Multivariate deformation-based analysis of brain atrophy to predict Alzheimer's disease in mild cognitive impairment

Unraveling the gut-brain connection: The association of microbiota-linked structural brain biomarkers with behavior and mental health

AIM

The gut microbiota can influence human behavior. However, due to the massive multiple-testing problem, research into the relationship between microbiome ecosystems and the human brain faces drawbacks. This problem arises when attempting to correlate thousands of gut bacteria with thousands of brain voxels.

METHODS

We performed brain magnetic resonance imaging (MRI) scans on 133 participants and applied machine-learning algorithms (Ridge regressions) combined with permutation tests. Using this approach, we were able to correlate specific gut bacterial families with brain MRI signals, circumventing the difficulties of massive multiple testing while considering sex, age, and body mass index as confounding factors.

RESULTS

The relative abundance (RA) of the Selenomonadaceae, Clostridiaceae, and Veillonellaceae families in the gut was associated with altered cerebellar, visual, and frontal T2-mapping and diffusion tensor imaging measures. Conversely, decreased relative abundance of the Eubacteriaceae family was also linked to T2-mapping values in the cerebellum. Significantly, the brain regions associated with the gut microbiome were also correlated with depressive symptoms and attentional deficits.

CONCLUSIONS

Our analytical strategy offers a promising approach for identifying potential brain biomarkers influenced by gut microbiota. By gathering a deeper understanding of the microbiota-brain connection, we can gain insights into the underlying mechanisms and potentially develop targeted interventions to mitigate the detrimental effects of dysbiosis on brain function and mental health.

Longitudinal Relationship Between Brain Atrophy Patterns, Cognitive Decline, and Cerebrospinal Fluid Biomarkers in Alzheimer's Disease Explored by Orthonormal Projective Non-Negative Matrix Factorization

Background

Longitudinal magnetic resonance imaging (MRI) has been proposed for tracking the progression of Alzheimer's disease (AD) through the assessment of brain atrophy.

Objective

Detection of brain atrophy patterns in patients with AD as the longitudinal disease tracker.

Methods

We used a refined version of orthonormal projective non-negative matrix factorization (OPNMF) to identify six distinct spatial components of voxel-wise volume loss in the brains of 83 subjects with AD from the ADNI3 cohort relative to healthy young controls from the ABIDE study. We extracted non-negative coefficients representing subject-specific quantitative measures of regional atrophy. Coefficients of brain atrophy were compared to subjects with mild cognitive impairment and controls, to investigate the cross-sectional and longitudinal associations between AD biomarkers and regional atrophy severity in different groups. We further validated our results in an independent dataset from ADNI2.

Results

The six non-overlapping atrophy components represent symmetric gray matter volume loss primarily in frontal, temporal, parietal and cerebellar regions. Atrophy in these regions was highly correlated with cognition both cross-sectionally and longitudinally, with medial temporal atrophy showing the strongest correlations. Subjects with elevated CSF levels of TAU and PTAU and lower baseline CSF Aβ42 values, demonstrated a tendency toward a more rapid increase of atrophy.

Conclusions

The present study has applied a transferable method to characterize the imaging changes associated with AD through six spatially distinct atrophy components and correlated these atrophy patterns with cognitive changes and CSF biomarkers cross-sectionally and longitudinally, which may help us better understand the underlying pathology of AD.

Alzheimer's Disease Is Associated with Increased Network Assortativity: Evidence from Metabolic Connectivity

Introduction: Unraveling the network pathobiology in neurodegenerative disorders is a popular and promising field in research. We use a relatively newer network measure of assortativity in metabolic connectivity to understand network differences in patients with Alzheimer's Disease (AD), compared with those with mild cognitive impairment (MCI). Methods: Eighty-three demographically matched patients with dementia (56 AD and 27 MCI) who underwent positron emission tomography-magnetic resonance imaging (PET-MRI) study were recruited for this exploratory study. Global and nodal network measures obtained using the BRain Analysis using graPH theory toolbox were used to derive group-level differences (corrected p < 0.05). The methods were validated in age, and gender-matched 23 cognitively normal, 25 MCI, and 53 AD patients from the publicly available Alzheimer's Disease Neuroimaging Initiative (ADNI) data. Regions that revealed significant differences were correlated with the Addenbrooke's Cognitive Examination-III (ACE-III) scores. Results: Patients with AD revealed significantly increased global assortativity compared with the MCI group. In addition, they also revealed increased modularity and decreased participation coefficient. These findings were validated in the ADNI data. We also found that the regional standard uptake values of the right superior parietal and left superior temporal lobes were proportional to the ACE-III memory subdomain scores. Conclusion: Global errors associated with network assortativity are found in patients with AD, making the networks more regular and less resilient. Since the regional measures of these network errors were proportional to memory deficits, these measures could be useful in understanding the network pathobiology in AD.

Whole-brain structure-function coupling abnormalities in mild cognitive impairment: a study combining amplitude of low-frequency fluctuations and voxel-based morphometry

Alzheimer's disease (AD), one of the leading diseases of the nervous system, is accompanied by symptoms such as loss of memory, thinking and language skills. Both mild cognitive impairment (MCI) and very mild cognitive impairment (VMCI) are the transitional pathological stages between normal aging and AD. While the changes in whole-brain structural and functional information have been extensively investigated in AD, The impaired structure-function coupling remains unknown. The current study employed the OASIS-3 dataset, which includes 53 MCI, 90 VMCI, and 100 Age-, gender-, and education-matched normal controls (NC). Several structural and functional parameters, such as the amplitude of low-frequency fluctuations (ALFF), voxel-based morphometry (VBM), and The ALFF/VBM ratio, were used To estimate The whole-brain neuroimaging changes In MCI, VMCI, and NC. As disease symptoms became more severe, these regions, distributed in the frontal-inf-orb, putamen, and paracentral lobule in the white matter (WM), exhibited progressively increasing ALFF (ALFFNC < ALFFVMCI < ALFFMCI), which was similar to the tendency for The cerebellum and putamen in the gray matter (GM). Additionally, as symptoms worsened in AD, the cuneus/frontal lobe in the WM and the parahippocampal gyrus/hippocampus in the GM showed progressively decreasing structure-function coupling. As the typical focal areas in AD, The parahippocampal gyrus and hippocampus showed significant positive correlations with the severity of cognitive impairment, suggesting the important applications of the ALFF/VBM ratio in brain disorders. On the other hand, these findings from WM functional signals provided a novel perspective for understanding the pathophysiological mechanisms involved In cognitive decline in AD.

A review on Alzheimer's disease classification from normal controls and mild cognitive impairment using structural MR images

Alzheimer's disease (AD) is an irreversible neurodegenerative brain disorder that degrades the memory and cognitive ability in elderly people. The main reason for memory loss and reduction in cognitive ability is the structural changes in the brain that occur due to neuronal loss. These structural changes are most conspicuous in the hippocampus, cortex, and grey matter and can be assessed by using neuroimaging techniques viz. Positron Emission Tomography (PET), structural Magnetic Resonance Imaging (MRI) and functional MRI (fMRI), etc. Out of these neuroimaging techniques, structural MRI has evolved as the best technique as it indicates the best soft tissue contrast and high spatial resolution which is important for AD detection. Currently, the focus of researchers is on predicting the conversion of Mild Cognitive Impairment (MCI) into AD. MCI represents the transition state between expected cognitive changes with normal aging and Alzheimer's disease. Not every MCI patient progresses into Alzheimer's disease. MCI can develop into stable MCI (sMCI, patients are called non-converters) or into progressive MCI (pMCI, patients are diagnosed as MCI converters). This paper discusses the prognosis of MCI to AD conversion and presents a review of structural MRI-based studies for AD detection. AD detection framework includes feature extraction, feature selection, and classification process. This paper reviews the studies for AD detection based on different feature extraction methods and machine learning algorithms for classification. The performance of various feature extraction methods has been compared and it has been observed that the wavelet transform-based feature extraction method would give promising results for AD classification. The present study indicates that researchers are successful in classifying AD from Normal Controls (N_rmC) but, it still requires a lot of work to be done for MCI/ N_rmC and MCI/AD, which would help in detecting AD at its early stage.

