基于低等级嵌入的增强型多模态特征选择模型用于多模态阿尔茨海默病诊断

Zhi Chen;Yongguo Liu;Yun Zhang;Jiajing Zhu;Qiaoqin Li;Xindong Wu
{"title":"基于低等级嵌入的增强型多模态特征选择模型用于多模态阿尔茨海默病诊断","authors":"Zhi Chen;Yongguo Liu;Yun Zhang;Jiajing Zhu;Qiaoqin Li;Xindong Wu","doi":"10.1109/TMI.2024.3464861","DOIUrl":null,"url":null,"abstract":"Identification of Alzheimer’s disease (AD) with multimodal neuroimaging data has been receiving increasing attention. However, the presence of numerous redundant features and corrupted neuroimages within multimodal datasets poses significant challenges for existing methods. In this paper, we propose a feature selection method named Enhanced Multimodal Low-rank Embedding (EMLE) for multimodal AD diagnosis. Unlike previous methods utilizing convex relaxations of the <inline-formula> <tex-math>$\\ell _{{2},{0}}$ </tex-math></inline-formula>-norm, EMLE exploits an <inline-formula> <tex-math>$\\ell _{{2},\\gamma }$ </tex-math></inline-formula>-norm regularized projection matrix to obtain an embedding representation and select informative features jointly for each modality. The <inline-formula> <tex-math>$\\ell _{{2},\\gamma }$ </tex-math></inline-formula>-norm, employing an upper-bounded nonconvex Minimax Concave Penalty (MCP) function to characterize sparsity, offers a superior approximation for the <inline-formula> <tex-math>$\\ell _{{2},{0}}$ </tex-math></inline-formula>-norm compared to other convex relaxations. Next, a similarity graph is learned based on the self-expressiveness property to increase the robustness to corrupted data. As the approximation coefficient vectors of samples from the same class should be highly correlated, an MCP function introduced norm, i.e., matrix <inline-formula> <tex-math>$\\gamma $ </tex-math></inline-formula>-norm, is applied to constrain the rank of the graph. Furthermore, recognizing that diverse modalities should share an underlying structure related to AD, we establish a consensus graph for all modalities to unveil intrinsic structures across multiple modalities. Finally, we fuse the embedding representations of all modalities into the label space to incorporate supervisory information. The results of extensive experiments on the Alzheimer’s Disease Neuroimaging Initiative datasets verify the discriminability of the features selected by EMLE.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"44 2","pages":"815-827"},"PeriodicalIF":0.0000,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Enhanced Multimodal Low-Rank Embedding-Based Feature Selection Model for Multimodal Alzheimer’s Disease Diagnosis\",\"authors\":\"Zhi Chen;Yongguo Liu;Yun Zhang;Jiajing Zhu;Qiaoqin Li;Xindong Wu\",\"doi\":\"10.1109/TMI.2024.3464861\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Identification of Alzheimer’s disease (AD) with multimodal neuroimaging data has been receiving increasing attention. However, the presence of numerous redundant features and corrupted neuroimages within multimodal datasets poses significant challenges for existing methods. In this paper, we propose a feature selection method named Enhanced Multimodal Low-rank Embedding (EMLE) for multimodal AD diagnosis. Unlike previous methods utilizing convex relaxations of the <inline-formula> <tex-math>$\\\\ell _{{2},{0}}$ </tex-math></inline-formula>-norm, EMLE exploits an <inline-formula> <tex-math>$\\\\ell _{{2},\\\\gamma }$ </tex-math></inline-formula>-norm regularized projection matrix to obtain an embedding representation and select informative features jointly for each modality. The <inline-formula> <tex-math>$\\\\ell _{{2},\\\\gamma }$ </tex-math></inline-formula>-norm, employing an upper-bounded nonconvex Minimax Concave Penalty (MCP) function to characterize sparsity, offers a superior approximation for the <inline-formula> <tex-math>$\\\\ell _{{2},{0}}$ </tex-math></inline-formula>-norm compared to other convex relaxations. Next, a similarity graph is learned based on the self-expressiveness property to increase the robustness to corrupted data. As the approximation coefficient vectors of samples from the same class should be highly correlated, an MCP function introduced norm, i.e., matrix <inline-formula> <tex-math>$\\\\gamma $ </tex-math></inline-formula>-norm, is applied to constrain the rank of the graph. Furthermore, recognizing that diverse modalities should share an underlying structure related to AD, we establish a consensus graph for all modalities to unveil intrinsic structures across multiple modalities. Finally, we fuse the embedding representations of all modalities into the label space to incorporate supervisory information. The results of extensive experiments on the Alzheimer’s Disease Neuroimaging Initiative datasets verify the discriminability of the features selected by EMLE.\",\"PeriodicalId\":94033,\"journal\":{\"name\":\"IEEE transactions on medical imaging\",\"volume\":\"44 2\",\"pages\":\"815-827\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on medical imaging\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10684737/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on medical imaging","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10684737/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

利用多模态神经成像数据识别阿尔茨海默病(AD)已受到越来越多的关注。然而,多模态数据集中存在大量冗余特征和损坏的神经图像,这给现有方法带来了巨大挑战。在本文中,我们提出了一种名为增强多模态低秩嵌入(EMLE)的特征选择方法,用于多模态 AD 诊断。与以往利用ℓ2,0-norm 的凸松弛的方法不同,EMLE 利用ℓ2,γ-norm 正则化投影矩阵获得嵌入表示,并为每种模态联合选择信息特征。ℓ2,γ-norm采用上界非凸最小凹惩罚(MCP)函数来表征稀疏性,与其他凸松弛相比,ℓ2,0-norm提供了更优越的近似值。接下来,根据自表达特性学习相似性图,以提高对损坏数据的鲁棒性。由于同一类样本的近似系数向量应高度相关,因此采用了 MCP 函数引入的规范,即矩阵 γ 规范,来约束图的秩。此外,考虑到不同模态应共享与注意力缺失有关的潜在结构,我们为所有模态建立了一个共识图,以揭示跨多种模态的内在结构。最后,我们将所有模态的嵌入表征融合到标签空间中,以纳入监督信息。在阿尔茨海默病神经成像计划数据集上进行的大量实验结果验证了 EMLE 所选特征的可辨别性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Enhanced Multimodal Low-Rank Embedding-Based Feature Selection Model for Multimodal Alzheimer’s Disease Diagnosis
Identification of Alzheimer’s disease (AD) with multimodal neuroimaging data has been receiving increasing attention. However, the presence of numerous redundant features and corrupted neuroimages within multimodal datasets poses significant challenges for existing methods. In this paper, we propose a feature selection method named Enhanced Multimodal Low-rank Embedding (EMLE) for multimodal AD diagnosis. Unlike previous methods utilizing convex relaxations of the $\ell _{{2},{0}}$ -norm, EMLE exploits an $\ell _{{2},\gamma }$ -norm regularized projection matrix to obtain an embedding representation and select informative features jointly for each modality. The $\ell _{{2},\gamma }$ -norm, employing an upper-bounded nonconvex Minimax Concave Penalty (MCP) function to characterize sparsity, offers a superior approximation for the $\ell _{{2},{0}}$ -norm compared to other convex relaxations. Next, a similarity graph is learned based on the self-expressiveness property to increase the robustness to corrupted data. As the approximation coefficient vectors of samples from the same class should be highly correlated, an MCP function introduced norm, i.e., matrix $\gamma $ -norm, is applied to constrain the rank of the graph. Furthermore, recognizing that diverse modalities should share an underlying structure related to AD, we establish a consensus graph for all modalities to unveil intrinsic structures across multiple modalities. Finally, we fuse the embedding representations of all modalities into the label space to incorporate supervisory information. The results of extensive experiments on the Alzheimer’s Disease Neuroimaging Initiative datasets verify the discriminability of the features selected by EMLE.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信