基于脑部磁共振图像三维局部模式变换特征提取进行阿尔茨海默病病程预测分类

doi:10.11938/cjmr20182686

摘要/Abstract

摘要： 本文提出一种三维局部模式变换提取进行纹理特征并与常规特征相融合的方法，基于脑部磁共振图像，对认知功能正常的健康人体（CN）、轻度认知障碍（MCI）患者和阿尔茨海默病（AD）患者进行预测分类.首先对46例CN对照组、61例MCI患者和25例AD患者的脑部磁共振图像提取感兴趣区域，然后提取双侧海马体组织、灰质和白质的三维局部模式变换纹理特征和常规特征，并将两类特征融合，使用支持向量机分类算法进行分类.结果显示利用本方法，基于双侧海马体组织对AD组和CN组进行分类的准确率为88.73%、敏感度为78.00%、特异度为95.7%、受试者工作特征（ROC）曲线下面积（AUC）为0.886 5；基于灰质的准确率为85.92%、敏感度为80.00%、特异度为86.6%、AUC为0.854 3.这证明基于海马体磁共振图像，利用本文提出的改进三维局部模式变换提取的纹理特征进行阿尔茨海默病病程分类效果较好，融合常规特征后更可提高分类预测的精度.

关键词: 脑部磁共振图像, 纹理特征, 三维局部模式变换, 阿尔茨海默病, 分类

Abstract: A classification method was developed to differentiate cognitive normal controls (CN), mild cognitive impairment (MCI) patients and Alzheimer's disease (AD) patients from the magnetic resonance (MR) image data. Three-dimensional (3D) local pattern transformation was used in the proposed method to obtain texture features, which were then fused with the conventional image features for the classification purposes. Region of interests (i.e., bilateral hippocampus, gray matter and white matter) were selected from the MR images of 46 CN, 61 MCI patients and 25 AD patients, from which the 3D local pattern transformation texture features and conventional image features were extracted, fused and used for classification with the support vector machine. It was demonstrated that the accuracy, sensitivity, specificity and area under the curve (AUC) were 88.73%, 78.00%, 95.7% and 0.886 5, respectively, for the fused texture feature/conventional image features in bilateral hippocampus of CN controls and AD patients. In comparison, the fused features in the gray matter gave an accuracy, sensitivity, specificity and AUC of 85.92%, 80.00%, 86.6% and 0.854 3, respectively. It is concluded that the texture features extracted from 3D local pattern transform in hippocampus could be used in conjunction with the conventional image features for better classification of the course of Alzheimer's disease.

Key words: brain magnetic resonance image, texture feature, three-dimensional local pattern transform, Alzheimer's disease, classification

中图分类号:

O482.53

孙京文, 闫士举, 韩勇森, 宋成利. 基于脑部磁共振图像三维局部模式变换特征提取进行阿尔茨海默病病程预测分类[J]. 波谱学杂志, 2019, 36(3): 268-277.

SUN Jing-wen, YAN Shi-ju, HAN Yong-sen, SONG Cheng-li. Classifying the Course of Alzheimer's Disease with Brain MR Images and a Method Based on Three-Dimensional Local Pattern Transformation[J]. Chinese Journal of Magnetic Resonance, 2019, 36(3): 268-277.