Cognitive dysfunction and cerebral volumetric deficits in individuals with Alzheimer's disease, alcohol use disorder, and dual diagnosis

Epidemiological surveys suggest that excessive drinking is associated with higher risk of Alzheimer's disease (AD). The present study utilized data from the National Alzheimer's Coordinating Center to examine cognition as well as gray/white matter and ventricular volumes among participants with AD and alcohol use disorder (AD/AUD, n = 52), AD only (n = 701), AUD only (n = 67), and controls (n = 1283). AUD diagnosis was associated with higher Clinical Dementia Rating Scale Sum of Boxes (CDR-SB) in AD than in non-AD. AD performed worse on semantic fluency and Trail Making Test A + B (TMT A + B) and showed smaller total GMV, WMV, and larger ventricular volume than non-AD. AD had smaller regional GMV in the inferior/superior parietal cortex, hippocampal formation, occipital cortex, inferior frontal gyrus, posterior cingulate cortex, and isthmus cingulate cortex than non-AD. AUD had significantly smaller somatomotor cortical GMV and showed a trend towards smaller volume in the hippocampal formation, relative to non-AUD participants. Misuse of alcohol has an additive effect on dementia severity among AD participants. Smaller hippocampal volume is a common feature of both AD and AUD. Although AD is associated with more volumetric deficits overall, AD and AUD are associated with atrophy in largely distinct brain regions.

Prediction of the progression from mild cognitive impairment to Alzheimer's disease using a radiomics-integrated model

Objective:

This study aimed to build and validate a radiomics-integrated model with whole-brain magnetic resonance imaging (MRI) to predict the progression of mild cognitive impairment (MCI) to Alzheimer’s disease (AD).

Methods:

357 patients with MCI were selected from the ADNI database, which is an open-source database for AD with multicentre cooperation, of which 154 progressed to AD during the 48-month follow-up period. Subjects were divided into a training and test group. For each patient, the baseline T₁WI MR images were automatically segmented into white matter, gray matter and cerebrospinal fluid (CSF), and radiomics features were extracted from each tissue. Based on the data from the training group, a radiomics signature was built using logistic regression after dimensionality reduction. The radiomics signatures, in combination with the apolipoprotein E4 (APOE4) and baseline neuropsychological scales, were used to build an integrated model using machine learning. The receiver operating characteristics (ROC) curve and data of the test group were used to evaluate the diagnostic accuracy and reliability of the model, respectively. In addition, the clinical prognostic efficacy of the model was evaluated based on the time of progression from MCI to AD.

Results:

Stepwise logistic regression analysis showed that the APOE4, clinical dementia rating, AD assessment scale, and radiomics signature were independent predictors of MCI progression to AD. The integrated model was constructed based on independent predictors using machine learning. The ROC curve showed that the accuracy of the model in the training and the test sets was 0.814 and 0.807, with a specificity of 0.671 and 0.738, and a sensitivity of 0.822 and 0.745, respectively. In addition, the model had the most significant diagnostic efficacy in predicting MCI progression to AD within 12 months, with an AUC of 0.814, sensitivity of 0.726, and specificity of 0.798.

Conclusion:

The integrated model based on whole-brain radiomics can accurately identify and predict the high-risk population of MCI patients who may progress to AD. Radiomics biomarkers are practical in the precursory stage of such disease.

Gga3 deletion and a GGA3 rare variant associated with late onset Alzheimer's disease trigger BACE1 accumulation in axonal swellings

Axonal dystrophy, indicative of perturbed axonal transport, occurs early during Alzheimer's disease (AD) pathogenesis. Little is known about the mechanisms underlying this initial sign of the pathology. This study proves that Golgi-localized γ-ear-containing ARF binding protein 3 (GGA3) loss of function, due to Gga3 genetic deletion or a GGA3 rare variant that cosegregates with late-onset AD, disrupts the axonal trafficking of the β-site APP-cleaving enzyme 1 (BACE1) resulting in its accumulation in axonal swellings in cultured neurons and in vivo. We show that BACE pharmacological inhibition ameliorates BACE1 axonal trafficking and diminishes axonal dystrophies in Gga3 null neurons in vitro and in vivo. These data indicate that axonal accumulation of BACE1 engendered by GGA3 loss of function results in local toxicity leading to axonopathy. Gga3 deletion exacerbates axonal dystrophies in a mouse model of AD before β-amyloid (Aβ) deposition. Our study strongly supports a role for GGA3 in AD pathogenesis, where GGA3 loss of function triggers BACE1 axonal accumulation independently of extracellular Aβ, and initiates a cascade of events leading to the axonal damage distinctive of the early stage of AD.

Individualized Prediction of Early Alzheimer's Disease Based on Magnetic Resonance Imaging Radiomics, Clinical, and Laboratory Examinations: A 60-Month Follow-Up Study

BACKGROUND

Accurately predicting whether and when mild cognitive impairment (MCI) will progress to Alzheimer's disease (AD) is of vital importance to help developing individualized treatment plans to defer the occurrence of irreversible dementia.

PURPOSE

To develop and validate radiomics models and multipredictor nomogram for predicting the time to progression (TTP) from MCI to AD.

STUDY TYPE

Retrospective.

POPULATION

One hundred sixty-two MCI patients (96 men and 66 women [median age, 72; age range, 56-88 years]) were included from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database.

FIELD STRENGTH/SEQUENCE

T₁ -weighted imaging and T₂ -weighted fluid-attenuation inversion recovery imaging acquired at 3.0 T.

ASSESSMENT

During the 5-year follow-up, 68 patients converted to AD and 94 remained stable. Patients were randomly divided into the training (n = 112) and validation datasets (n = 50). Radiomic features were extracted from the whole cerebral cortex and subcortical nucleus of MR images. A radiomics model was established using least absolute shrinkage and selection operator (LASSO) Cox regression. The clinical-laboratory model and radiomics-clinical-laboratory model were developed by multivariate Cox proportional hazard model. The performance of each model was assessed by the concordance index (C-index). A multipredictor nomogram derived from the radiomics-clinical-laboratory model was constructed for individualized TTP estimation.

STATISTICAL TESTS

LASSO cox regression, univariate and multivariate Cox regression, Kaplan-Meier analysis and Student's t test were performed.

RESULTS

The C-index of the radiomics, clinical-laboratory and radiomics-clinical-laboratory models were 0.924 (95% confidence interval [CI]: 0.894-0.952), 0.903 (0.868-0.938), 0.950 (0.929-0.971) in the training cohort and 0.811 (0.707-0.914), 0.901 (0824-0.977), 0.907 (0.836-0.979) in the validation cohort, respectively. A multipredictor nomogram with 15 predictors was established, which had high accuracy for individual TTP prediction with the C-index of 0.950 (0.929-0.971).

DATA CONCLUSION

The prediction of individual TTP from MCI to AD could be accurately conducted using the radiomics-clinical-laboratory model and multipredictor nomogram.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: 2.

Denouements of machine learning and multimodal diagnostic classification of Alzheimer's disease

Alzheimer's disease (AD) is the most common type of dementia. The exact cause and treatment of the disease are still unknown. Different neuroimaging modalities, such as magnetic resonance imaging (MRI), positron emission tomography, and single-photon emission computed tomography, have played a significant role in the study of AD. However, the effective diagnosis of AD, as well as mild cognitive impairment (MCI), has recently drawn large attention. Various technological advancements, such as robots, global positioning system technology, sensors, and machine learning (ML) algorithms, have helped improve the diagnostic process of AD. This study aimed to determine the influence of implementing different ML classifiers in MRI and analyze the use of support vector machines with various multimodal scans for classifying patients with AD/MCI and healthy controls. Conclusions have been drawn in terms of employing different classifier techniques and presenting the optimal multimodal paradigm for the classification of AD.

Disconnection of the right superior parietal lobule from the precuneus is associated with memory impairment in oldest-old Alzheimer's disease patients

There is a wide range of onset age in Alzheimer's disease (AD). Emerging evidence indicates variation of AD manifestations in oldest-old AD (OOAD); however, the pattern of cognitive dysfunctions remains unclear. We aimed to reveal cognitive performance characteristics and changes in brain functional connectivity in OOAD patients by a resting-state fMRI (rs-fMRI) study. We enrolled AD patients who had been referred to Kyushu University Hospital (KUH) or Sanno Hospital, and classified them into middle-old AD (MOAD) (65-79 years old) and OOAD (≥80 years old) according to the age of onset. Our subjects consisted of 19 OOAD, 17 MOAD, and 8 normal subjects. Cognitive performance was evaluated using Mini Mental State Examination-Japanese (MMSE-J) and Clinical Dementia Rating (CDR). rs-fMRI scanning and independent component analysis (ICA) were performed on Sanno Hospital patients and MOAD vs. OOAD patients were compared. The resulting significant regions were used as seeds for ROI-to-ROI analysis of the KUH dataset. Collectively, MMSE-J delayed recall sub-scores were significantly lower in OOAD patients compared with MOAD patients. ICA of the Sanno Hospital data indicated significant connectivity decrease in the default mode network (DMN) in the OOAD group compared with the MOAD group in the right superior parietal lobule (SPL). ROI-to-ROI analysis of the KUH dataset indicated significant disconnection in the OOAD group of the right SPL from the precuneus (p < 0.01). The functional connectivity from the right SPL to the precuneus was positively correlated with the MMSE-J delayed recall sub-score (p = 0.03) and negatively correlated with the CDR memory sub-scale (p = 0.04). These findings indicate that disconnection between the right SPL and the precuneus may contribute to worse memory capability in OOAD compared with MOAD.

