It is well known that de-identified research brain images from MRI and CT can potentially be re-identified using face recognition; however, this has not been examined for PET images. We generated face reconstruction images of 182 volunteers using amyloid, tau, and FDG PET scans, and we measured how accurately commercial face recognition software (Microsoft Azure's Face API) automatically matched them with the individual participants' face photographs. We then compared this accuracy with the same experiments using participants' CT and MRI. Face reconstructions from PET images from PET/CT scanners were correctly matched at rates of 42% (FDG), 35% (tau), and 32% (amyloid), while CT were matched at 78% and MRI at 97-98%. We propose that these recognition rates are high enough that research studies should consider using face de-identification ("de-facing") software on PET images, in addition to CT and structural MRI, before data sharing. We also updated our mri_reface de-identification software with extended functionality to replace face imagery in PET and CT images. Rates of face recognition on de-faced images were reduced to 0-4% for PET, 5% for CT, and 8% for MRI. We measured the effects of de-facing on regional amyloid PET measurements from two different measurement pipelines (PETSurfer/FreeSurfer 6.0, and one in-house method based on SPM12 and ANTs), and these effects were small: ICC values between de-faced and original images were > 0.98, biases were <2%, and median relative errors were < 2%. Effects on global amyloid PET SUVR measurements were even smaller: ICC values were 1.00, biases were <0.5%, and median relative errors were also <0.5%.

Early Alzheimer's disease can involve social disinvestment, possibly as a consequence of impairment of nonverbal communication skills. This study explores whether patients with Alzheimer's disease at the mild cognitive impairment or mild dementia stage have impaired recognition of emotions in facial expressions, and describes neuroanatomical correlates of emotion processing impairment. As part of the ongoing PACO study (personality, Alzheimer's disease and behaviour), 39 patients with Alzheimer's disease at the mild cognitive impairment or mild dementia stage and 39 matched controls completed tests involving discrimination of four basic emotions-happiness, fear, anger, and disgust-on photographs of faces. In patients, automatic volumetry of 83 brain regions was performed on structural magnetic resonance images using MAPER (multi-atlas propagation with enhanced registration). From the literature, we identified for each of the four basic emotions one brain region thought to be primarily associated with the function of recognizing that emotion. We hypothesized that the volume of each of these regions would be correlated with subjects' performance in recognizing the associated emotion. Patients showed deficits of basic emotion recognition, and these impairments were correlated with the volumes of the expected regions of interest. Unexpectedly, most of these correlations were negative: better emotional facial recognition was associated with lower brain volume. In particular, recognition of fear was negatively correlated with the volume of amygdala, disgust with pallidum, and happiness with fusiform gyrus. Recognition impairment in mild stages of Alzheimer's disease for a given emotion was thus associated with less visible atrophy of functionally responsible brain structures within the patient group. Possible explanations for this counterintuitive result include neuroinflammation, regional β-amyloid deposition, or transient overcompensation during early stages of Alzheimer's disease.

We describe the Queensland Twin Adolescent Brain (QTAB) dataset and provide a detailed methodology and technical validation to facilitate data usage. The QTAB dataset comprises multimodal neuroimaging, as well as cognitive and mental health data collected in adolescent twins over two sessions (session 1: N = 422, age 9-14 years; session 2: N = 304, 10-16 years). The MRI protocol consisted of T1-weighted (MP2RAGE), T2-weighted, FLAIR, high-resolution TSE, SWI, resting-state fMRI, DWI, and ASL scans. Two fMRI tasks were added in session 2: an emotional conflict task and a passive movie-watching task. Outside of the scanner, we assessed cognitive function using standardised tests. We also obtained self-reports of symptoms for anxiety and depression, perceived stress, sleepiness, pubertal development measures, and risk and protective factors. We additionally collected several biological samples for genomic and metagenomic analysis. The QTAB project was established to promote health-related research in adolescence.

