Significance of normalization on anatomical MRI measures in predicting Alzheimer's disease

Comparison of Ensemble Techniques for Early Prediction of Alzhiemer Disease

Alzheimer's disease (AD) is a progressive neurological condition characterized by a loss in cognitive functions, with no disease-modifying medication now available. It is crucial for early detection and treatment of Alzheimer's disease before clinical manifestation. The stage between cognitively healthy older persons and AD is known as mild cognitive impairment (MCI). To predict the transition from one-stage MCI to probable AD, five ensemble learning approach was used (Stacking, Gradient boost Bagging, Adaptive boost and Voting), an integrated model that combines not only cross-sectional neuroimaging biomarkers at baseline but also longitudinal cerebrospinal fluid (CSF) and cognitive performance biomarkers from the Alzheimer's Disease Neuroimaging Initiative cohort (ADNI). The adaptive boost, stacking and bagging ensemble approach has shown potential to identify those at risk of developing Alzheimer's disease, this would benefit them the most from a clinical trial or to use as a stratification approach inside clinical trials.

Impact of sex and APOE-ε4 genotype on patterns of regional brain atrophy in Alzheimer's disease and healthy aging

Alzheimer's Disease (AD) is a heterogeneous disease that disproportionately affects women and people with the APOE-ε4 susceptibility gene. We aim to describe the not-well-understood influence of both risk factors on the dynamics of brain atrophy in AD and healthy aging. Regional cortical thinning and brain atrophy were modeled over time using non-linear mixed-effect models and the FreeSurfer software with t1-MRI scans from the Alzheimer's Disease Neuroimaging Initiative (N = 1,502 subjects, 6,728 images in total). Covariance analysis was used to disentangle the effect of sex and APOE genotype on the regional onset age and pace of atrophy, while correcting for educational level. A map of the regions mostly affected by neurodegeneration is provided. Results were confirmed on gray matter density data from the SPM software. Women experience faster atrophic rates in the temporal, frontal, parietal lobes and limbic system and earlier onset in the amygdalas, but slightly later onset in the postcentral and cingulate gyri as well as all regions of the basal ganglia and thalamus. APOE-ε4 genotypes leads to earlier and faster atrophy in the temporal, frontal, parietal lobes, and limbic system in AD patients, but not in healthy patients. Higher education was found to slightly delay atrophy in healthy patients, but not for AD patients. A cohort of amyloid positive patients with MCI showed a similar impact of sex as in the healthy cohort, while APOE-ε4 showed similar associations as in the AD cohort. Female sex is as strong a risk factor for AD as APOE-ε4 genotype regarding neurodegeneration. Women experience a sharper atrophy in the later stages of the disease, although not a significantly earlier onset. These findings may have important implications for the development of targeted intervention.

Development of Human Lateral Prefrontal Sulcal Morphology and Its Relation to Reasoning Performance

Previous findings show that the morphology of folds (sulci) of the human cerebral cortex flatten during postnatal development. However, previous studies did not consider the relationship between sulcal morphology and cognitive development in individual participants. Here, we fill this gap in knowledge by leveraging cross-sectional morphologic neuroimaging data in the lateral PFC (LPFC) from individual human participants (6-36 years old, males and females; N = 108; 3672 sulci), as well as longitudinal morphologic and behavioral data from a subset of child and adolescent participants scanned at two time points (6-18 years old; N = 44; 2992 sulci). Manually defining thousands of sulci revealed that LPFC sulcal morphology (depth, surface area, and gray matter thickness) differed between children (6-11 years old)/adolescents (11-18 years old) and young adults (22-36 years old) cross-sectionally, but only cortical thickness showed differences across childhood and adolescence and presented longitudinal changes during childhood and adolescence. Furthermore, a data-driven approach relating morphology and cognition identified that longitudinal changes in cortical thickness of four left-hemisphere LPFC sulci predicted longitudinal changes in reasoning performance, a higher-level cognitive ability that relies on LPFC. Contrary to previous findings, these results suggest that sulci may flatten either after this time frame or over a longer longitudinal period of time than previously presented. Crucially, these results also suggest that longitudinal changes in the cortex within specific LPFC sulci are behaviorally meaningful, providing targeted structures, and areas of the cortex, for future neuroimaging studies examining the development of cognitive abilities.SIGNIFICANCE STATEMENT Recent work has shown that individual differences in neuroanatomical structures (indentations, or sulci) within the lateral PFC are behaviorally meaningful during childhood and adolescence. Here, we describe how specific lateral PFC sulci develop at the level of individual participants for the first time: from both cross-sectional and longitudinal perspectives. Further, we show, also for the first time, that the longitudinal morphologic changes in these structures are behaviorally relevant. These findings lay the foundation for a future avenue to precisely study the development of the cortex and highlight the importance of studying the development of sulci in other cortical expanses and charting how these changes relate to the cognitive abilities those areas support at the level of individual participants.