MCLENA-1: A Phase II Clinical Trial for the Assessment of Safety, Tolerability, and Efficacy of Lenalidomide in Patients with Mild Cognitive Impairment Due to Alzheimer's Disease

With the general population reaching higher ages, a surge in Alzheimer's disease (AD) incidence will happen in the coming decades, putting a heavy burden on families and healthcare systems Worldwide. This emphasizes the pressing need for AD therapeutic interventions. Accumulating evidence indicates that inflammation is prominent both in the blood and central nervous system of AD sufferers. These data suggest that systemic inflammation plays a crucial role in the cause and effects of AD neuropathology. Capitalizing on our experience from a previous clinical trial with thalidomide, we hypothesize that modulating inflammation via the pleiotropic immunomodulator lenalidomide may alter AD if administered during a proper time window in the course of the disease. Thus, in this Phase II, proof-of mechanism study, 30 amnestic mild cognitive impairment (aMCI) subjects will be treated with lenalidomide at 10 mg/day for 12 months on a 1:1 ratio, followed by a 6 months washout period. The primary objective of this study is to investigate the effect of lenalidomide on cognition, which is assessed at regular intervals. The secondary objective is to assess the safety and tolerability of lenalidomide in aMCI patients evaluated through adverse events, vital signs, clinical biochemistry, and physical and neurological examinations. Tertiary objectives are to analyze the effects of lenalidomide on brain amyloid loads (Florbetapir PET imaging) and neurodegeneration (volumetric MRI) by comparing pre- and post-dosing data. Finally, exploratory objectives will investigate whether blood inflammatory markers can serve as surrogate markers of therapeutic efficacy. Our study should determine whether lenalidomide is safe in AD subjects and whether it can alter the clinical progression of AD when administered before dementia onset. If effective, lenalidomide would become the first drug capable of delaying the trajectory of AD, which could lead the way to find additional, less toxic treatments in the near future.

Multi-Modality Sparse Representation for Alzheimer's Disease Classification

BACKGROUND

Alzheimer's disease (AD) and mild cognitive impairment (MCI) are age-related neurodegenerative diseases characterized by progressive loss of memory and irreversible cognitive functions. The hippocampus, a brain area critical for learning and memory processes, is especially susceptible to damage at early stages of AD.

OBJECTIVE

We aimed to develop prediction model using a multi-modality sparse representation approach.

METHODS

We proposed a sparse representation approach to the hippocampus using structural T1-weighted magnetic resonance imaging (MRI) and 18-fluorodeoxyglucose-positron emission tomography (FDG-PET) to distinguish AD/MCI from healthy control subjects (HCs). We considered structural and function information for the hippocampus and applied a sparse patch-based approach to effectively reduce the dimensions of neuroimaging biomarkers.

RESULTS

In experiments using Alzheimer's Disease Neuroimaging Initiative data, our proposed method demonstrated more reliable than previous classification studies. The effects of different parameters on segmentation accuracy were also evaluated. The mean classification accuracy obtained with our proposed method was 0.94 for AD/HCs, 0.82 for MCI/HCs, and 0.86 for AD/MCI.

CONCLUSION

We extracted multi-modal features from automatically defined hippocampal regions of training subjects and found this method to be discriminative and robust for AD and MCI classification. The extraction of features in T1 and FDG-PET images is expected to improve classification performance due to the relationship between brain structure and function.

Harnessing the Power of Machine Learning in Dementia Informatics Research: Issues, Opportunities, and Challenges

Dementia is a chronic and degenerative condition affecting millions globally. The care of patients with dementia presents an ever-continuing challenge to healthcare systems in the 21st century. Medical and health sciences have generated unprecedented volumes of data related to health and wellbeing for patients with dementia due to advances in information technology, such as genetics, neuroimaging, cognitive assessment, free texts, routine electronic health records, etc. Making the best use of these diverse and strategic resources will lead to high-quality care of patients with dementia. As such, machine learning becomes a crucial factor in achieving this objective. The aim of this paper is to provide a state-of-the-art review of machine learning methods applied to health informatics for dementia care. We collate and review the existing scientific methodologies and identify the relevant issues and challenges when faced with big health data. Machine learning has demonstrated promising applications to neuroimaging data analysis for dementia care, while relatively less effort has been made to make use of integrated heterogeneous data via advanced machine learning approaches. We further indicate future potential and research directions in applying advanced machine learning, such as deep learning, to dementia informatics.

Voxel-wise deviations from healthy aging for the detection of region-specific atrophy

The identification of pathological atrophy in MRI scans requires specialized training, which is scarce outside dedicated centers. We sought to investigate the clinical usefulness of computer-generated representations of local grey matter (GM) loss or increased volume of cerebral fluids (CSF) as normalized deviations (z-scores) from healthy aging to either aid human visual readings or directly detect pathological atrophy.

Two experienced neuroradiologists rated atrophy in 30 patients with Alzheimer's disease (AD), 30 patients with frontotemporal dementia (FTD), 30 with dementia due to Lewy-body disease (LBD) and 30 healthy controls (HC) on a three-point scale in 10 anatomical regions as reference gold standard. Seven raters, varying in their experience with MRI diagnostics rated all cases on the same scale once with and once without computer-generated volume deviation maps that were overlaid on anatomical slices. In addition, we investigated the predictive value of the computer generated deviation maps on their own for the detection of atrophy as identified by the gold standard raters.

Inter and intra-rater agreements of the two gold standard raters were substantial (Cohen's kappa κ > 0.62). The intra-rater agreement of the other raters ranged from fair (κ = 0.37) to substantial (κ = 0.72) and improved on average by 0.13 (0.57 < κ < 0.87) when volume deviation maps were displayed. The seven other raters showed good agreement with the gold standard in regions including the hippocampus but agreement was substantially lower in e.g. the parietal cortex and did not improve with the display of atrophy scores. Rating speed increased over the course of the study and irrespective of the presentation of voxel-wise deviations.

Automatically detected large deviations of local volume were consistently associated with gold standard atrophy reading as shown by an area under the receiver operator characteristic of up to 0.95 for the hippocampus region. When applying these test characteristics to prevalences typically found in a memory clinic, we observed a positive or negative predictive value close to or above 0.9 in the hippocampus for almost all of the expected cases. The volume deviation maps derived from CSF volume increase were generally better in detecting atrophy.

Our study demonstrates an agreement of visual ratings among non-experts not further increased by displaying, region-specific deviations of volume. The high predictive value of computer generated local deviations independent from human interaction and the consistent advantages of CSF-over GM-based estimations should be considered in the development of diagnostic tools and indicate clinical utility well beyond aiding visual assessments.

•

The visual identification of atrophy is most accurate in the temporal lobe.

•

Voxel-wise deviations of tissue volume from normal aging is easy to implement.

•

Displaying voxel-wise deviations subjectively but not objectively aids readers.

•

Voxel-wise deviations themselves show high agreement with expert readings.

•

Information on tissue deviations should be provided with cerebral MRI scans.

Separating Symptomatic Alzheimer's Disease from Depression based on Structural MRI

Older patients with depression or Alzheimer’s disease (AD) at the stage of early dementia or mild cognitive impairment may present with objective cognitive impairment, although the pathology and thus therapy and prognosis differ substantially. In this study, we assessed the potential of an automated algorithm to categorize a test set of 65 T1-weighted structural magnetic resonance images (MRI). A convenience sample of elderly individuals fulfilling clinical criteria of either AD (n = 28) or moderate and severe depression (n = 37) was recruited from different settings to assess the potential of the pattern recognition method to assist in the differential diagnosis of AD versus depression. We found that our algorithm learned discriminative patterns in the subject’s grey matter distribution reflected by an area under the receiver operator characteristics curve of up to 0.83 (confidence interval ranged from 0.67 to 0.92) and a balanced accuracy of 0.79 for the separation of depression from AD, evaluated by leave-one-out cross validation. The algorithm also identified consistent structural differences in a clinically more relevant scenario where the data used during training were independent from the data used for evaluation and, critically, which included five possible diagnoses (specifically AD, frontotemporal dementia, Lewy body dementia, depression, and healthy aging). While the output was insufficiently accurate to use it directly as a means for classification when multiple classes are possible, the continuous output computed by the machine learning algorithm differed between the two groups that were investigated. The automated analysis thus could complement, but not replace clinical assessments.

Characterization of brain anatomical patterns by comparing region intensity distributions: Applications to the description of Alzheimer's disease

PURPOSE

This work presents an automatic characterization of the Alzheimer's disease describing the illness as a multidirectional departure from a baseline defining the control state, being these directions determined by a distance between functional-equivalent anatomical regions.