Visual cognition such as face recognition requests a high degree of functional integration between distributed brain areas of a network. It has been reported that the fusiform gyrus (FG) is an important brain area involved in facial cognition; altered connectivity of FG to some other regions may lead to a deficit in visual cognition especially face recognition. However, whether functional connectivity between the FG and other brain areas changes remains unclear in the resting state in amnestic mild cognitive impairment (aMCI) subjects. Here, we employed a resting-state functional MRI (fMRI) to examine alterations in functional connectivity of left/right FG comparing aMCI patients with age-matched control subjects. Forty-eight aMCI and 38 control subjects from the Alzheimer's disease Neuroimaging Initiative were analyzed. We concentrated on the correlation between low frequency fMRI time courses in the FG and those in all other brain regions. Relative to the control group, we found some discrepant regions in the aMCI group which presented increased or decreased connectivity with the left/right FG including the left precuneus, left lingual gyrus, right thalamus, supramarginal gyrus, left supplementary motor area, left inferior temporal gyrus, and left parahippocampus. More importantly, we also obtained that both left and right FG have increased functional connections with the left middle occipital gyrus (MOG) and right anterior cingulate gyrus (ACC) in aMCI patients. That was not a coincidence and might imply that the MOG and ACC also play a critical role in visual cognition, especially face recognition. These findings in a large part supported our hypothesis and provided a new insight in understanding the important subtype of MCI.

While sarcasm can be conveyed solely through contextual cues such as counterfactual or echoic statements, face-to-face sarcastic speech may be characterized by specific paralinguistic features that alert the listener to interpret the utterance as ironic or critical, even in the absence of contextual information. We investigated the neuroanatomy underlying failure to understand sarcasm from dynamic vocal and facial paralinguistic cues. Ninety subjects (20 frontotemporal dementia, 11 semantic dementia [SemD], 4 progressive non-fluent aphasia, 27 Alzheimer's disease, 6 corticobasal degeneration, 9 progressive supranuclear palsy, 13 healthy older controls) were tested using the Social Inference - Minimal subtest of The Awareness of Social Inference Test (TASIT). Subjects watched brief videos depicting sincere or sarcastic communication and answered yes-no questions about the speaker's intended meaning. All groups interpreted Sincere (SIN) items normally, and only the SemD group was impaired on the Simple Sarcasm (SSR) condition. Patients failing the SSR performed more poorly on dynamic emotion recognition tasks and had more neuropsychiatric disturbances, but had better verbal and visuospatial working memory than patients who comprehended sarcasm. Voxel-based morphometry analysis of SSR scores in SPM5 demonstrated that poorer sarcasm comprehension was predicted by smaller volume in bilateral posterior parahippocampi (PHc), temporal poles, and R medial frontal pole (pFWE<0.05). This study provides lesion data suggesting that the PHc may be involved in recognizing a paralinguistic speech profile as abnormal, leading to interpretive processing by the temporal poles and right medial frontal pole that identifies the social context as sarcastic, and recognizes the speaker's paradoxical intentions.

Alzheimer's disease (AD) is a progressive disorder associated with cognitive dysfunction that alters the brain's functional connectivity. Assessing these alterations has become a topic of increasing interest. However, a few studies have examined different stages of AD from a complex network perspective that cover different topological scales. This study used resting state fMRI data to analyze the trend of functional connectivity alterations from a cognitively normal (CN) state through early and late mild cognitive impairment (EMCI and LMCI) and to Alzheimer's disease. The analyses had been done at the local (hubs and activated links and areas), meso (clustering, assortativity, and rich-club), and global (small-world, small-worldness, and efficiency) topological scales. The results showed that the trends of changes in the topological architecture of the functional brain network were not entirely proportional to the AD progression. There were network characteristics that have changed non-linearly regarding the disease progression, especially at the earliest stage of the disease, i.e., EMCI. Further, it has been indicated that the diseased groups engaged somatomotor, frontoparietal, and default mode modules compared to the CN group. The diseased groups also shifted the functional network towards more random architecture. In the end, the methods introduced in this paper enable us to gain an extensive understanding of the pathological changes of the AD process.

A coding missense mutation (rs3747742) in triggering receptor expressed on myeloid cell-like 2 (TREML2) has been recently proposed as an important protective factor against Alzheimer's disease (AD). However, the link between TREML2 and AD pathology remains unclear. Therefore, we explored the association of TREML2 rs3747742 with cognitive function, neuroimaging biomarkers and cerebrospinal fluid (CSF) biomarkers related to AD, including CSF total-tau (T-tau), phosphor-tau (P-tau), and amyloid-β (Aβ1-42). As for cognitive function, related cognitive scores of Clinical Dementia Rating Sum of Boxes (CDRSB), Alzheimer's Disease Assessment Scale-cognitive section 11 (ADAS-cog 11), Mini-Mental State Examination (MMSE), and Rey Auditory-Verbal Learning Test (RAVLT) were extracted. We used a multiple linear regression model to examine the association of TREML2 rs3747742 with the baseline variables. Furthermore, we also calculated the change rate of above variables influenced by TREML2 rs3747742 via applying a mixed-effects model over a 4-year follow-up. In this analysis, a total of 1,306 individuals from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database were included. Finally, we observed that only in AD patients, but not in normal controls or mild cognitive impairment (MCI) individuals, TREML2 rs3747742 exhibited a strong association with CSF total-tau levels at baseline (β = -22.1210, p = 0.0166) and 4-year follow-up (β = -0.3961, p = 0.0115). Furthermore, no associations were found with CSF Aβ1-42 levels, P-tau levels, neuroimaging biomarkers and cognitive function neither for baseline variables nor for longitudinal data. Thus, this study indicated that TREML2 mediated the risk of AD through influencing AD-related neurodegeneration (abnormal T-tau levels) but not P-tau levels and Aβ pathology.

