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。
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.
作者
李伟汉
侯北平
胡飞阳
朱必宏
LI Weihan;HOU Beiping;HU Feiyang;ZHU Bihong(School of Automation and Electrical Engineering,Zhejiang University of Science and Technology,Hangzhou 310023,Zhejiang,China)
出处
《应用科学学报》
CAS
CSCD
北大核心
2023年第6期1004-1018,共15页
Journal of Applied Sciences
基金
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。
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
magnetic resonance imaging
the greatest difference of brain region
multimodal fusion
clinical markers
ResNet