METHODS

After a brain parcellation, a region is described by its histogram of gray levels, and the Earth mover's distance establishes how close or far these regions are. The medoid of the control group is set as the reference and any brain is characterized by its set of distances to this medoid.

EVALUATION

This hypothesis was assessed by separating groups of patients with mild Alzheimer's disease and mild cognitive impairment from control subjects, using a subset of the Open Access Series of Imaging Studies (OASIS) database. An additional experiment evaluated the method generalization and consisted in training with the OASIS data and testing with the Minimal Interval Resonance Imaging in Alzheimer's disease (MIRIAD) database.

RESULTS

Classification between controls and patients with AD resulted in an equal error rate of 0.1 (90% of sensitivity and specificity at the same time). The automatic ranking of regions resulting is in strong agreement with those regions described as important in clinical practice. Classification with different databases results in a sensitivity of 85% and a specificity of 91%.

CONCLUSIONS

This method automatically finds out a multidimensional expression of the AD, which is directly related to the anatomical changes in specific areas such as the hippocampus, the amygdala, the planum temporale, and thalamus.

Longitudinal Alteration of Intrinsic Brain Activity in the Striatum in Mild Cognitive Impairment

The striatum is a critical functional hub in understanding neurological disorders. However, the Alzheimer's disease (AD)-associated striatal change is unclear, as is the relationship between striatal change and AD pathology. Three-year resting-state fMRI data from 15 healthy control (HC) and 20 mild cognitive impairment (MCI) participants were obtained. We analyzed the amplitude of low-frequency fluctuations (ALFF) (0.01-0.08 Hz) and two subdivided bands (slow-4:0.027-0.073 Hz; slow-5:0.01-0.027 Hz). We calculated Aβ/pTau ratio using baseline cerebrospinal fluid pTau and Aβ1-42 to represent AD pathology. Compared to HC, MCI participants showed greater decline in right putaminal ALFF, including the slow-4 band. Greater decline of ALFF in the right putamen was significantly related to the memory decline over time and lower baseline Aβ/pTau ratio regardless of age or group. The slow-4 band, relative to slow-5 band, showed a stronger correlation between Aβ/pTau ratio and decline of ALFF in the right putamen. The results suggest that the putaminal function declines early in the AD-associated neurodegeneration. The continuous decline in putaminal ALFF, especially slow-4 band, may be a sensitive marker of AD pathology such as Aβ/pTau ratio regardless of clinical diagnosis.

Multi-modal MRI classifiers identify excessive alcohol consumption and treatment effects in the brain

Robust neuroimaging markers of neuropsychiatric disorders have proven difficult to obtain. In alcohol use disorders, profound brain structural deficits can be found in severe alcoholic patients, but the heterogeneity of unimodal MRI measurements has so far precluded the identification of selective biomarkers, especially for early diagnosis. In the present work we used a combination of multiple MRI modalities to provide comprehensive and insightful descriptions of brain tissue microstructure. We performed a longitudinal experiment using Marchigian-Sardinian (msP) rats, an established model of chronic excessive alcohol consumption, and acquired multi-modal images before and after 1 month of alcohol consumption (6.8 ± 1.4 g/kg/day, mean ± SD), as well as after 1 week of abstinence with or without concomitant treatment with the antirelapse opioid antagonist naltrexone (2.5 mg/kg/day). We found remarkable sensitivity and selectivity to accurately classify brains affected by alcohol even after the relative short exposure period. One month drinking was enough to imprint a highly specific signature of alcohol consumption. Brain alterations were regionally specific and affected both gray and white matter and persisted into the early abstinence state without any detectable recovery. Interestingly, naltrexone treatment during early abstinence resulted in subtle brain changes that could be distinguished from non-treated abstinent brains, suggesting the existence of an intermediate state associated with brain recovery from alcohol exposure induced by medication. The presented framework is a promising tool for the development of biomarkers for clinical diagnosis of alcohol use disorders, with capacity to further inform about its progression and response to treatment.

Feature selective temporal prediction of Alzheimer's disease progression using hippocampus surface morphometry

INTRODUCTION

Prediction of Alzheimer's disease (AD) progression based on baseline measures allows us to understand disease progression and has implications in decisions concerning treatment strategy. To this end, we combine a predictive multi-task machine learning method (cFSGL) with a novel MR-based multivariate morphometric surface map of the hippocampus (mTBM) to predict future cognitive scores of patients.

METHODS

Previous work has shown that a multi-task learning framework that performs prediction of all future time points simultaneously (cFSGL) can be used to encode both sparsity as well as temporal smoothness. The authors showed that this method is able to predict cognitive outcomes of ADNI subjects using FreeSurfer-based baseline MRI features, MMSE score demographic information and ApoE status. Whilst volumetric information may hold generalized information on brain status, we hypothesized that hippocampus specific information may be more useful in predictive modeling of AD. To this end, we applied a multivariate tensor-based parametric surface analysis method (mTBM) to extract features from the hippocampal surfaces.

RESULTS

We combined mTBM features with traditional surface features such as middle axis distance, the Jacobian determinant as well as 2 of the Jacobian principal eigenvalues to yield 7 normalized hippocampal surface maps of 300 points each. By combining these 7 × 300 = 2100 features together with the previous ~350 features, we illustrate how this type of sparsifying method can be applied to an entire surface map of the hippocampus that yields a feature space that is 2 orders of magnitude larger than what was previously attempted.

CONCLUSIONS

By combining the power of the cFSGL multi-task machine learning framework with the addition of AD sensitive mTBM feature maps of the hippocampus surface, we are able to improve the predictive performance of ADAS cognitive scores 6, 12, 24, 36 and 48 months from baseline.

A multilevel-ROI-features-based machine learning method for detection of morphometric biomarkers in Parkinson's disease

Machine learning methods have been widely used in recent years for detection of neuroimaging biomarkers in regions of interest (ROIs) and assisting diagnosis of neurodegenerative diseases. The innovation of this study is to use multilevel-ROI-features-based machine learning method to detect sensitive morphometric biomarkers in Parkinson's disease (PD). Specifically, the low-level ROI features (gray matter volume, cortical thickness, etc.) and high-level correlative features (connectivity between ROIs) are integrated to construct the multilevel ROI features. Filter- and wrapper- based feature selection method and multi-kernel support vector machine (SVM) are used in the classification algorithm. T1-weighted brain magnetic resonance (MR) images of 69 PD patients and 103 normal controls from the Parkinson's Progression Markers Initiative (PPMI) dataset are included in the study. The machine learning method performs well in classification between PD patients and normal controls with an accuracy of 85.78%, a specificity of 87.79%, and a sensitivity of 87.64%. The most sensitive biomarkers between PD patients and normal controls are mainly distributed in frontal lobe, parental lobe, limbic lobe, temporal lobe, and central region. The classification performance of our method with multilevel ROI features is significantly improved comparing with other classification methods using single-level features. The proposed method shows promising identification ability for detecting morphometric biomarkers in PD, thus confirming the potentiality of our method in assisting diagnosis of the disease.

Longitudinal Analysis for Disease Progression via Simultaneous Multi-Relational Temporal-Fused Learning

It is highly desirable to predict the progression of Alzheimer's disease (AD) of patients [e.g., to predict conversion of mild cognitive impairment (MCI) to AD], especially longitudinal prediction of AD is important for its early diagnosis. Currently, most existing methods predict different clinical scores using different models, or separately predict multiple scores at different future time points. Such approaches prevent coordinated learning of multiple predictions that can be used to jointly predict clinical scores at multiple future time points. In this paper, we propose a joint learning method for predicting clinical scores of patients using multiple longitudinal prediction models for various future time points. Three important relationships among training samples, features, and clinical scores are explored. The relationship among different longitudinal prediction models is captured using a common feature set among the multiple prediction models at different time points. Our experimental results based on the Alzheimer's disease neuroimaging initiative (ADNI) database shows that our method achieves considerable improvement over competing methods in predicting multiple clinical scores.