参考文献

[1] SAMI S, WILLIAMS N, HUGHES L E, et al. Neurophysiological signatures of Alzheimer's disease and frontotemporal lobar degeneration:pathology versus phenotype[J]. Brain, 2018, 141(8):2500-2510.
[2] KIM H, LEE J U, SONG S, et al. A shape-code nanoplasmonic biosensor for multiplex detection of Alzheimer's disease biomarkers[J]. Biosens Bioelectron, 2018, 101:96-102.
[3] ALZHEIMEI'S ASSOCIATION. 2018 Alzheimer's disease facts and figures[OL]. http://www.alz.org/alzheimers-dementia/facts-figures.
[4] ZHANG Y D, WANG S H, PHILLIPS P, et al. Detection of Alzheimer's disease and mild cognitive impairment based on structural volumetric MR images using 3D-DWT and WTA-KSVM trained by PSOTVAC[J]. Biomed Signal Proces, 2015, 21:58-73.
[5] XIA H, LIU W F, WANG X, et al. Comparative study of two-dimensional and three-dimensional texture analysis of brain MR images in patients with Alzheimer's disease[J]. Journal of Beihua University (Nature), 2013, 14(5):553-556.夏翃, 刘卫芳, 王旭, 等. 阿尔茨海默病患者脑MR图像二维及三维纹理分析比较研究[J]. 北华大学学报(自然), 2013, 14(5):553-556.
[6] LI X, TONG L Z, ZHOU X X, et al. Classification of Alzheimer's disease and mild cognitive impairment based on three-dimensional texture features of MR images[J]. Chinese Medical Imaging Technology, 2011, 27(5):1047-1051.李昕, 童隆正, 周晓霞, 等. 基于MR图像三维纹理特征的阿尔茨海默病和轻度认知障碍的分类[J]. 中国医学影像技术, 2011, 27(5):1047-1051.
[7] YU L, XIA H, LIU W F. Classification of Alzheimer's disease and healthy controls based on three-dimensional texture features of hippocampus based on magnetic resonance images[J]. Journal of Biomedical Engineering, 2016(6):1090-1094.于鲁, 夏翃, 刘卫芳. 基于磁共振图像海马三维纹理特征的阿尔茨海默病及健康对照的分类研究[J]. 生物医学工程学杂志, 2016(6):1090-1094.
[8] JONGKREANGKRAI C, VICHIANIN Y, TOCHAROENCHAI C, et al. Computer-aided classification of Alzheimer's disease based on support vector machine with combination of cerebral image features in MRI[J]. Journal of Physics:Conference Series, 2016, 694(1):012036.
[9] JAISWAL A K, BANKA H. Local pattern transformation based feature extraction techniques for classification of epileptic EEG signals[J]. Biomed Signal Proces, 2017, 34:81-92.
[10] HARALICK R M, SHANMUGAM K, DINSTEIN I H. Textural features for image classification[J]. IEEE T Syst Man Cy, 1973, smc-3(6):610-621.
[11] THIBAULT G, ANGULO J, MEYER F. Advanced statistical matrices for texture characterization:Application to DNA chromatin and microtubule network classification[C]//IEEE International Conference on Image Processing. 2011.
[12] JOACHIMS T. Making large-scale SVM learning practical[R]//Technische Universität Dortmund, Sonderforschungsbereich 475:Komplexitätsreduktion in Multivariaten Datenstrukturen, 1998.
[13] ZHANG H M, CHEN S Z. A new brain function imaging analysis method-Statistical parametric mapping(SPM)[J]. Chinese Medical Imaging Technology, 2002, 18(7):711-713.张海敏, 陈盛祖. 一种新的脑功能显像分析法-统计参数图(SPM)[J]. 中国医学影像技术, 2002, 18(7):711-713.
[14] OJALA T, PIETIKÄINEN M, MÄENPÄÄ T. Gray scale and rotation invariant texture classification with local binary patterns[C]//European Conference on Computer Vision. Springer, Berlin, Heidelberg, 2000.
[15] TAN X Y, TRIGGS B. Enhanced local texture feature sets for face recognition under difficult lighting conditions[J]. IEEE Trans Image Process, 2010, 19(6):1635-1650.
[16] LI M W, OISHI K, HE X H, et al. An efficient approach for differentiating Alzheimer's disease from normal elderly based on multicenter MRI using gray-level invariant features[J]. PloS One, 2014, 9(8):e105563.
[17] MURALA S, WU Q M J. Spherical symmetric 3D local ternary patterns for natural, texture and biomedical image indexing and retrieval[J]. Neurocomputing, 2015, 149(C):1502-1514.
[18] MORGADO P, SILVEIRA M, MARQUES J S. Diagnosis of Alzheimer's disease using 3D local binary patterns[J]. Computer Methods in Biomechanics & Biomedical Engineering Imaging & Visualization, 2013, 1(1):2-12.
[19] HOLMES G, DONKIN A, WITTEN I H. WEKA:a machine learning workbench[C]//Brisbane:Proceedings of ANZⅡS'94-Australian New Zealand Intelligent Information Systems Conference, 1994. doi:10.1109/ANZⅡS.1994.396988.
[20] ALTAF M A B, TILLAK J, KIFLE Y, et al. A 1.83µJ/classification nonlinear support-vector-machine-based patient-specific seizure classification SoC[C]//IEEE International Solid-State Circuits Conference Digest of Technical Papers. 2013:100-101.
[21] CHIK Z, ALJANABI Q A, KASA A, et al. Tenfold cross validation artificial neural network modeling of the settlement behavior of a stone column under a highway embankment[J]. Arab J Geosci, 2014, 7(11):4877-4887.
[22] SONG Y, XIE H B, YANG G. Segmented dictionary learning algorithm for compressed perceptual magnetic resonance imaging[J]. Chinese J Magn Reson, 2016, 33(4):559-569.宋阳, 谢海滨, 杨光. 用于压缩感知磁共振成像的分割字典学习算法[J]. 波谱学杂志, 2016, 33(4):559-569.
[23] ZHU X T, HE X B, LIU Y, et al. Semi-automatic region division and cell counting method for simple brain slice images[J]. Chinese J Magn Reson, 2018, 35(2):133-140.朱续涛, 何晓斌, 刘悦, 等. 一种简易的脑片图像的半自动区域划分及细胞计数方法[J]. 波谱学杂志, 2018, 35(2):133-140.