Prediction and classification of Alzheimer disease based on quantification of MRI deformation.
Ontology highlight
ABSTRACT:
SUBMITTER: Long X
PROVIDER: S-EPMC5338815 | biostudies-literature | 2017
REPOSITORIES: biostudies-literature
Publications
Prediction and classification of Alzheimer disease based on quantification of MRI deformation.
Long Xiaojing X Chen Lifang L Jiang Chunxiang C Zhang Lijuan L
PloS one 20170306 3
Detecting early morphological changes in the brain and making early diagnosis are important for Alzheimer's disease (AD). High resolution magnetic resonance imaging can be used to help diagnosis and prediction of the disease. In this paper, we proposed a machine learning method to discriminate patients with AD or mild cognitive impairment (MCI) from healthy elderly and to predict the AD conversion in MCI patients by computing and analyzing the regional morphological differences of brain between ...[more]
Similar Datasets
Project description:Late-onset Alzheimer's disease (LOAD) is the most common multifactorial neurodegenerative disease among elderly people. LOAD is heterogeneous, and the symptoms vary among patients. Genome-wide association studies (GWAS) have identified genetic risk factors for LOAD but not for LOAD subtypes. Here, we examined the genetic architecture of LOAD based on Japanese GWAS data from 1947 patients and 2192 cognitively normal controls in a discovery cohort and 847 patients and 2298 controls in an independent validation cohort. Two distinct groups of LOAD patients were identified. One was characterized by major risk genes for developing LOAD (APOC1 and APOC1P1) and immune-related genes (RELB and CBLC). The other was characterized by genes associated with kidney disorders (AXDND1, FBP1, and MIR2278). Subsequent analysis of albumin and hemoglobin values from routine blood test results suggested that impaired kidney function could lead to LOAD pathogenesis. We developed a prediction model for LOAD subtypes using a deep neural network, which achieved an accuracy of 0.694 (2870/4137) in the discovery cohort and 0.687 (2162/3145) in the validation cohort. These findings provide new insights into the pathogenic mechanisms of LOAD.
| S-EPMC10310810 | biostudies-literature
Project description:BackgroundDetermining brain atrophy is crucial for the diagnosis of neurodegenerative diseases. Despite detailed brain atrophy assessments using three-dimensional (3D) T1-weighted magnetic resonance imaging, their practical utility is limited by cost and time. This study introduces deep learning algorithms for quantifying brain atrophy using a more accessible two-dimensional (2D) T1, aiming to achieve cost-effective differentiation of dementia of the Alzheimer's type (DAT) from cognitively unimpaired (CU), while maintaining or exceeding the performance obtained with T1-3D individuals and to accurately predict AD-specific atrophy similarity and atrophic changes [W-scores and Brain Age Index (BAI)].MethodsInvolving 924 participants (478 CU and 446 DAT), our deep learning models were trained on cerebrospinal fluid (CSF) volumes from 2D T1 images and compared with 3D T1 images. The performance of the models in differentiating DAT from CU was assessed using receiver operating characteristic analysis. Pearson's correlation analyses were used to evaluate the relations between 3D T1 and 2D T1 measurements of cortical thickness and CSF volumes, AD-specific atrophy similarity, W-scores, and BAIs.ResultsOur deep learning models demonstrated strong correlations between 2D and 3D T1-derived CSF volumes, with correlation coefficients r ranging from 0.805 to 0.971. The algorithms based on 2D T1 accurately distinguished DAT from CU with high accuracy (area under the curve values of 0.873), which were comparable to those of algorithms based on 3D T1. Algorithms based on 2D T1 image-derived CSF volumes showed high correlations in AD-specific atrophy similarity (r = 0.915), W-scores for brain atrophy (0.732 ≤ r ≤ 0.976), and BAIs (r = 0.821) compared with those based on 3D T1 images.ConclusionDeep learning-based analysis of 2D T1 images is a feasible and accurate alternative for assessing brain atrophy, offering diagnostic precision comparable to that of 3D T1 imaging. This approach offers the advantage of the availability of T1-2D imaging, as well as reduced time and cost, while maintaining diagnostic precision comparable to T1-3D.
| S-EPMC11349618 | biostudies-literature
Project description:Using prediction analysis for microarrays (PAM), peripheral blood mononuclear cells (BMC) gene expression proves useful as predictive markers of sporadic AD. We obtained 90% accuracy for correct AD classification by PAM (36 of 40; four NEC classified as AD) using BMC gene expression. Investigating the contribution of these genes to the pathology of AD and their usefulness as prognostic biomarkers holds promise in the prevention of this devastating disease.
