
53 Lu C , Hsu FT , Hsieh KL , et al. Machine learning-based radiomics for molecular subtyping of gliomas[J]. Clin Cancer Res, 2018, 24 (18): 4429- 4436.
doi: 10.1158/1078-0432.CCR-17-3445
54 Zhou H , Vallieres M , Bai HX , et al. MRI features predict survival and molecular markers in diffuse lower-grade gliomas[J]. Neuro Oncol, 2017, 19 (6): 862- 870.
doi: 10.1093/neuonc/now256
55 Zhang B , Chang K , Ramkissoon S , et al. Multimodal MRI features predict isocitrate dehydrogenase genotype in high-grade gliomas[J]. Neuro Oncol, 2017, 19 (1): 109- 117.
doi: 10.1093/neuonc/now121
56 Chen L , Zhang H , Lu J , et al. Multi-label nonlinear matrix completion with transductive multi-task feature selection for joint MGMT and IDH1 status prediction of patient with high-grade gliomas[J]. IEEE Trans Med Imaging, 2018, 37 (8): 1775- 1787.
doi: 10.1109/TMI.2018.2807590
57 Levner I, Drabycz S, Roldan G, et al. Predicting MGMT Methylation Status of Glioblastomas from MRI Texture[C]. Medical Image Computing and Computer-Assisted Intervention, 2009: 522-530.
58 Chaddad A , Desrosiers C , Abdulkarim B , et al. Predicting the gene status and survival outcome of lower grade glioma patients with multimodal MRI features[J]. IEEE Access, 2019, 7: 75976- 75984.
doi: 10.1109/ACCESS.2019.2920396
59 Ahmad A, Sarkar S, Shah A, et al. Predictive and discriminative localization of IDH genotype in high grade gliomas using deep convolutional neural nets[C]. International Symposium on Biomedical Imaging, 2019: 372-375.
60 Tixier F , Um H , Bermudez D , et al. Preoperative MRI-radiomics features improve prediction of survival in glioblastoma patients over MGMT methylation status alone[J]. Oncotarget, 2019, 10 (6): 660- 672.
doi: 10.18632/oncotarget.26578
61 Wu G , Chen Y , Wang Y , et al. Sparse representation-based radiomics for the diagnosis of brain tumors[J]. IEEE Trans Med Imaging, 2018, 37 (4): 893- 905.
doi: 10.1109/TMI.2017.2776967
[1] 张伟,谭文浩,李贻斌. 基于深度强化学习的四足机器人运动控制发展现状与展望[J]. 山东大学学报 (医学版), 2020, 58(8): 61-66.
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