Predicting primary progressive aphasias with support vector machine approaches in structural MRI data

Primary progressive aphasia (PPA) encompasses the three subtypes nonfluent/agrammatic variant PPA, semantic variant PPA, and the logopenic variant PPA, which are characterized by distinct patterns of language difficulties and regional brain atrophy. To validate the potential of structural magnetic resonance imaging data for early individual diagnosis, we used support vector machine classification on grey matter density maps obtained by voxel-based morphometry analysis to discriminate PPA subtypes (44 patients: 16 nonfluent/agrammatic variant PPA, 17 semantic variant PPA, 11 logopenic variant PPA) from 20 healthy controls (matched for sample size, age, and gender) in the cohort of the multi-center study of the German consortium for frontotemporal lobar degeneration. Here, we compared a whole-brain with a meta-analysis-based disease-specific regions-of-interest approach for support vector machine classification. We also used support vector machine classification to discriminate the three PPA subtypes from each other. Whole brain support vector machine classification enabled a very high accuracy between 91 and 97% for identifying specific PPA subtypes vs. healthy controls, and 78/95% for the discrimination between semantic variant vs. nonfluent/agrammatic or logopenic PPA variants. Only for the discrimination between nonfluent/agrammatic and logopenic PPA variants accuracy was low with 55%. Interestingly, the regions that contributed the most to the support vector machine classification of patients corresponded largely to the regions that were atrophic in these patients as revealed by group comparisons. Although the whole brain approach took also into account regions that were not covered in the regions-of-interest approach, both approaches showed similar accuracies due to the disease-specificity of the selected networks. Conclusion, support vector machine classification of multi-center structural magnetic resonance imaging data enables prediction of PPA subtypes with a very high accuracy paving the road for its application in clinical settings.

•

Aim was to evaluate the potential of multi-center MRI data for individual PPA diagnosis.

•

We used support vector machine classification in PPA variants and healthy controls.

•

We compared a whole brain approach with a ROI (taken from meta-analyses) approach.

•

Accuracies were overall quite high, for both, the whole brain and the ROI approach.

Decoding post-stroke motor function from structural brain imaging

Clinical research based on neuroimaging data has benefited from machine learning methods, which have the ability to provide individualized predictions and to account for the interaction among units of information in the brain. Application of machine learning in structural imaging to investigate diseases that involve brain injury presents an additional challenge, especially in conditions like stroke, due to the high variability across patients regarding characteristics of the lesions. Extracting data from anatomical images in a way that translates brain damage information into features to be used as input to learning algorithms is still an open question. One of the most common approaches to capture regional information from brain injury is to obtain the lesion load per region (i.e. the proportion of voxels in anatomical structures that are considered to be damaged). However, no systematic evaluation has yet been performed to compare this approach with using patterns of voxels (i.e. considering each voxel as a single feature). In this paper we compared both approaches applying Gaussian Process Regression to decode motor scores in 50 chronic stroke patients based solely on data derived from structural MRI. For both approaches we compared different ways to delimit anatomical areas: regions of interest from an anatomical atlas, the corticospinal tract, a mask obtained from fMRI analysis with a motor task in healthy controls and regions selected using lesion-symptom mapping. Our analysis showed that extracting features through patterns of voxels that represent lesion probability produced better results than quantifying the lesion load per region. In particular, from the different ways to delimit anatomical areas compared, the best performance was obtained with a combination of a range of cortical and subcortical motor areas as well as the corticospinal tract. These results will inform the appropriate methodology for predicting long term motor outcomes from early post-stroke structural brain imaging.

Principal component of explained variance: An efficient and optimal data dimension reduction framework for association studies

The genomics era has led to an increase in the dimensionality of data collected in the investigation of biological questions. In this context, dimension-reduction techniques can be used to summarise high-dimensional signals into low-dimensional ones, to further test for association with one or more covariates of interest. This paper revisits one such approach, previously known as principal component of heritability and renamed here as principal component of explained variance (PCEV). As its name suggests, the PCEV seeks a linear combination of outcomes in an optimal manner, by maximising the proportion of variance explained by one or several covariates of interest. By construction, this method optimises power; however, due to its computational complexity, it has unfortunately received little attention in the past. Here, we propose a general analytical PCEV framework that builds on the assets of the original method, i.e. conceptually simple and free of tuning parameters. Moreover, our framework extends the range of applications of the original procedure by providing a computationally simple strategy for high-dimensional outcomes, along with exact and asymptotic testing procedures that drastically reduce its computational cost. We investigate the merits of the PCEV using an extensive set of simulations. Furthermore, the use of the PCEV approach is illustrated using three examples taken from the fields of epigenetics and brain imaging.

Application of Machine Learning to Arterial Spin Labeling in Mild Cognitive Impairment and Alzheimer Disease

Purpose To investigate whether multivariate pattern recognition analysis of arterial spin labeling (ASL) perfusion maps can be used for classification and single-subject prediction of patients with Alzheimer disease (AD) and mild cognitive impairment (MCI) and subjects with subjective cognitive decline (SCD) after using the W score method to remove confounding effects of sex and age. Materials and Methods Pseudocontinuous 3.0-T ASL images were acquired in 100 patients with probable AD; 60 patients with MCI, of whom 12 remained stable, 12 were converted to a diagnosis of AD, and 36 had no follow-up; 100 subjects with SCD; and 26 healthy control subjects. The AD, MCI, and SCD groups were divided into a sex- and age-matched training set (n = 130) and an independent prediction set (n = 130). Standardized perfusion scores adjusted for age and sex (W scores) were computed per voxel for each participant. Training of a support vector machine classifier was performed with diagnostic status and perfusion maps. Discrimination maps were extracted and used for single-subject classification in the prediction set. Prediction performance was assessed with receiver operating characteristic (ROC) analysis to generate an area under the ROC curve (AUC) and sensitivity and specificity distribution. Results Single-subject diagnosis in the prediction set by using the discrimination maps yielded excellent performance for AD versus SCD (AUC, 0.96; P < .01), good performance for AD versus MCI (AUC, 0.89; P < .01), and poor performance for MCI versus SCD (AUC, 0.63; P = .06). Application of the AD versus SCD discrimination map for prediction of MCI subgroups resulted in good performance for patients with MCI diagnosis converted to AD versus subjects with SCD (AUC, 0.84; P < .01) and fair performance for patients with MCI diagnosis converted to AD versus those with stable MCI (AUC, 0.71; P > .05). Conclusion With automated methods, age- and sex-adjusted ASL perfusion maps can be used to classify and predict diagnosis of AD, conversion of MCI to AD, stable MCI, and SCD with good to excellent accuracy and AUC values. ^© RSNA, 2016.

Applying Automated MR-Based Diagnostic Methods to the Memory Clinic: A Prospective Study

Several studies have demonstrated that fully automated pattern recognition methods applied to structural magnetic resonance imaging (MRI) aid in the diagnosis of dementia, but these conclusions are based on highly preselected samples that significantly differ from that seen in a dementia clinic. At a single dementia clinic, we evaluated the ability of a linear support vector machine trained with completely unrelated data to differentiate between Alzheimer’s disease (AD), frontotemporal dementia (FTD), Lewy body dementia, and healthy aging based on 3D-T1 weighted MRI data sets. Furthermore, we predicted progression to AD in subjects with mild cognitive impairment (MCI) at baseline and automatically quantified white matter hyperintensities from FLAIR-images. Separating additionally recruited healthy elderly from those with dementia was accurate with an area under the curve (AUC) of 0.97 (according to Fig. 4). Multi-class separation of patients with either AD or FTD from other included groups was good on the training set (AUC >  0.9) but substantially less accurate (AUC = 0.76 for AD, AUC = 0.78 for FTD) on 134 cases from the local clinic. Longitudinal data from 28 cases with MCI at baseline and appropriate follow-up data were available. The computer tool discriminated progressive from stable MCI with AUC = 0.73, compared to AUC = 0.80 for the training set. A relatively low accuracy by clinicians (AUC = 0.81) illustrates the difficulties of predicting conversion in this heterogeneous cohort. This first application of a MRI-based pattern recognition method to a routine sample demonstrates feasibility, but also illustrates that automated multi-class differential diagnoses have to be the focus of future methodological developments and application studies

Inherent Structure-Based Multiview Learning With Multitemplate Feature Representation for Alzheimer's Disease Diagnosis

Multitemplate-based brain morphometric pattern analysis using magnetic resonance imaging has been recently proposed for automatic diagnosis of Alzheimer's disease (AD) and its prodromal stage (i.e., mild cognitive impairment or MCI). In such methods, multiview morphological patterns generated from multiple templates are used as feature representation for brain images. However, existing multitemplate-based methods often simply assume that each class is represented by a specific type of data distribution (i.e., a single cluster), while in reality, the underlying data distribution is actually not preknown. In this paper, we propose an inherent structure-based multiview leaning method using multiple templates for AD/MCI classification. Specifically, we first extract multiview feature representations for subjects using multiple selected templates and then cluster subjects within a specific class into several subclasses (i.e., clusters) in each view space. Then, we encode those subclasses with unique codes by considering both their original class information and their own distribution information, followed by a multitask feature selection model. Finally, we learn an ensemble of view-specific support vector machine classifiers based on their, respectively, selected features in each view and fuse their results to draw the final decision. Experimental results on the Alzheimer's Disease Neuroimaging Initiative database demonstrate that our method achieves promising results for AD/MCI classification, compared to the state-of-the-art multitemplate-based methods.