Research utilizing magnetic resonance imaging (MRI) has been crucial to the understanding of the neuropathological mechanisms behind and clinical identification of Alzheimer's disease (AD) and mild cognitive impairment (MCI). MRI modalities show patterns of brain damage that discriminate AD from other brain illnesses and brain abnormalities that are associated with risk of conversion to AD from MCI and other behavioural outcomes. This review discusses the application of various MRI techniques to and their clinical usefulness in AD and MCI. MRI modalities covered include structural MRI, diffusion tensor imaging (DTI), arterial spin labelling (ASL), magnetic resonance spectroscopy (MRS), and functional MRI (fMRI). There is much evidence supporting the validity of MRI as a biomarker for these disorders; however, only traditional structural imaging is currently recommended for routine use in clinical settings. Future research is needed to warrant the inclusion for more advanced MRI methodology in forthcoming revisions to diagnostic criteria for AD and MCI.

Biological data mining is a powerful tool that can provide a wealth of information about patterns of genetic and genomic biomarkers of health and disease. A potential disadvantage of data mining is volume and complexity of the results that can often be overwhelming. It is our working hypothesis that visualization methods can greatly enhance our ability to make sense of data mining results. More specifically, we propose that 3-D printing has an important role to play as a visualization technology in biological data mining. We provide here a brief review of 3-D printing along with a case study to illustrate how it might be used in a research setting.

This study's aims are to identify whether or not a relationship between statin use and rate of cognitive decline exists.

Genome-wide association studies (GWAS) provide a powerful means to identify associations between genetic variants and phenotypes. However, GWAS techniques for detecting epistasis, the interactions between genetic variants associated with phenotypes, are still limited. We believe that developing an efficient and effective GWAS method to detect epistasis will be a key for discovering sophisticated pathogenesis, which is especially important for complex diseases such as Alzheimer's disease (AD).

Accurate and realistic simulation of high-dimensional medical images has become an important research area relevant to many AI-enabled healthcare applications. However, current state-of-the-art approaches lack the ability to produce satisfactory high-resolution and accurate subject-specific images. In this work, we present a deep learning framework, namely 4D-Degenerative Adversarial NeuroImage Net (4D-DANI-Net), to generate high-resolution, longitudinal MRI scans that mimic subject-specific neurodegeneration in ageing and dementia. 4D-DANI-Net is a modular framework based on adversarial training and a set of novel spatiotemporal, biologically-informed constraints. To ensure efficient training and overcome memory limitations affecting such high-dimensional problems, we rely on three key technological advances: i) a new 3D training consistency mechanism called Profile Weight Functions (PWFs), ii) a 3D super-resolution module and iii) a transfer learning strategy to fine-tune the system for a given individual. To evaluate our approach, we trained the framework on 9852 T1-weighted MRI scans from 876 participants in the Alzheimer's Disease Neuroimaging Initiative dataset and held out a separate test set of 1283 MRI scans from 170 participants for quantitative and qualitative assessment of the personalised time series of synthetic images. We performed three evaluations: i) image quality assessment; ii) quantifying the accuracy of regional brain volumes over and above benchmark models; and iii) quantifying visual perception of the synthetic images by medical experts. Overall, both quantitative and qualitative results show that 4D-DANI-Net produces realistic, low-artefact, personalised time series of synthetic T1 MRI that outperforms benchmark models.

