阿尔茨海默症的多模态分类方法

doi:10.3969/j.issn.0255-8297.2023.06.008

应用科学学报 ›› 2023, Vol. 41 ›› Issue (6): 1004-1018.doi: 10.3969/j.issn.0255-8297.2023.06.008

阿尔茨海默症的多模态分类方法

李伟汉, 侯北平, 胡飞阳, 朱必宏

浙江科技学院自动化与电气工程学院, 浙江杭州 310023

收稿日期:2021-09-27 出版日期:2023-11-30 发布日期:2023-11-30
通信作者: 侯北平,教授,研究方向为图像处理、机器视觉、人工智能。E-mail:bphou@zust.edu.cn E-mail:bphou@zust.edu.cn
基金资助:
浙江省重点研发计划项目(No.2021C04030);浙江省公益技术计划应用研究项目(No.2017C33119)资助

Multi-modal Diagnosis Method of Alzheimer’s Disease

LI Weihan, HOU Beiping, HU Feiyang, ZHU Bihong

School of Automation and Electrical Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, Zhejiang, China

Received:2021-09-27 Online:2023-11-30 Published:2023-11-30

摘要/Abstract

摘要： 目前在阿尔茨海默病(Alzheimer’s disease,AD)、早期轻度认知障碍患者(early mild cognitive impairment,EMCI)和正常人(normal control,NC)的分级诊断中存在着EMCI识别困难、多分类识别率低的问题。针对上述难点,提出一种脑区域特征选取方法,设计了融合残差网络的多模态AD分类模型。首先对三类脑核磁共振影像进行配准;然后采用贝叶斯方法和高斯混合模型分割脑组织,获得灰质信息进行组间差异性分析,确定脑图像选取区域;最后将脑图像与生物标志物一起输入分类模型。实验表明:与传统方法相比,本方法脑图像分类准确率提高5%以上,融合生物标志物和脑图像的多模态分类中AD&NC、AD&EMCI、AD&EMCI&NC分类准确率分别为95.5%、93.5%、86.3%,均高于任意单模态网络,验证了本方法的有效性。

关键词: 核磁共振影像, 最大差异脑区域, 多模态融合, 临床标志物, 残差网络

Abstract: The current grading methods for Alzheimer’s disease（AD）, Early Mild Cognitive Impairment（EMCI）, and Normal Control（NC） suffer from difficulties recognizing EMCI and low multi-classification accuracy. To address these issues, a brain region feature extraction method is proposed, and an AD multi-modal classification model is designed with a fusion of ResNet network. Brain MRI images are spatially registered, segmented by Bayesian and Gaussian mixture models to obtain gray matter, the regions with the greatest difference are selected as the feature image area, and images and biomarkers are processed by the classification model. The proposed method improves performance by at least 5% and achieves an accuracy of 95.5%, 93.5%, and 86.3% for AD＆NC, AD＆EMCI,and AD＆EMCI＆NC classification, respectively, surpassing any single-modal network and verifying the effectiveness of this method.

Key words: magnetic resonance imaging, the greatest difference of brain region, multimodal fusion, clinical markers, ResNet

中图分类号:

TP391.4

李伟汉, 侯北平, 胡飞阳, 朱必宏. 阿尔茨海默症的多模态分类方法[J]. 应用科学学报, 2023, 41(6): 1004-1018.

LI Weihan, HOU Beiping, HU Feiyang, ZHU Bihong. Multi-modal Diagnosis Method of Alzheimer’s Disease[J]. Journal of Applied Sciences, 2023, 41(6): 1004-1018.