Ensembles of Deep Learning Architectures for the Early Diagnosis of the Alzheimer's Disease

Computer Aided Diagnosis (CAD) constitutes an important tool for the early diagnosis of Alzheimer's Disease (AD), which, in turn, allows the application of treatments that can be simpler and more likely to be effective. This paper explores the construction of classification methods based on deep learning architectures applied on brain regions defined by the Automated Anatomical Labeling (AAL). Gray Matter (GM) images from each brain area have been split into 3D patches according to the regions defined by the AAL atlas and these patches are used to train different deep belief networks. An ensemble of deep belief networks is then composed where the final prediction is determined by a voting scheme. Two deep learning based structures and four different voting schemes are implemented and compared, giving as a result a potent classification architecture where discriminative features are computed in an unsupervised fashion. The resulting method has been evaluated using a large dataset from the Alzheimer's disease Neuroimaging Initiative (ADNI). Classification results assessed by cross-validation prove that the proposed method is not only valid for differentiate between controls (NC) and AD images, but it also provides good performances when tested for the more challenging case of classifying Mild Cognitive Impairment (MCI) Subjects. In particular, the classification architecture provides accuracy values up to 0.90 and AUC of 0.95 for NC/AD classification, 0.84 and AUC of 0.91 for stable MCI/AD classification and 0.83 and AUC of 0.95 for NC/MCI converters classification.

Evaluating Alzheimer's Disease Progression by Modeling Crosstalk Network Disruption

Aβ, tau, and P-tau have been widely accepted as reliable markers for Alzheimer's disease (AD). The crosstalk between these markers forms a complex network. AD may induce the integral variation and disruption of the network. The aim of this study was to develop a novel mathematic model based on a simplified crosstalk network to evaluate the disease progression of AD. The integral variation of the network is measured by three integral disruption parameters. The robustness of network is evaluated by network disruption probability. Presented results show that network disruption probability has a good linear relationship with Mini Mental State Examination (MMSE). The proposed model combined with Support vector machine (SVM) achieves a relative high 10-fold cross-validated performance in classification of AD vs. normal and mild cognitive impairment (MCI) vs. normal (95% accuracy, 95% sensitivity, 95% specificity for AD vs. normal; 90% accuracy, 94% sensitivity, 83% specificity for MCI vs. normal). This research evaluates the progression of AD and facilitates AD early diagnosis.

Integrative Bayesian analysis of neuroimaging-genetic data with application to cocaine dependence

Neuroimaging and genetic studies provide distinct and complementary information about the structural and biological aspects of a disease. Integrating the two sources of data facilitates the investigation of the links between genetic variability and brain mechanisms among different individuals for various medical disorders. This article presents a general statistical framework for integrative Bayesian analysis of neuroimaging-genetic (iBANG) data, which is motivated by a neuroimaging-genetic study in cocaine dependence. Statistical inference necessitated the integration of spatially dependent voxel-level measurements with various patient-level genetic and demographic characteristics under an appropriate probability model to account for the multiple inherent sources of variation. Our framework uses Bayesian model averaging to integrate genetic information into the analysis of voxel-wise neuroimaging data, accounting for spatial correlations in the voxels. Using multiplicity controls based on the false discovery rate, we delineate voxels associated with genetic and demographic features that may impact diffusion as measured by fractional anisotropy (FA) obtained from DTI images. We demonstrate the benefits of accounting for model uncertainties in both model fit and prediction. Our results suggest that cocaine consumption is associated with FA reduction in most white matter regions of interest in the brain. Additionally, gene polymorphisms associated with GABAergic, serotonergic and dopaminergic neurotransmitters and receptors were associated with FA.

Construction and Validation of Brain MRI Templates from a Korean Normal Elderly Population

OBJECTIVE

This study aimed to construct a Korean normal elderly brain template (KNE96) using Korean elderly individuals for use in brain MRI studies and to validate it.

METHODS

We used high-resolution 3.0T T1 structural MR images from 96 Korean normal elderly individuals (M/F=48/48), aged 60 years or older (M=69.5±6.2 years, F=70.1±7.0 years), for constructing the KNE96 template. The KNE96 template was validated by comparing the registration-induced deformations between the KNE96 and ICBM152 templates using different MR images from 48 Korean normal elderly individuals (M/F=24/24), aged 60 years or older (M=71.5±5.9 years, F=72.8±5.1 years). We used the magnitude of displacement vectors (mag-displacement) and log of Jacobian determinants (log-Jacobian) to quantify the deformation produced during registration process to templates.

RESULTS

The mag-displacement and log-Jacobian of the registration were much smaller using the KNE96 template than with the ICBM152 template in most brain regions. There was a prominent difference in the significant averaged differences (SADs) of the mag-displacement and log-Jacobian between the KNE96 and ICBM152 at the superior, medial, and middle frontal gyrus, the lingual, inferior, middle, and superior occipital gyrus, and the caudate and thalamus.

CONCLUSION

This study suggests that templates constructed from Asian populations, such as the KNE96, may be more desirable than those from Caucasian populations, like the ICBM152, in computational neuroimaging studies that measure and compare anatomical features of the frontal and occipital lobe, thalamus and caudate.

SPReM: Sparse Projection Regression Model For High-dimensional Linear Regression

The aim of this paper is to develop a sparse projection regression modeling (SPReM) framework to perform multivariate regression modeling with a large number of responses and a multivariate covariate of interest. We propose two novel heritability ratios to simultaneously perform dimension reduction, response selection, estimation, and testing, while explicitly accounting for correlations among multivariate responses. Our SPReM is devised to specifically address the low statistical power issue of many standard statistical approaches, such as the Hotelling's T² test statistic or a mass univariate analysis, for high-dimensional data. We formulate the estimation problem of SPREM as a novel sparse unit rank projection (SURP) problem and propose a fast optimization algorithm for SURP. Furthermore, we extend SURP to the sparse multi-rank projection (SMURP) by adopting a sequential SURP approximation. Theoretically, we have systematically investigated the convergence properties of SURP and the convergence rate of SURP estimates. Our simulation results and real data analysis have shown that SPReM out-performs other state-of-the-art methods.

Boosting diagnosis accuracy of Alzheimer's disease using high dimensional recognition of longitudinal brain atrophy patterns

OBJECTIVE

Boosting accuracy in automatically discriminating patients with Alzheimer's disease (AD) and normal controls (NC), based on multidimensional classification of longitudinal whole brain atrophy rates and their intermediate counterparts in analyzing magnetic resonance images (MRI).

METHOD

Longitudinal percentage of brain volume changes (PBVC) in two-year follow up and its intermediate counterparts in early 6-month and late 18-month are used as features in supervised and unsupervised classification procedures based on K-mean, fuzzy clustering method (FCM) and support vector machine (SVM). The most relevant features for classification are selected using discriminative analysis (DA) of features and their principal components (PC). Accuracy of the proposed method is evaluated in a group of 30 patients with AD (16 males, 14 females, age±standard-deviation (SD)=75±1.36 years) and 30 normal controls (15 males, 15 females, age±SD=77±0.88 years) using leave-one-out cross-validation.

RESULTS

Results indicate superiority of supervised machine learning techniques over unsupervised ones in diagnosing AD and withal, predominance of RBF kernel over lineal one. Accuracies of 83.3%, 83.3%, 90% and 91.7% are achieved in classification by K-mean, FCM, linear SVM and SVM with radial based function (RBF) respectively.

CONCLUSION

Evidence that SVM classification of longitudinal atrophy rates may results in high accuracy is given. Additionally, it is realized that use of intermediate atrophy rates and their principal components improves diagnostic accuracy.

View-centralized multi-atlas classification for Alzheimer's disease diagnosis

Multi-atlas based methods have been recently used for classification of Alzheimer's disease (AD) and its prodromal stage, that is, mild cognitive impairment (MCI). Compared with traditional single-atlas based methods, multiatlas based methods adopt multiple predefined atlases and thus are less biased by a certain atlas. However, most existing multiatlas based methods simply average or concatenate the features from multiple atlases, which may ignore the potentially important diagnosis information related to the anatomical differences among different atlases. In this paper, we propose a novel view (i.e., atlas) centralized multi-atlas classification method, which can better exploit useful information in multiple feature representations from different atlases. Specifically, all brain images are registered onto multiple atlases individually, to extract feature representations in each atlas space. Then, the proposed view-centralized multi-atlas feature selection method is used to select the most discriminative features from each atlas with extra guidance from other atlases. Next, we design a support vector machine (SVM) classifier using the selected features in each atlas space. Finally, we combine multiple SVM classifiers for multiple atlases through a classifier ensemble strategy for making a final decision. We have evaluated our method on 459 subjects [including 97 AD, 117 progressive MCI (p-MCI), 117 stable MCI (s-MCI), and 128 normal controls (NC)] from the Alzheimer's Disease Neuroimaging Initiative database, and achieved an accuracy of 92.51% for AD versus NC classification and an accuracy of 78.88% for p-MCI versus s-MCI classification. These results demonstrate that the proposed method can significantly outperform the previous multi-atlas based classification methods.