Diagnostic performance of magnetic resonance imaging-based machine learning in Alzheimer's disease detection: a meta-analysis

PURPOSE

Advanced machine learning (ML) algorithms can assist rapid medical image recognition and realize automatic, efficient, noninvasive, and convenient diagnosis. We aim to further evaluate the diagnostic performance of ML to distinguish patients with probable Alzheimer's disease (AD) from normal older adults based on structural magnetic resonance imaging (MRI).

METHODS

The Medline, Embase, and Cochrane Library databases were searched for relevant literature published up until July 2021. We used the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool and Checklist for Artificial Intelligence in Medical Imaging (CLAIM) to evaluate all included studies' quality and potential bias. Random-effects models were used to calculate pooled sensitivity and specificity, and the Deeks' test was used to assess publication bias.

RESULTS

We included 24 models based on different brain features extracted by ML algorithms in 19 papers. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio, and area under the summary receiver operating characteristic curve for ML in detecting AD were 0.85 (95%CI 0.81-0.89), 0.88 (95%CI 0.84-0.91), 7.15 (95%CI 5.40-9.47), 0.17 (95%CI 0.12-0.22), 43.34 (95%CI 26.89-69.84), and 0.93 (95%CI 0.91-0.95).

CONCLUSION

ML using structural MRI data performed well in diagnosing probable AD patients and normal elderly. However, more high-quality, large-scale prospective studies are needed to further enhance the reliability and generalizability of ML for clinical applications before it can be introduced into clinical practice.

Improving Accuracy of Brainstem MRI Volumetry: Effects of Age and Sex, and Normalization Strategies

Background: Brainstem-mediated functions are impaired in neurodegenerative diseases and aging. Atrophy can be visualized by MRI. This study investigates extrinsic sources of brainstem volume variability, intrinsic sources of anatomical variability, and the influence of age and sex on the brainstem volumes in healthy subjects. We aimed to develop efficient normalization strategies to reduce the effects of intrinsic anatomic variability on brainstem volumetry.

Methods: Brainstem segmentation was performed from MPRAGE data using our deep-learning-based brainstem segmentation algorithm MD-GRU. The extrinsic variability of brainstem volume assessments across scanners and protocols was investigated in two groups comprising 11 (median age 33.3 years, 7 women) and 22 healthy subjects (median age 27.6 years, 50% women) scanned twice and compared using Dice scores. Intrinsic anatomical inter-individual variability and age and sex effects on brainstem volumes were assessed in segmentations of 110 healthy subjects (median age 30.9 years, range 18–72 years, 53.6% women) acquired on 1.5T (45%) and 3T (55%) scanners. The association between brainstem volumes and predefined anatomical covariates was studied using Pearson correlations. Anatomical variables with associations of |r| > 0.30 as well as the variables age and sex were used to construct normalization models using backward selection. The effect of the resulting normalization models was assessed by % relative standard deviation reduction and by comparing the inter-individual variability of the normalized brainstem volumes to the non-normalized values using paired t- tests with Bonferroni correction.

Results: The extrinsic variability of brainstem volumetry across different field strengths and imaging protocols was low (Dice scores > 0.94). Mean inter-individual variability/SD of total brainstem volumes was 9.8%/7.36. A normalization based on either total intracranial volume (TICV), TICV and age, or v-scale significantly reduced the inter-individual variability of total brainstem volumes compared to non-normalized volumes and similarly reduced the relative standard deviation by about 35%.

Conclusion: The extrinsic variability of the novel brainstem segmentation method MD-GRU across different scanners and imaging protocols is very low. Anatomic inter-individual variability of brainstem volumes is substantial. This study presents efficient normalization models for variability reduction in brainstem volumetry in healthy subjects.

Substantially thinner internal granular layer and reduced molecular layer surface in the cerebellar cortex of the Tc1 mouse model of down syndrome - a comprehensive morphometric analysis with active staining contrast-enhanced MRI

Down Syndrome is a chromosomal disorder that affects the development of cerebellar cortical lobules. Impaired neurogenesis in the cerebellum varies among different types of neuronal cells and neuronal layers. In this study, we developed an imaging analysis framework that utilizes gadolinium-enhanced ex vivo mouse brain MRI. We extracted the middle Purkinje layer of the mouse cerebellar cortex, enabling the estimation of the volume, thickness, and surface area of the entire cerebellar cortex, the internal granular layer, and the molecular layer in the Tc1 mouse model of Down Syndrome. The morphometric analysis of our method revealed that a larger proportion of the cerebellar thinning in this model of Down Syndrome resided in the inner granule cell layer, while a larger proportion of the surface area shrinkage was in the molecular layer.