参考文献

[1] 刘慧瑛,夏兆云,施扬,等.阿尔茨海默病发病机制概述[J].老年医学与保健, 2020, 26(6):1098-1100.Liu H Y, XiA Z Y, Shi Y, et al. Overview of pathogenesis of Alzheimer's disease[J]. Geriatrics&Health Care, 2020, 26(6):1098-1100.(in Chinese)
[2] 王英全,梁景宏,贾瑞霞,等. 2020D2050年中国阿尔茨海默病患病情况预测研究[J].阿尔茨海默病及相关病, 2019, 2(1):289-298.WAnG Y Q, LiAnG J H, JiA R X, et al. Alzheimer disease in China(2015-2050)estimated using the 1%population sampling survey in 2015[J]. Chinese Journal of Alzheimer's Disease and Related Disorders, 2019, 2(1):289-298.(in Chinese)
[3] 张雯艳,陆媛.老年轻度认知功能障碍患者相关病因及治疗的研究进展[J].国际老年医学杂志,2021, 42(1):57-61.ZhAnG W Y, Lu Y. Advances in etiology and treatment of mild cognitive impairment in older people[J]. International Journal of Digestive Diseases, 2021, 42(1):57-61.(in Chinese)
[4] 贺超.核磁共振成像系统原理及MR图像研究[J].云南大学学报(自然科学版), 2010, 32(S1):245-248, 251.HE C. The study of principle of nuclear magnetic resonance imaging and MR image[J]. Journal of Yunnan University(Natural Sciences Edition), 2010, 32(S1):245-248, 251.(in Chinese)
[5] 邓爽,何小海,卿粼波,等.基于改进VGG网络的弱监督细粒度阿尔兹海默症分类方法[J].计算机应用, 2022, 42(1):302-309.DEnG S, HE X H, QinG L B, et al. Weakly supervised fine-grained classification method of Alzheimer's disease based on improved visual geometry group network[J]. Journal of Computer Applications, 2022, 42(1):302-309.(in Chinese)
[6] 张柏雯,林岚,吴水才.基于AlexNet模型的AD分类[J].北京工业大学学报, 2020, 46(1):68-74.ZhAnG B W, Lin L, Wu S C. Efficient Alzheimer's disease classification based on AlexNet model[J]. Journal of Beijing University of Technology, 2020, 46(1):68-74.(in Chinese)
[7] KLEin G, ScoTT D, LEuzy A, et al. Optimized regional analysis to detect longitudinal 18 FRO-948 tau PET change in early AD:neuroimaging/optimal neuroimaging measures for tracking dis-ease progression[J]. Alzheimer's and Dementia, 2020, 16(S5):045765.
[8] 曾安,黄殷,潘丹,等.基于卷积循环神经网络的阿尔茨海默症早期诊断[J].生物医学工程研究,2020, 39(3):249-255.ZEnG A, HuAnG Y, PAn D, et al. Early diagnosis of Alzheimer's disease based on convolutional recurrent neural network[J]. Journal of Biomedical Engineering Research, 2020, 39(3):249-255.(in Chinese)
[9] 陈蕊森,夏军,陈建良,等.基于VBM的AD患者整体认知水平与脑灰质容积关系的横断面研究1[J]. CT理论与应用研究, 2018, 27(6):709-717.ChEn R S, XiA J, ChEn J L, et al. Cross-sectional study on the relationship between integral cognitive level and gray matter volume in patients with Alzheimer's disease based on VBM[J].Computerized Tomography Theory and Applications, 2018, 27(6):709-717.(in Chinese)
[10] JAck C R, BERnsTEin M A, Fox N C, et al. The Alzheimer's disease neuroimaging initiative(ADNI):MRI methods[J]. Journal of Magnetic Resonance Imaging, 2008, 27(4):685-691.
[11] FRisTon K J, AshBuRnER J, KiEBEL S, et al. Statistical parametric mapping:the analysis of funtional brain images[M]. Amsterdam:Elsevier/Academic Press, 2007.
[12] WEiskopF N, LuTTi A, HELMs G, et al. Unified segmentation based correction of R1 brain maps for RF transmit field inhomogeneities(UNICORT)[J]. NeuroImage, 2011, 54(3):2116-2124.
[13] AshBuRnER J, FRisTon K J. Nonlinear spatial normalization using basis functions[J]. Human Brain Mapping, 1999, 7(4):254-266.
[14] AshBuRnER J, FRisTon K J. Unified segmentation[J]. NeuroImage, 2005, 26(3):839-851.
[15] 吕明提,杨志军,张伟. PPARα与阿尔茨海默病的研究进展[J].生物化学与生物物理进展, 2021,48(8):866-874.LüM T, YAnG Z J, ZhAnG W. Research progress of PPARα and Alzheimer's disease[J].Progress in Biochemistry and Biophysics, 2021, 48(8):866-874.(in Chinese)
[16] BAnGEn K J, SMRinov D S, DELAno W L, et al. Arterial stiffening acts synergistic aly with APOE genotype and AD biomarker status to influence memory in older adults without dementia[J]. Alzheimer's Research&Therapy, 2021, 13(1):1-11.
[17] 刘建强,王晴,井超.载脂蛋白E基因多态性与阿尔茨海默病的相关性研究[J].神经损伤与功能重建, 2016, 11(3):227-229.Liu J Q, WAnG Q, JinG C. Correlation between apolipoprotein E gene polymorphisms and alzheimer's disease[J]. Neural Injury and Functional Reconstruction, 2016, 11(3):227-229.(in Chinese)
[18] HE K M, ZhAnG X Y, REn S Q, et al. Deep residual learning for image recognition[C]//2016IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), 2016:770-778.
[19] ChuA E, NAvARATnAM A V, ST LEGER D, et al. Comparison of MRI and CT in the evaluation of unilateral maxillary sinus opacification[J]. Radiology Research and Practice, 2021, 2021:1-10.
[20] KinGMA D P, BA J. Adam:a method for stochastic optimization[DB/OL]. 2014[2021-09-27].https://arxiv.org/abs/1412.6980.

阿尔茨海默症的多模态分类方法

Multi-modal Diagnosis Method of Alzheimer’s Disease

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	魏洁玲, 马秀丽, 金彦亮, 王瑞. 基于VPN通道下的加密流量分类算法[J]. 应用科学学报, 2023, 41(4): 646-656.
[2]	倪翠, 王朋, 张广渊, 李克峰. 一种基于双重网络模型的单幅图像超分辨率方法[J]. 应用科学学报, 2021, 39(2): 321-329.
[3]	吴韵清, 吴鹏, 陈北京, 鞠兴旺, 高野. 基于残差全卷积网络的图像拼接定位算法[J]. 应用科学学报, 2019, 37(5): 651-662.
[4]	李欣, 唐文莉, 杨博. 利用深度残差网络的高分遥感影像语义分割[J]. 应用科学学报, 2019, 37(2): 282-290.
[5]	郭戈平西建张涛. 基于概念选择和重要性度量的多模态语义融合[J]. 应用科学学报, 2010, 28(3): 266-270.