The advantages of structural magnetic resonance imaging(sMRI)-based multidimensional tensor morphological features in brain disease research are the high sensitivity and resolution of sMRI to comprehensively capture t...The advantages of structural magnetic resonance imaging(sMRI)-based multidimensional tensor morphological features in brain disease research are the high sensitivity and resolution of sMRI to comprehensively capture the key structural information and quantify the structural deformation.However,its direct application to regression analysis of high-dimensional small-sample data for brain age prediction may cause“dimensional catastrophe”.Therefore,this paper develops a brain age prediction method for high-dimensional small-sample data based on sMRI multidimensional morphological features and constructs brain age gap estimation(BrainAGE)biomarkers to quantify abnormal aging of key subcortical structures by extracting subcortical structural features for brain age prediction,which can then establish statistical analysis models to help diagnose Alzheimer’s disease and monitor health conditions,intervening at the preclinical stage.展开更多
主观性耳鸣发病机制复杂,其发生不仅局限在听觉通路的异常,非经典通路的中枢可塑性变化也参与其中。随着影像学技术的发展,越来越多的学者试图利用结构磁共振成像(structural Magnetic Resonance Imaging,sMRI)和磁共振弥散张量成像(dif...主观性耳鸣发病机制复杂,其发生不仅局限在听觉通路的异常,非经典通路的中枢可塑性变化也参与其中。随着影像学技术的发展,越来越多的学者试图利用结构磁共振成像(structural Magnetic Resonance Imaging,sMRI)和磁共振弥散张量成像(diffusion tensor imaging,DTI)对主观性耳鸣中枢机制进行探索。本文总结sMRI和DTI两种技术运用于主观性耳鸣中的研究进展,以期为耳鸣的发病机制及治疗提供新思路。展开更多
Background:There is an urgent need to understand the pathways and processes underlying Alzheimer's disease(AD)for early diagnosis and development of effective treatments.This study was aimed to investigate Alzheim...Background:There is an urgent need to understand the pathways and processes underlying Alzheimer's disease(AD)for early diagnosis and development of effective treatments.This study was aimed to investigate Alzheimer's dementia using an unsupervised lipid,protein and gene multi-omics integrative approach.Methods:A lipidomics dataset comprising 185 AD patients,40 mild cognitive impairment(MCI)individuals and 185 controls,and two proteomics datasets(295 AD,159 MCI and 197 controls)were used for weighted gene CO-expression network analyses(WGCNA).Correlations of modules created within each modality with clinical AD diagnosis,brain atrophy measures and disease progression,as well as their correlations with each other,were analyzed.Gene ontology enrichment analysis was employed to examine the biological processes and molecular and cellular functions of protein modules associated with AD phenotypes.Lipid species were annotated in the lipid modules associated with AD phenotypes.The associations between established AD risk loci and the lipid/protein modules that showed high correlation with AD phenotypes were also explored.Results:Five of the 20 identified lipid modules and five of the 17 identified protein modules were correlated with clinical AD diagnosis,brain atrophy measures and disease progression.The lipid modules comprising phospholipids,triglycerides,sphingolipids and cholesterol esters were correlated with AD risk loci involved in immune response and lipid metabolism.The five protein modules involved in positive regulation of cytokine production,neutrophil-mediated immunity,and humoral immune responses were correlated with AD risk loci involved in immune and complement systems and in lipid metabolism(the APOE ε4 genotype).Conclusions:Modules of tightly regulated lipids and proteins,drivers in lipid homeostasis and innate immunity,are strongly associated with AD phenotypes.展开更多
Background:Alzheimer’s disease(AD)is one of the most common neurodegenerative disorders in the elderly.Although numerous structural magnetic resonance imaging(sMRI)studies have reported diagnostic models that could d...Background:Alzheimer’s disease(AD)is one of the most common neurodegenerative disorders in the elderly.Although numerous structural magnetic resonance imaging(sMRI)studies have reported diagnostic models that could distinguish AD from normal controls(NCs)with 80–95%accuracy,limited efforts have been made regarding the clinically practical computer-aided diagnosis(CAD)system for AD.Objective:To explore the potential factors that hinder the clinical translation of the AD-related diagnostic mod-els based on sMRI.Methods:To systematically review the diagnostic models for AD based on sMRI,we identified relevant studies published in the past 15 years on PubMed,Web of Science,Scopus,and Ovid.To evaluate the heterogeneity and publication bias among those studies,we performed subgroup analysis,meta-regression,Begg’s test,and Egger’s test.Results:According to our screening criterion,101 studies were included.Our results demonstrated that high diagnostic accuracy for distinguishing AD from NC was obtained in recently published studies,accompanied by significant heterogeneity.Meta-analysis showed that many factors contributed to the heterogeneity of high diagnostic accuracy of AD using sMRI,which included but was not limited to the following aspects:(i)different datasets;(ii)different machine learning models,e.g.traditional machine learning or deep learning model;(iii)different cross-validation methods,e.g.k-fold cross-validation leads to higher accuracies than leave-one-out cross-validation,but both overestimate the accuracy when compared to validation in independent samples;(iv)different sample sizes;and(v)the publication times.We speculate that these complicated variables might be the adverse factor for developing a clinically applicable system for the early diagnosis of AD.Conclusions:Our findings proved that previous studies reported promising results for classifying AD from NC with different models using sMRI.However,considering the many factors hindering clinical radiology practice,there would still be a long way to go to improve.展开更多
基金supported by China Postdoctoral Science Foundation(No.2022M720434)。
文摘The advantages of structural magnetic resonance imaging(sMRI)-based multidimensional tensor morphological features in brain disease research are the high sensitivity and resolution of sMRI to comprehensively capture the key structural information and quantify the structural deformation.However,its direct application to regression analysis of high-dimensional small-sample data for brain age prediction may cause“dimensional catastrophe”.Therefore,this paper develops a brain age prediction method for high-dimensional small-sample data based on sMRI multidimensional morphological features and constructs brain age gap estimation(BrainAGE)biomarkers to quantify abnormal aging of key subcortical structures by extracting subcortical structural features for brain age prediction,which can then establish statistical analysis models to help diagnose Alzheimer’s disease and monitor health conditions,intervening at the preclinical stage.