Clinical prediction from structural brain MRI scans: a large-scale empirical study

Multivariate pattern analysis (MVPA) methods have become an important tool in neuroimaging, revealing complex associations and yielding powerful prediction models. Despite methodological developments and novel application domains, there has been little effort to compile benchmark results that researchers can reference and compare against. This study takes a significant step in this direction. We employed three classes of state-of-the-art MVPA algorithms and common types of structural measurements from brain Magnetic Resonance Imaging (MRI) scans to predict an array of clinically relevant variables (diagnosis of Alzheimer's, schizophrenia, autism, and attention deficit and hyperactivity disorder; age, cerebrospinal fluid derived amyloid-β levels and mini-mental state exam score). We analyzed data from over 2,800 subjects, compiled from six publicly available datasets. The employed data and computational tools are freely distributed ( https://www.nmr.mgh.harvard.edu/lab/mripredict), making this the largest, most comprehensive, reproducible benchmark image-based prediction experiment to date in structural neuroimaging. Finally, we make several observations regarding the factors that influence prediction performance and point to future research directions. Unsurprisingly, our results suggest that the biological footprint (effect size) has a dramatic influence on prediction performance. Though the choice of image measurement and MVPA algorithm can impact the result, there was no universally optimal selection. Intriguingly, the choice of algorithm seemed to be less critical than the choice of measurement type. Finally, our results showed that cross-validation estimates of performance, while generally optimistic, correlate well with generalization accuracy on a new dataset.

Using Copula distributions to support more accurate imaging-based diagnostic classifiers for neuropsychiatric disorders

Many investigators have tried to apply machine learning techniques to magnetic resonance images (MRIs) of the brain in order to diagnose neuropsychiatric disorders. Usually the number of brain imaging measures (such as measures of cortical thickness and measures of local surface morphology) derived from the MRIs (i.e., their dimensionality) has been large (e.g. >10) relative to the number of participants who provide the MRI data (<100). Sparse data in a high dimensional space increase the variability of the classification rules that machine learning algorithms generate, thereby limiting the validity, reproducibility, and generalizability of those classifiers. The accuracy and stability of the classifiers can improve significantly if the multivariate distributions of the imaging measures can be estimated accurately. To accurately estimate the multivariate distributions using sparse data, we propose to estimate first the univariate distributions of imaging data and then combine them using a Copula to generate more accurate estimates of their multivariate distributions. We then sample the estimated Copula distributions to generate dense sets of imaging measures and use those measures to train classifiers. We hypothesize that the dense sets of brain imaging measures will generate classifiers that are stable to variations in brain imaging measures, thereby improving the reproducibility, validity, and generalizability of diagnostic classification algorithms in imaging datasets from clinical populations. In our experiments, we used both computer-generated and real-world brain imaging datasets to assess the accuracy of multivariate Copula distributions in estimating the corresponding multivariate distributions of real-world imaging data. Our experiments showed that diagnostic classifiers generated using imaging measures sampled from the Copula were significantly more accurate and more reproducible than were the classifiers generated using either the real-world imaging measures or their multivariate Gaussian distributions. Thus, our findings demonstrate that estimated multivariate Copula distributions can generate dense sets of brain imaging measures that can in turn be used to train classifiers, and those classifiers are significantly more accurate and more reproducible than are those generated using real-world imaging measures alone.

Predictive Models Based on Support Vector Machines: Whole-Brain versus Regional Analysis of Structural MRI in the Alzheimer's Disease

Decision-making systems trained on structural magnetic resonance imaging data of subjects affected by the Alzheimer's disease (AD) and healthy controls (CTRL) are becoming widespread prognostic tools for subjects with mild cognitive impairment (MCI). This study compares the performances of three classification methods based on support vector machines (SVMs), using as initial sets of brain voxels (ie, features): (1) the segmented grey matter (GM); (2) regions of interest (ROIs) by voxel-wise t-test filtering; (3) parceled ROIs, according to prior knowledge. The recursive feature elimination (RFE) is applied in all cases to investigate whether feature reduction improves the classification accuracy. We analyzed more than 600 AD Neuroimaging Initiative (ADNI) subjects, training the SVMs on the AD/CTRL dataset, and evaluating them on a trial MCI dataset. The classification performance, evaluated as the area under the receiver operating characteristic curve (AUC), reaches AUC = (88.9 ± .5)% in 20-fold cross-validation on the AD/CTRL dataset, when the GM is classified as a whole. The highest discrimination accuracy between MCI converters and nonconverters is achieved when the SVM-RFE is applied to the whole GM: with AUC reaching (70.7 ± .9)%, it outperforms both ROI-based approaches in predicting the AD conversion.

Advances in MRI biomarkers for the diagnosis of Alzheimer's disease

With the prevalence of Alzheimer's disease (AD) predicted to increase substantially over the coming decades, the development of effective biomarkers for the early detection of the disease is paramount. In this short review, the main neuroimaging techniques which have shown potential as biomarkers for AD are introduced, with a focus on MRI. Structural MRI measures of the hippocampus and medial temporal lobe are still the most clinically validated biomarkers for AD, but newer techniques such as functional MRI and diffusion tensor imaging offer great scope in tracking changes in the brain, particularly in functional and structural connectivity, which may precede gray matter atrophy. These new advances in neuroimaging methods require further development and crucially, standardization; however, before they are used as biomarkers to aid in the diagnosis of AD.

Brain imaging of mild cognitive impairment and Alzheimer's disease

The rapidly increasing prevalence of cognitive impairment and Alzheimer's disease has the potential to create a major worldwide healthcare crisis. Structural MRI studies in patients with Alzheimer's disease and mild cognitive impairment are currently attracting considerable interest. It is extremely important to study early structural and metabolic changes, such as those in the hippocampus, entorhinal cortex, and gray matter structures in the medial temporal lobe, to allow the early detection of mild cognitive impairment and Alzheimer's disease. The microstructural integrity of white matter can be studied with diffusion tensor imaging. Increased mean diffusivity and decreased fractional anisotropy are found in subjects with white matter damage. Functional imaging studies with positron emission tomography tracer compounds enable detection of amyloid plaques in the living brain in patients with Alzheimer's disease. In this review, we will focus on key findings from brain imaging studies in mild cognitive impairment and Alzheimer's disease, including structural brain changes studied with MRI and white matter changes seen with diffusion tensor imaging, and other specific imaging methodologies will also be discussed.

An ensemble-of-classifiers based approach for early diagnosis of Alzheimer's disease: classification using structural features of brain images

Structural brain imaging is playing a vital role in identification of changes that occur in brain associated with Alzheimer's disease. This paper proposes an automated image processing based approach for the identification of AD from MRI of the brain. The proposed approach is novel in a sense that it has higher specificity/accuracy values despite the use of smaller feature set as compared to existing approaches. Moreover, the proposed approach is capable of identifying AD patients in early stages. The dataset selected consists of 85 age and gender matched individuals from OASIS database. The features selected are volume of GM, WM, and CSF and size of hippocampus. Three different classification models (SVM, MLP, and J48) are used for identification of patients and controls. In addition, an ensemble of classifiers, based on majority voting, is adopted to overcome the error caused by an independent base classifier. Ten-fold cross validation strategy is applied for the evaluation of our scheme. Moreover, to evaluate the performance of proposed approach, individual features and combination of features are fed to individual classifiers and ensemble based classifier. Using size of left hippocampus as feature, the accuracy achieved with ensemble of classifiers is 93.75%, with 100% specificity and 87.5% sensitivity.