Predictive Model of Spread of Progressive Supranuclear Palsy Using Directional Network Diffusion

Several neurodegenerative disorders including Alzheimer’s disease (AD), frontotemporal dementia (FTD), Parkinson’s disease (PD), amyotrophic lateral sclerosis, and Huntington’s disease report aggregation and transmission of pathogenic proteins between cells. The topography of these diseases in the human brain also, therefore, displays a well-characterized and stereotyped regional pattern, and a stereotyped progression over time. This is most commonly true for AD and other dementias characterized by hallmark misfolded tau or alpha-synuclein pathology. Both tau and synuclein appear to propagate within brain circuits using a shared mechanism. The most canonical synucleopathy is PD; however, much less studied is a rare disorder called progressive supranuclear palsy (PSP). The hallmark pathology and atrophy in PSP are, therefore, also highly stereotyped: initially appearing in the striatum, followed by its neighbors and connected cortical areas. In this study, we explore two mechanistic aspects hitherto unknown about the canonical network diffusion model (NDM) of spread: (a) whether the NDM can apply to other common degenerative pathologies, specifically PSP, and (b) whether the directionality of spread is important in explaining empirical data. Our results on PSP reveal two important findings: first, that PSP is amenable to the connectome-based ND modeling in the same way as previously applied to AD and FTD and, second, that the NDM fit with empirical data are significantly enhanced by using the directional rather than the non-directional form of the human connectome. Specifically, we show that both the anterograde model of transmission (some to axonal terminal) and retrograde mode explain PSP topography more accurately than non-directional transmission. Collectively, these data show that the intrinsic architecture of the structural network mediates disease spread in PSP, most likely via a process of trans-neuronal transmission. These intriguing results have several ramifications for future studies.

A physical model for dementia

Aging associated brain decline often result in some kind of dementia. Even when this is a complex brain disorder a physical model can be used in order to describe its general behavior. A probabilistic model for the development of dementia is obtained and fitted to some experimental data obtained from the Alzheimer's Disease Neuroimaging Initiative. It is explained how dementia appears as a consequence of aging and why it is irreversible.

Is there a relation between novelty seeking, striatal dopamine release and frontal cortical thickness?

BACKGROUND

Novelty-seeking (NS) and impulsive personality traits have been proposed to reflect an interplay between fronto-cortical and limbic systems, including the limbic striatum (LS). Although neuroimaging studies have provided some evidence for this, most are comprised of small samples and many report surprisingly large effects given the challenges of trying to relate a snapshot of brain function or structure to an entity as complex as personality. The current work tested a priori hypotheses about associations between striatal dopamine (DA) release, cortical thickness (CT), and NS in a large sample of healthy adults.

METHODS

Fifty-two healthy adults (45M/7F; age: 23.8±4.93) underwent two positron emission tomography scans with [11C]raclopride (specific for striatal DA D2/3 receptors) with or without amphetamine (0.3 mg/kg, p.o.). Structural magnetic resonance image scans were acquired, as were Tridimensional Personality Questionnaire data. Amphetamine-induced changes in [11C]raclopride binding potential values (ΔBPND) were examined in the limbic, sensorimotor (SMS) and associative (AST) striatum. CT measures, adjusted for whole brain volume, were extracted from the dorsolateral sensorimotor and ventromedial/limbic cortices.

RESULTS

BPND values were lower in the amphetamine vs. no-drug sessions, with the largest effect in the LS. When comparing low vs. high LS ΔBPND groups (median split), higher NS2 (impulsiveness) scores were found in the high ΔBPND group. Partial correlations (age and gender as covariates) yielded a negative relation between ASTS ΔBPND and sensorimotor CT; trends for inverse associations existed between ΔBPND values in other striatal regions and frontal CT. In other words, the greater the amphetamine-induced striatal DA response, the thinner the frontal cortex.

CONCLUSIONS

These data expand upon previously reported associations between striatal DA release in the LS and both NS related impulsiveness and CT in the largest sample reported to date. The findings add to the plausibility of these associations while suggesting that the effects are likely weaker than has been previously proposed.