2009-01-12 | GSE4229 | GEO
Project description:Modern machine learning algorithms are increasingly being used in neuroimaging studies, such as the prediction of Alzheimer's disease (AD) from structural MRI. However, finding a good representation for multivariate brain MRI features in which their essential structure is revealed and easily extractable has been difficult. We report a successful application of a machine learning framework that significantly improved the use of brain MRI for predictions. Specifically, we used the unsupervised learning algorithm of local linear embedding (LLE) to transform multivariate MRI data of regional brain volume and cortical thickness to a locally linear space with fewer dimensions, while also utilizing the global nonlinear data structure. The embedded brain features were then used to train a classifier for predicting future conversion to AD based on a baseline MRI. We tested the approach on 413 individuals from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had baseline MRI scans and complete clinical follow-ups over 3 years with the following diagnoses: cognitive normal (CN; n=137), stable mild cognitive impairment (s-MCI; n=93), MCI converters to AD (c-MCI, n=97), and AD (n=86). We found that classifications using embedded MRI features generally outperformed (p<0.05) classifications using the original features directly. Moreover, the improvement from LLE was not limited to a particular classifier but worked equally well for regularized logistic regressions, support vector machines, and linear discriminant analysis. Most strikingly, using LLE significantly improved (p=0.007) predictions of MCI subjects who converted to AD and those who remained stable (accuracy/sensitivity/specificity: =0.68/0.80/0.56). In contrast, predictions using the original features performed not better than by chance (accuracy/sensitivity/specificity: =0.56/0.65/0.46). In conclusion, LLE is a very effective tool for classification studies of AD using multivariate MRI data. The improvement in predicting conversion to AD in MCI could have important implications for health management and for powering therapeutic trials by targeting non-demented subjects who later convert to AD.
| S-EPMC3815961 | biostudies-literature
Project description:BackgroundAlzheimer's is a degenerative dementing disorder that starts with a mild memory impairment and progresses to a total loss of mental and physical faculties. The sooner the diagnosis is made, the better for the patient, as preventive actions and treatment can be started. Although tests such as the Mini-Mental State Tests Examination are usually used for early identification, diagnosis relies on magnetic resonance imaging (MRI) brain analysis.MethodsPublic initiatives such as the OASIS (Open Access Series of Imaging Studies) collection provide neuroimaging datasets openly available for research purposes. In this work, a new method based on deep learning and image processing techniques for MRI-based Alzheimer's diagnosis is proposed and compared with previous literature works.ResultsOur method achieves a balance accuracy (BAC) up to 0.93 for image-based automated diagnosis of the disease, and a BAC of 0.88 for the establishment of the disease stage (healthy tissue, very mild and severe stage).ConclusionsResults obtained surpassed the state-of-the-art proposals using the OASIS collection. This demonstrates that deep learning-based strategies are an effective tool for building a robust solution for Alzheimer's-assisted diagnosis based on MRI data.