文摘Background:There is an urgent need to understand the pathways and processes underlying Alzheimer's disease(AD)for early diagnosis and development of effective treatments.This study was aimed to investigate Alzheimer's dementia using an unsupervised lipid,protein and gene multi-omics integrative approach.Methods:A lipidomics dataset comprising 185 AD patients,40 mild cognitive impairment(MCI)individuals and 185 controls,and two proteomics datasets(295 AD,159 MCI and 197 controls)were used for weighted gene CO-expression network analyses(WGCNA).Correlations of modules created within each modality with clinical AD diagnosis,brain atrophy measures and disease progression,as well as their correlations with each other,were analyzed.Gene ontology enrichment analysis was employed to examine the biological processes and molecular and cellular functions of protein modules associated with AD phenotypes.Lipid species were annotated in the lipid modules associated with AD phenotypes.The associations between established AD risk loci and the lipid/protein modules that showed high correlation with AD phenotypes were also explored.Results:Five of the 20 identified lipid modules and five of the 17 identified protein modules were correlated with clinical AD diagnosis,brain atrophy measures and disease progression.The lipid modules comprising phospholipids,triglycerides,sphingolipids and cholesterol esters were correlated with AD risk loci involved in immune response and lipid metabolism.The five protein modules involved in positive regulation of cytokine production,neutrophil-mediated immunity,and humoral immune responses were correlated with AD risk loci involved in immune and complement systems and in lipid metabolism(the APOE ε4 genotype).Conclusions:Modules of tightly regulated lipids and proteins,drivers in lipid homeostasis and innate immunity,are strongly associated with AD phenotypes.
基金supported by the Beijing Natural Science Funds for Distinguished Young Scholars(No.JQ20036)the Fundamental Research Funds for the Central Universities(No.2021XD-A03-1)the National Natural Science Foundation of China(Nos.81871438 and 82172018).
文摘Background:Alzheimer’s disease(AD)is one of the most common neurodegenerative disorders in the elderly.Although numerous structural magnetic resonance imaging(sMRI)studies have reported diagnostic models that could distinguish AD from normal controls(NCs)with 80–95%accuracy,limited efforts have been made regarding the clinically practical computer-aided diagnosis(CAD)system for AD.Objective:To explore the potential factors that hinder the clinical translation of the AD-related diagnostic mod-els based on sMRI.Methods:To systematically review the diagnostic models for AD based on sMRI,we identified relevant studies published in the past 15 years on PubMed,Web of Science,Scopus,and Ovid.To evaluate the heterogeneity and publication bias among those studies,we performed subgroup analysis,meta-regression,Begg’s test,and Egger’s test.Results:According to our screening criterion,101 studies were included.Our results demonstrated that high diagnostic accuracy for distinguishing AD from NC was obtained in recently published studies,accompanied by significant heterogeneity.Meta-analysis showed that many factors contributed to the heterogeneity of high diagnostic accuracy of AD using sMRI,which included but was not limited to the following aspects:(i)different datasets;(ii)different machine learning models,e.g.traditional machine learning or deep learning model;(iii)different cross-validation methods,e.g.k-fold cross-validation leads to higher accuracies than leave-one-out cross-validation,but both overestimate the accuracy when compared to validation in independent samples;(iv)different sample sizes;and(v)the publication times.We speculate that these complicated variables might be the adverse factor for developing a clinically applicable system for the early diagnosis of AD.Conclusions:Our findings proved that previous studies reported promising results for classifying AD from NC with different models using sMRI.However,considering the many factors hindering clinical radiology practice,there would still be a long way to go to improve.