Estimating Intracranial Volume in Brain Research: An Evaluation of Methods

Intracranial volume (ICV) is a standard measure often used in morphometric analyses to correct for head size in brain studies. Inaccurate ICV estimation could introduce bias in the outcome. The current study provides a decision aid in defining protocols for ICV estimation across different subject groups in terms of sampling frequencies that can be optimally used on the volumetric MRI data, and type of software most suitable for use in estimating the ICV measure. Four groups of 53 subjects are considered, including adult controls (AC, adults with Alzheimer's disease (AD), pediatric controls (PC) and group of pediatric epilepsy subjects (PE). Reference measurements were calculated for each subject by manually tracing intracranial cavity without sub-sampling. The reliability of reference measurements were assured through intra- and inter- variation analyses. Three publicly well-known software packages (FreeSurfer Ver. 5.3.0, FSL Ver. 5.0, SPM8 and SPM12) were examined in their ability to automatically estimate ICV across the groups. Results on sub-sampling studies with a 95 % confidence showed that in order to keep the accuracy of the inter-leaved slice sampling protocol above 99 %, sampling period cannot exceed 20 mm for AC, 25 mm for PC, 15 mm for AD and 17 mm for the PE groups. The study assumes a priori knowledge about the population under study into the automated ICV estimation. Tuning of the parameters in FSL and the use of proper atlas in SPM showed significant reduction in the systematic bias and the error in ICV estimation via these automated tools. SPM12 with the use of pediatric template is found to be a more suitable candidate for PE group. SPM12 and FSL subjected to tuning are the more appropriate tools for the PC group. The random error is minimized for FS in AD group and SPM8 showed less systematic bias. Across the AC group, both SPM12 and FS performed well but SPM12 reported lesser amount of systematic bias.

Altered small-world anatomical networks in Apolipoprotein-E4 (ApoE4) carriers using MRI

Apolipoprotein E (ApoE) gene and primarily its allele e4 have been identified as a risk factor for Alzheimer's disease (AD). The prevalence of the gene in 25-30% in the population makes it essential to estimate its role in neuroregulation and its impact on distributed brain networks. In this study, we provide computational neuroanatomy based interpretation of large-scale and small-world cortical networks in cognitive normal (CN) subjects with differing Apolipoprotein-E4 (ApoE4) gene expression. We estimated large-scale anatomical networks from cortical thickness measurements derived from magnetic resonance imaging in 147 CN subjects explored in relation to ApoE4 genotype (e4+ carriers (n=41) versus e4- non-carriers (n=106)). Brain networks were constructed by thresholding cortical thickness correlation matrices of 68 bilateral regions of the brain analyzed using well-established graph theoretical approaches. Compared to ApoE4 non-carriers, carriers showed increased interregional correlation coefficients in regions like precentral, superior frontal and inferior temporal regions. Interestingly most of the altered connections were intra-hemispheric limited primarily to the right hemisphere. Furthermore, ApoE4 carriers demonstrated abnormal small-world architecture in the cortical networks with increased clustering coefficient and path lengths as compared to non-carrier, suggesting a less optimal topological organization. Additionally non-carriers demonstrated higher betweenness in regions such as middle temporal, para-hippocampal gyrus, posterior cingulate and insula of the default mode network (DMN), also seen in subjects with AD and mild cognitive impairment (MCI). The results suggest that the complex morphological cortical connectivity patterns are altered in ApoE4 carriers as compared to non-carriers, providing evidence for disruption of integrity in large-scale anatomical brain networks.

Comparative reliability analysis of publicly available software packages for automatic intracranial volume estimation

Intracranial volume is an important measure in brain research often used as a correction factor in inter subject studies. The current study investigates the resulting outcome in terms of the type of software used for automatically estimating ICV measure. Five groups of 70 subjects are considered, including adult controls (AC) (n=11), adult with dementia (AD) (n=11), pediatric controls (PC) (n=18) and two groups of pediatric epilepsy subjects (PE1.5 and PE3) (n=30) using 1.5 T and 3T scanners, respectively. Reference measurements were calculated for each subject by manually tracing intracranial cavity without sub-sampling. Four publicly available software packages (AFNI, Freesurfer, FSL, and SPM) were examined in their ability to automatically estimate ICV across the five groups. Linear regression analyses suggest that reference measurement discrepancy could be explained best by SPM [R(2)= 0.67;p <; 0.01] for the AC group, Freesurfer [R(2) = 0.46; p = 0.02] for the AD group, AFNI [R(2)=0.97;p<; 0.01] for the PC group and FSL [R(2) = 0.6; p = 0.1] for the PE1.5 and [R(2) = 0.6; p <; 0.01] for PE3 groups. The study demonstrates that the choice of the automated software for ICV estimation is dependent on the population under consideration and whether the software used is atlas-based or not.