| S-EPMC8466762 | biostudies-literature
Project description:ImportanceThere is currently no consensus as to which biomarkers best predict longitudinal tau accumulation at different clinical stages of Alzheimer disease (AD).ObjectiveTo describe longitudinal [18F]RO948 tau positron emission tomography (PET) findings across the clinical continuum of AD and determine which biomarker combinations showed the strongest associations with longitudinal tau PET and best optimized clinical trial enrichment.Design, setting, and participantsThis longitudinal cohort study consecutively enrolled amyloid-β (Aβ)-negative cognitively unimpaired (CU) participants, Aβ-positive CU individuals, Aβ-positive individuals with mild cognitive impairment (MCI), and individuals with AD dementia between September 2017 and November 2020 from the Swedish BioFINDER-2 (discovery cohort) and BioFINDER-1 (validation cohort) studies.ExposuresBaseline plasma and cerebrospinal fluid Aβ42/Aβ40, tau phosphorylated at threonine-217 (p-tau217), p-tau181 and neurofilament light, magnetic resonance imaging, amyloid PET ([18F]flutemetamol), and tau PET ([18F]RO948 in the BioFINDER-2 study; [18F]flortaucipir in the BioFINDER-1 study).Main outcomes and measuresBaseline tau PET standardized uptake value ratio (SUVR) and annual percent change in tau PET SUVR across regions of interest derived using a data-driven approach combining clustering and event-based modeling. Regression models were used to examine associations between individual biomarkers and longitudinal tau PET and to identify which combinations best predicted longitudinal tau PET. These combinations were then entered in a power analysis to examine how their use as an enrichment strategy would affect sample size in a simulated clinical trial.ResultsOf 343 participants, the mean (SD) age was 72.56 (7.24) years, and 157 (51.1%) were female. The clustering/event-based modeling-based approach identified 5 regions of interest (stages). In Aβ-positive CU individuals, the largest annual increase in tau PET SUVR was seen in stage I (entorhinal cortex, hippocampus, and amygdala; 4.04% [95% CI, 2.67%-5.32%]). In Aβ-positive individuals with MCI and with AD dementia, the greatest increases were seen in stages II (temporal cortical regions; 4.45% [95% CI, 3.41%-5.49%]) and IV (certain frontal regions; 5.22% [95% CI, 3.95%-6.49%]), respectively. In Aβ-negative CU individuals and those with MCI, modest change was seen in stage I (1.38% [95% CI, 0.78%-1.99%] and 1.80% [95% CI, 0.76%-2.84%], respectively). When looking at individual predictors and longitudinal tau PET in the stages that showed most change, plasma p-tau217 (R2 = 0.27, P < .005), tau PET (stage I baseline SUVR; R2 = 0.13, P < .05) and amyloid PET (R2 = 0.10, P < .05) were significantly associated with longitudinal tau PET in stage I in Aβ-positive CU individuals. In Aβ-positive individuals with MCI, plasma p-tau217 (R2 = 0.24, P < .005) and tau PET (stage II baseline SUVR; R2 = 0.44, P < .001) were significantly associated with longitudinal tau PET in stage II. Findings were replicated in BioFINDER-1 using longitudinal [18F]flortaucipir. For the power analysis component, plasma p-tau217 with tau PET resulted in sample size reductions of 43% (95% CI, 34%-46%; P < .005) in Aβ-positive CU individuals and of 68% (95% CI, 61%-73%; P < .001) in Aβ-positive individuals with MCI.Conclusions and relevanceIn trials using tau PET as the outcome, plasma p-tau217 with tau PET may prove optimal for enrichment in preclinical and prodromal AD. However, plasma p-tau217 was most important in preclinical AD, while tau PET was more important in prodromal AD.
| S-EPMC8689441 | biostudies-literature
Project description:Structural imaging based on magnetic resonance is an integral part of the clinical assessment of patients with suspected Alzheimer dementia. Prospective data on the natural history of change in structural markers from preclinical to overt stages of Alzheimer disease are radically changing how the disease is conceptualized, and will influence its future diagnosis and treatment. Atrophy of medial temporal structures is now considered to be a valid diagnostic marker at the mild cognitive impairment stage. Structural imaging is also included in diagnostic criteria for the most prevalent non-Alzheimer dementias, reflecting its value in differential diagnosis. In addition, rates of whole-brain and hippocampal atrophy are sensitive markers of neurodegeneration, and are increasingly used as outcome measures in trials of potentially disease-modifying therapies. Large multicenter studies are currently investigating the value of other imaging and nonimaging markers as adjuncts to clinical assessment in diagnosis and monitoring of progression. The utility of structural imaging and other markers will be increased by standardization of acquisition and analysis methods, and by development of robust algorithms for automated assessment.