Alzheimer's disease is the most common neurodegenerative disease and is characterized by the accumulation of amyloid-beta peptides leading to the formation of plaques and tau protein tangles in brain. These neuropathological features precede cognitive impairment and Alzheimer's dementia by many years. To better understand and predict the course of disease from early-stage asymptomatic to late-stage dementia, it is critical to study the patterns of progression of multiple markers. In particular, we aim to predict the likely future course of progression for individuals given only a single observation of their markers. Improved individual-level prediction may lead to improved clinical care and clinical trials. We propose a two-stage approach to modeling and predicting measures of cognition, function, brain imaging, fluid biomarkers, and diagnosis of individuals using multiple domains simultaneously. In the first stage, joint (or multivariate) mixed-effects models are used to simultaneously model multiple markers over time. In the second stage, random forests are used to predict categorical diagnoses (cognitively normal, mild cognitive impairment, or dementia) from predictions of continuous markers based on the first-stage model. The combination of the two models allows one to leverage their key strengths in order to obtain improved accuracy. We characterize the predictive accuracy of this two-stage approach using data from the Alzheimer's Disease Neuroimaging Initiative. The two-stage approach using a single joint mixed-effects model for all continuous outcomes yields better diagnostic classification accuracy compared to using separate univariate mixed-effects models for each of the continuous outcomes. Overall prediction accuracy above 80% was achieved over a period of 2.5 years. The results further indicate that overall accuracy is improved when markers from multiple assessment domains, such as cognition, function, and brain imaging, are used in the prediction algorithm as compared to the use of markers from a single domain only.

Prediction of subject age from brain anatomical MRI has the potential to provide a sensitive summary of brain changes, indicative of different neurodegenerative diseases. However, existing studies typically neglect the uncertainty of these predictions. In this work we take into account this uncertainty by applying methods of functional data analysis. We propose a penalised functional quantile regression model of age on brain structure with cognitively normal (CN) subjects in the Alzheimer's Disease Neuroimaging Initiative (ADNI), and use it to predict brain age in Mild Cognitive Impairment (MCI) and Alzheimer's Disease (AD) subjects. Unlike the machine learning approaches available in the literature of brain age prediction, which provide only point predictions, the outcome of our model is a prediction interval for each subject.

Automated methods for Alzheimer's disease (AD) classification have the potential for great clinical benefits and may provide insight for combating the disease. Machine learning, and more specifically deep neural networks, have been shown to have great efficacy in this domain. These algorithms often use neurological imaging data such as MRI and FDG PET, but a comprehensive and balanced comparison of the MRI and amyloid PET modalities has not been performed. In order to accurately determine the relative strength of each imaging variant, this work performs a comparison study in the context of Alzheimer's dementia classification using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with identical neural network architectures. Furthermore, this work analyzes the benefits of using both modalities in a fusion setting and discusses how these data types may be leveraged in future AD studies using deep learning.

In Mendelian randomization (MR), inference about causal relationship between a phenotype of interest and a response or disease outcome can be obtained by constructing instrumental variables from genetic variants. However, MR inference requires three assumptions, one of which is that the genetic variants only influence the outcome through phenotype of interest. Pleiotropy, that is, the situation in which some genetic variants affect more than one phenotype, can invalidate these genetic variants for use as instrumental variables; thus a naive analysis will give biased estimates of the causal relation. Here, we present new methods (constrained instrumental variable [CIV] methods) to construct valid instrumental variables and perform adjusted causal effect estimation when pleiotropy exists and when the pleiotropic phenotypes are available. We demonstrate that a smoothed version of CIV performs approximate selection of genetic variants that are valid instruments, and provides unbiased estimates of the causal effects. We provide details on a number of existing methods, together with a comparison of their performance in a large series of simulations. CIV performs robustly across different pleiotropic violations of the MR assumptions. We also analyzed the data from the Alzheimer's disease (AD) neuroimaging initiative (ADNI; Mueller et al., 2005. Alzheimer's Dementia, 11(1), 55-66) to disentangle causal relationships of several biomarkers with AD progression.

Ideal biomarkers of Alzheimer's disease (AD) should correlate with accepted measures of pathology in the cerebrospinal fluid (CSF); they should also correlate with, or predict, future clinical decline, and should be readily measured in hundreds to thousands of subjects. Here we explored the utility of automated 3D maps of the lateral ventricles as a possible biomarker of AD. We used our multi-atlas fluid image alignment (MAFIA) method, to compute ventricular models automatically, without user intervention, from 804 brain MRI scans with 184 AD, 391 mild cognitive impairment (MCI), and 229 healthy elderly controls (446 men, 338 women; age: 75.50 +/- 6.81 [SD] years). Radial expansion of the ventricles, computed pointwise, was strongly correlated with current cognition, depression ratings, Hachinski Ischemic scores, language scores, and with future clinical decline after controlling for any effects of age, gender, and educational level. In statistical maps ranked by effect sizes, ventricular differences were highly correlated with CSF measures of Abeta(1-42), and correlated with ApoE4 genotype. These statistical maps are highly automated, and offer a promising biomarker of AD for large-scale studies.