Inclusion of Neuropsychological Scores in Atrophy Models Improves Diagnostic Classification of Alzheimer's Disease and Mild Cognitive Impairment

Brain atrophy in mild cognitive impairment (MCI) and Alzheimer's disease (AD) are difficult to demarcate to assess the progression of AD. This study presents a statistical framework on the basis of MRI volumes and neuropsychological scores. A feature selection technique using backward stepwise linear regression together with linear discriminant analysis is designed to classify cognitive normal (CN) subjects, early MCI (EMCI), late MCI (LMCI), and AD subjects in an exhaustive two-group classification process. Results show a dominance of the neuropsychological parameters like MMSE and RAVLT. Cortical volumetric measures of the temporal, parietal, and cingulate regions are found to be significant classification factors. Moreover, an asymmetrical distribution of the volumetric measures across hemispheres is seen for CN versus EMCI and EMCI versus AD, showing dominance of the right hemisphere; whereas CN versus LMCI and EMCI versus LMCI show dominance of the left hemisphere. A 2-fold cross-validation showed an average accuracy of 93.9%, 90.8%, and 94.5%, for the CN versus AD, CN versus LMCI, and EMCI versus AD, respectively. The accuracy for groups that are difficult to differentiate like EMCI versus LMCI was 73.6%. With the inclusion of the neuropsychological scores, a significant improvement (24.59%) was obtained over using MRI measures alone.

A practical guideline for intracranial volume estimation in patients with Alzheimer's disease

Background

Intracranial volume (ICV) is an important normalization measure used in morphometric analyses to correct for head size in studies of Alzheimer Disease (AD). Inaccurate ICV estimation could introduce bias in the outcome. The current study provides a decision aid in defining protocols for ICV estimation in patients with Alzheimer disease in terms of sampling frequencies that can be optimally used on the volumetric MRI data, and the type of software most suitable for use in estimating the ICV measure.

Methods

Two groups of 22 subjects are considered, including adult controls (AC) and patients with Alzheimer Disease (AD). Reference measurements were calculated for each subject by manually tracing intracranial cavity by the means of visual inspection. The reliability of reference measurements were assured through intra- and inter- variation analyses. Three publicly well-known software packages (Freesurfer, FSL, and SPM) were examined in their ability to automatically estimate ICV across the groups.

Results

Analysis of the results supported the significant effect of estimation method, gender, cognitive condition of the subject and the interaction among method and cognitive condition factors in the measured ICV. Results on sub-sampling studies with a 95% confidence showed that in order to keep the accuracy of the interleaved slice sampling protocol above 99%, the sampling period cannot exceed 20 millimeters for AC and 15 millimeters for AD. Freesurfer showed promising estimates for both adult groups. However SPM showed more consistency in its ICV estimation over the different phases of the study.

Conclusions

This study emphasized the importance in selecting the appropriate protocol, the choice of the sampling period in the manual estimation of ICV and selection of suitable software for the automated estimation of ICV. The current study serves as an initial framework for establishing an appropriate protocol in both manual and automatic ICV estimations with different subject populations.

Multivariate analysis of structural MRI and PET (FDG and 18F-AV-45) for Alzheimer's disease and its prodromal stages

A multivariate analysis method, orthogonal partial least squares to latent structures (OPLS), was used to discriminate Alzheimer's disease (AD), early and late mild cognitive impairment (EMCI and LMCI) from cognitively normal control (CN) using MRI and PET measures. FreeSurfer 5.1 generated 271 MRI features including 49 subcortical volumes, 68 cortical volumes, 68 cortical thicknesses, 70 surface areas and 16 hippocampus subfields. Subjects with all aforementioned MRI measures passing quality control and valid Fludeoxyglucose (18F) (FDG) and Florbetapir (18F) PET scans were selected from ADNI database, resulting in a total of 524 participants (137 CN, 214 EMCI, 103 LMCI and 70 AD) for the study. Altogether 286 features including 15 significant PET uptake features (7 for FDG and 8 for AV-45) were utilized for OPLS analysis. Predictive power was evaluated by Q2(Y), a quantifier of the statistical significance for class separation. The results show that MRI features (Q2(Y) =0.645), and PET features (Q2(Y) = 0.636) has comparable predictive power in separating AD from CN, and MRI features are better predictor of LMCI (Q2(Y) = 0.282) than PET (Q2(Y) = 0.294). Combination of PET and MRI has the most predictive power for LMCI and AD with Q2(Y) of 0.294 and 0.721, respectively. While for EMCI, cortical thickness was found to be the best predictor with a Q2(Y) of 0.108, suggesting cortical thickness may be the first structural change ahead of others and should be prioritized in prediction of very mild cognitive impairment.