| S-EPMC2938772 | biostudies-literature
Project description:Objective: Late-life depression (LLD) is associated with development of different types of dementia. Identification of LLD patients, who will develop cognitive decline, i.e., the early stage of dementia would help to implement interventions earlier. The purpose of this study was to assess whether structural brain magnetic resonance imaging (MRI) in LLD patients can predict mild cognitive impairment (MCI) or dementia 1 year prior to the diagnosis. Methods: LLD patients underwent brain MRI at baseline and repeated clinical assessment after 1-year. Structural brain measurements were obtained using Freesurfer software (v. 5.1) from the T1W brain MRI images. MRI-based Random Forest classifier was used to discriminate between LLD who developed MCI or dementia after 1-year follow-up and cognitively stable LLD. Additionally, a previously established Random Forest model trained on 185 patients with Alzheimer's disease (AD) vs. 225 cognitively normal elderly from the Alzheimer's disease Neuroimaging Initiative was tested on the LLD data set (ADNI model). Results: MCI and dementia diagnoses were predicted in LLD patients with 76%/68%/84% accuracy/sensitivity/specificity. Adding the baseline Mini-Mental State Examination (MMSE) scores to the models improved accuracy/sensitivity/specificity to 81%/75%/86%. The best model predicted MCI status alone using MRI and baseline MMSE scores with accuracy/sensitivity/specificity of 89%/85%/90%. The most important region for all the models was right ventral diencephalon, including hypothalamus. Its volume correlated negatively with the number of depressive episodes. ADNI model trained on AD vs. Controls using SV could predict MCI-DEM patients with 67% accuracy. Conclusion: LDD patients developing MCI and dementia can be discriminated from LLD patients remaining cognitively stable with good accuracy based on baseline structural MRI alone. Baseline MMSE score improves prediction accuracy. Ventral diencephalon, including the hypothalamus might play an important role in preservation of cognitive functions in LLD.
| S-EPMC5288688 | biostudies-literature
Project description:Background and purposeEarly stratification of degenerative processes is a prerequisite to warrant therapeutic options in prodromal Alzheimer disease. Our aim was to investigate differences in cerebral macromolecular tissue composition between patients with AD, mild cognitive impairment, and age- and sex-matched healthy controls by using model-based magnetization transfer with a binary spin-bath magnetization transfer model and magnetization transfer ratio at 1.5 T.Materials and methodsWe investigated patients with de novo AD (n=18), MCI (n=18), and CTRLs (n=18). A region-of-interest analysis of the entorhinal cortex, hippocampal head and body, insula, and temporal neocortex was performed with fuzzy clustering to associate every subregion to a cluster representative for each group.ResultsCluster analysis achieved a concordance of 0.92 (50 of 54 subjects) between a combination of the calculated mMT parameters (kf,kr,T2r,F,T2f) in the entorhinal cortex and the neuropsychological diagnosis. The sensitivity and specificity for the discrimination of AD from MCI reached 1 and 0.94, with a positive predictive value of 0.95 and a negative predictive value of 1. Compared with mMT, the concordance for MTR was 0.83 (45 of 54 subjects) with a lower specificity of 0.5 and positive predictive value of 0.67 to discriminate patients with AD and MCI.ConclusionsmMT imaging detects macromolecule-related alterations and allows an improved classification of patients with early AD and MCI compared with MTR.
| S-EPMC7964474 | biostudies-literature
Project description:Anatomical magnetic resonance imaging (MRI), diffusion MRI and resting state functional MRI (rs-fMRI) have been used for Alzheimer's disease (AD) classification. These scans are typically used to build models for discriminating AD patients from control subjects, but it is not clear if these models can also discriminate AD in diverse clinical populations as found in memory clinics. To study this, we trained MRI-based AD classification models on a single centre data set consisting of AD patients (N = 76) and controls (N = 173), and used these models to assign AD scores to subjective memory complainers (N = 67), mild cognitive impairment (MCI) patients (N = 61), and AD patients (N = 61) from a multi-centre memory clinic data set. The anatomical MRI scans were used to calculate grey matter density, subcortical volumes and cortical thickness, the diffusion MRI scans were used to calculate fractional anisotropy, mean, axial and radial diffusivity, and the rs-fMRI scans were used to calculate functional connectivity between resting state networks and amplitude of low frequency fluctuations. Within the multi-centre memory clinic data set we removed scan site differences prior to applying the models. For all models, on average, the AD patients were assigned the highest AD scores, followed by MCI patients, and later followed by SMC subjects. The anatomical MRI models performed best, and the best performing anatomical MRI measure was grey matter density, separating SMC subjects from MCI patients with an AUC of 0.69, MCI patients from AD patients with an AUC of 0.70, and SMC patients from AD patients with an AUC of 0.86. The diffusion MRI models did not generalise well to the memory clinic data, possibly because of large scan site differences. The functional connectivity model separated SMC subjects and MCI patients relatively good (AUC = 0.66). The multimodal MRI model did not improve upon the anatomical MRI model. In conclusion, we showed that the grey matter density model generalises best to memory clinic subjects. When also considering the fact that grey matter density generally performs well in AD classification studies, this feature is probably the best MRI-based feature for AD diagnosis in clinical practice.
| S-EPMC7303669 | biostudies-literature