We report on the ongoing project "PREDICT-ADFTD: Multimodal Imaging Prediction of AD/FTD and Differential Diagnosis" describing completed and future work supported by this grant. This project is a multi-site, multi-study collaboration effort with research spanning seven sites across the US and Canada. The overall goal of the project is to study neurodegeneration within Alzheimer's Disease, Frontotemporal Dementia, and related neurodegenerative disorders, using a variety of brain imaging and computational techniques to develop methods for the early and accurate prediction of disease and its course. The overarching goal of the project is to develop the earliest and most accurate biomarker that can differentiate clinical diagnoses to inform clinical trials and patient care. In its third year, this project has already completed several projects to achieve this goal, focusing on (1) structural MRI (2) machine learning and (3) FDG-PET and multimodal imaging. Studies utilizing structural MRI have identified key features of underlying pathology by studying hippocampal deformation that is unique to clinical diagnosis and also post-mortem confirmed neuropathology. Several machine learning experiments have shown high classification accuracy in the prediction of disease based on Convolutional Neural Networks utilizing MRI images as input. In addition, we have also achieved high accuracy in predicting conversion to DAT up to five years in the future. Further, we evaluated multimodal models that combine structural and FDG-PET imaging, in order to compare the predictive power of multimodal to unimodal models. Studies utilizing FDG-PET have shown significant predictive ability in the prediction and progression of disease.

The increasing incidence of Alzheimer's disease (AD) has been leading towards a significant growth in socioeconomic challenges. A reliable prediction of AD might be useful to mitigate or at-least slow down its progression for which, identification of the factors affecting the AD and its accurate diagnoses, are vital. In this study, we use Genome-Wide Association Studies (GWAS) dataset which comprises significant genetic markers of complex diseases. The original dataset contains large number of attributes (620901) for which we propose a hybrid feature selection approach based on association test, principal component analysis, and the Boruta algorithm, to identify the most promising predictors of AD. The selected features are then forwarded to a wide and deep neural network models to classify the AD cases and healthy controls. The experimental outcomes indicate that our approach outperformed the existing methods when evaluated on standard dataset, producing an accuracy and f1-score of 99%. The outcomes from this study are impactful particularly, the identified features comprising AD-associated genes and a reliable classification model that might be useful for other chronic diseases.

Objectives: Neuropsychological tests are an important basis for the memory impairment diagnosis in Alzheimer's disease (AD). However, multiple memory tests might be conflicting within-subjects and lead to uncertain diagnoses in some cases. This study proposed a framework to diagnose the uncertain cases of memory impairment. Methods: We collected 2,386 samples including AD, mild cognitive impairment (MCI), and cognitive normal (CN) using 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) and three different neuropsychological tests (Mini-Mental State Examination, Alzheimer's Disease Assessment Scale-Cognitive Subscale, and Clinical Dementia Rating) from the Alzheimer's Disease Neuroimaging Initiative (ADNI). A deep learning (DL) framework using FDG-PET was proposed to diagnose uncertain memory impairment cases that were conflicting between tests. Subsequent ANOVA, chi-squared, and t-test were used to explain the potential causes of uncertain cases. Results: For certain cases in the testing set, the proposed DL framework outperformed other methods with 95.65% accuracy. For the uncertain cases, its positive diagnoses had a significant (p < 0.001) worse decline in memory function than negative diagnoses in a longitudinal study of 40 months on average. In the memory-impaired group, uncertain cases were mainly explained by an AD metabolism pattern but mild in extent (p < 0.05). In the healthy group, uncertain cases were mainly explained by a non-energetic mental state (p < 0.001) measured using a global deterioration scale (GDS), with a significant depression-related metabolism pattern detected (p < 0.05). Conclusion: A DL framework for diagnosing uncertain cases of memory impairment is proposed. Proved by longitudinal tracing of its diagnoses, it showed clinical validity and had application potential. Its valid diagnoses also provided evidence and explanation of uncertain cases based on the neurodegeneration and depression mental state.