Application of a MRI based index to longitudinal atrophy change in Alzheimer disease, mild cognitive impairment and healthy older individuals in the AddNeuroMed cohort

Cross sectional studies of patients at risk of developing Alzheimer disease (AD) have identified several brain regions known to be prone to degeneration suitable as biomarkers, including hippocampal, ventricular, and whole brain volume. The aim of this study was to longitudinally evaluate an index based on morphometric measures derived from MRI data that could be used for classification of AD and healthy control subjects, as well as prediction of conversion from mild cognitive impairment (MCI) to AD. Patients originated from the AddNeuroMed project at baseline (119 AD, 119 MCI, 110 controls (CTL)) and 1-year follow-up (62 AD, 73 MCI, 79 CTL). Data consisted of 3D T1-weighted MR images, demographics, MMSE, ADAS-Cog, CERAD and CDR scores, and APOE e4 status. We computed an index using a multivariate classification model (AD vs. CTL), using orthogonal partial least squares to latent structures (OPLS). Sensitivity, specificity and AUC were determined. Performance of the classifier (AD vs. CTL) was high at baseline (10-fold cross-validation, 84% sensitivity, 91% specificity, 0.93 AUC) and at 1-year follow-up (92% sensitivity, 74% specificity, 0.93 AUC). Predictions of conversion from MCI to AD were good at baseline (77% of MCI converters) and at follow-up (91% of MCI converters). MCI carriers of the APOE e4 allele manifested more atrophy and presented a faster cognitive decline when compared to non-carriers. The derived index demonstrated a steady increase in atrophy over time, yielding higher accuracy in prediction at the time of clinical conversion. Neuropsychological tests appeared less sensitive to changes over time. However, taking the average of the two time points yielded better correlation between the index and cognitive scores as opposed to using cross-sectional data only. Thus, multivariate classification seemed to detect patterns of AD changes before conversion from MCI to AD and including longitudinal information is of great importance.

Classification and localization of early-stage Alzheimer's disease in magnetic resonance images using a patch-based classifier ensemble

INTRODUCTION

Classification methods have been proposed to detect Alzheimer’s disease (AD) using magnetic resonance images. Most rely on features such as the shape/volume of brain structures that need to be defined a priori. In this work, we propose a method that does not require either the segmentation of specific brain regions or the nonlinear alignment to a template. Besides classification, we also analyze which brain regions are discriminative between a group of normal controls and a group of AD patients.

METHODS

We perform 3D texture analysis using Local Binary Patterns computed at local image patches in the whole brain, combined in a classifier ensemble.We evaluate our method in a publicly available database including very mild-to-mild AD subjects and healthy elderly controls.

RESULTS

For the subject cohort including only mild AD subjects, the best results are obtained using a combination of large (30×30×30 and 40×40×40 voxels) patches. A spatial analysis on the best performing patches shows that these are located in the medial-temporal lobe and in the periventricular regions. When very mild AD subjects are included in the dataset, the small (10×10×10 voxels) patches perform best, with the most discriminative ones being located near the left hippocampus.

CONCLUSION

We show that our method is able not only to perform accurate classification, but also to localize dis-criminative brain regions, which are in accordance with the medical literature. This is achieved without the need to segment-specific brain structures and without performing nonlinear registration to a template, indicating that the method may be suitable for a clinical implementation that can help to diagnose AD at an earlier stage.

[Neuroimaging in psychiatry: multivariate analysis techniques for diagnosis and prognosis]

BACKGROUND

Multiple studies successfully applied multivariate analysis to neuroimaging data demonstrating the potential utility of neuroimaging for clinical diagnostic and prognostic purposes.

OBJECTIVES

Summary of the current state of research regarding the application of neuroimaging in the field of psychiatry.

MATERIAL AND METHODS

Literature review of current studies.

RESULTS

Results of current studies indicate the potential application of neuroimaging data across various diagnoses, such as depression, schizophrenia, bipolar disorder and dementia. Potential applications include disease classification, differential diagnosis and prediction of disease course.

CONCLUSION

The results of the studies are heterogeneous although some studies report promising findings. Further multicentre studies are needed with clearly specified patient populations to systematically investigate the potential utility of neuroimaging for the clinical routine.

Multi-atlas based representations for Alzheimer's disease diagnosis

Brain morphometry based classification from magnetic resonance (MR) acquisitions has been widely investigated in the diagnosis of Alzheimer's disease (AD) and its prodromal stage, i.e., mild cognitive impairment (MCI). In the literature, a morphometric representation of brain structures is obtained by spatial normalization of each image into a common space (i.e., a pre-defined atlas) via non-linear registration, thus the corresponding regions in different brains can be compared. However, representations generated from one single atlas may not be sufficient to reveal the underlying anatomical differences between the groups of disease-affected patients and normal controls (NC). In this article, we propose a different methodology, namely the multi-atlas based morphometry, which measures morphometric representations of the same image in different spaces of multiple atlases. Representations generated from different atlases can thus provide the complementary information to discriminate different groups, and also reduce the negative impacts from registration errors. Specifically, each studied subject is registered to multiple atlases, where adaptive regional features are extracted. Then, all features from different atlases are jointly selected by a correlation and relevance based scheme, followed by final classification with the support vector machine (SVM). We have evaluated the proposed method on 459 subjects (97 AD, 117 progressive-MCI (p-MCI), 117 stable-MCI (s-MCI), and 128 NC) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and achieved 91.64% for AD/NC classification and 72.41% for p-MCI/s-MCI classification. Our results clearly demonstrate that the proposed multi-atlas based method can significantly outperform the previous single-atlas based methods.

What do temporal lobe epilepsy and progressive mild cognitive impairment have in common?

Temporal lobe epilepsy (TLE) and mild cognitive impairment (MCI) are both subject to intensive memory research. Memory problems are a core characteristic of both conditions and we wonder if there are analogies which would enrich the two distinct research communities. In this review we focus on memory decline in both conditions, that is, the most feared psychosocial effect. While it is clear that memory decline in MCI is highly likely and would lead to the more severe diagnosis of Alzheimer's disease, it is a debate if TLE is a dementing disease or not. As such, like for MCI, one can differentiate progressive from stable TLE subtypes, mainly depending on the age of onset. Neuroimaging techniques such as volumetric analysis of the hippocampus, entorhinal, and perirhinal cortex show evidence of pathological changes in TLE and are predictive for memory decline in MCI. Several studies emphasize that it is necessary to extend the region of interest—even whole-brain characteristics can be predictive for conversion from MCI to Alzheimer's disease. Electroencephalography is increasingly subject to computational neuroscience, revealing new approaches for analyzing frequency, spatial synchronization, and information content of the signals. These methods together with event-related designs that assess memory functions are highly promising for understanding the mechanisms of memory decline in both TLE and MCI populations. Finally, there is evidence that the potential of such markers for memory decline is far from being exhausted. Similar structural and neurophysiological characteristics are linked to memory decline in TLE and MCI. We raise the hope that interdisciplinary research and cross-talk between fields such as research on epilepsy and dementia, will shed further light on the dementing characteristics of the pathological basis of MCI and TLE and support the development of new memory enhancing treatment strategies.

Randomized denoising autoencoders for smaller and efficient imaging based AD clinical trials

There is growing body of research devoted to designing imaging-based biomarkers that identify Alzheimer's disease (AD) in its prodromal stage using statistical machine learning methods. Recently several authors investigated how clinical trials for AD can be made more efficient (i.e., smaller sample size) using predictive measures from such classification methods. In this paper, we explain why predictive measures given by such SVM type objectives may be less than ideal for use in the setting described above. We give a solution based on a novel deep learning model, randomized denoising autoencoders (rDA), which regresses on training labels y while also accounting for the variance, a property which is very useful for clinical trial design. Our results give strong improvements in sample size estimates over strategies based on multi-kernel learning. Also, rDA predictions appear to more accurately correlate to stages of disease. Separately, our formulation empirically shows how deep architectures can be applied in the large d, small n regime--the default situation in medical imaging. This result is of independent interest.

Machine learning on brain MRI data for differential diagnosis of Parkinson's disease and Progressive Supranuclear Palsy

BACKGROUND

Supervised machine learning has been proposed as a revolutionary approach for identifying sensitive medical image biomarkers (or combination of them) allowing for automatic diagnosis of individual subjects. The aim of this work was to assess the feasibility of a supervised machine learning algorithm for the assisted diagnosis of patients with clinically diagnosed Parkinson's disease (PD) and Progressive Supranuclear Palsy (PSP).

METHOD

Morphological T1-weighted Magnetic Resonance Images (MRIs) of PD patients (28), PSP patients (28) and healthy control subjects (28) were used by a supervised machine learning algorithm based on the combination of Principal Components Analysis as feature extraction technique and on Support Vector Machines as classification algorithm. The algorithm was able to obtain voxel-based morphological biomarkers of PD and PSP.

RESULTS

The algorithm allowed individual diagnosis of PD versus controls, PSP versus controls and PSP versus PD with an Accuracy, Specificity and Sensitivity>90%. Voxels influencing classification between PD and PSP patients involved midbrain, pons, corpus callosum and thalamus, four critical regions known to be strongly involved in the pathophysiological mechanisms of PSP.

COMPARISON WITH EXISTING METHODS

Classification accuracy of individual PSP patients was consistent with previous manual morphological metrics and with other supervised machine learning application to MRI data, whereas accuracy in the detection of individual PD patients was significantly higher with our classification method.

CONCLUSIONS

The algorithm provides excellent discrimination of PD patients from PSP patients at an individual level, thus encouraging the application of computer-based diagnosis in clinical practice.