Explore the vast range of titles available.

Similar to most chronic diseases, Alzheimer's disease (AD) develops slowly from a preclinical phase into a fully expressed clinical syndrome. We aimed to use longitudinal data to calculate the rates of amyloid β (Aβ) deposition, cerebral atrophy, and cognitive decline. In this prospective cohort study, healthy controls, patients with mild cognitive impairment (MCI), and patients with AD were assessed at enrolment and every 18 months. At every visit, participants underwent neuropsychological examination, MRI, and a carbon-11-labelled Pittsburgh compound B (11C-PiB) PET scan. We included participants with three or more 11C-PiB PET follow-up assessments. Aβ burden was expressed as 11C-PiB standardised uptake value ratio (SUVR) with the cerebellar cortex as reference region. An SUVR of 1·5 was used to discriminate high from low Aβ burdens. The slope of the regression plots over 3–5 years was used to estimate rates of change for Aβ deposition, MRI volumetrics, and cognition. We included those participants with a positive rate of Aβ deposition to calculate the trajectory of each variable over time. 200 participants (145 healthy controls, 36 participants with MCI, and 19 participants with AD) were assessed at enrolment and every 18 months for a mean follow-up of 3·8 (95% CI CI 3·6–3·9) years. At baseline, significantly higher Aβ burdens were noted in patients with AD (2·27, SD 0·43) and those with MCI (1·94, 0·64) than in healthy controls (1·38, 0·39). At follow-up, 163 (82%) of the 200 participants showed positive rates of Aβ accumulation. Aβ deposition was estimated to take 19·2 (95% CI 16·8–22·5) years in an almost linear fashion—with a mean increase of 0·043 (95% CI 0·037–0·049) SUVR per year—to go from the threshold of 11C-PiB positivity (1·5 SUVR) to the levels observed in AD. It was estimated to take 12·0 (95% CI 10·1–14·9) years from the levels observed in healthy controls with low Aβ deposition (1·2 [SD 0·1] SUVR) to the threshold of 11C-PiB positivity. As AD progressed, the rate of Aβ deposition slowed towards a plateau. Our projections suggest a prolonged preclinical phase of AD in which Aβ deposition reaches our threshold of positivity at 17·0 (95% CI 14·9–19·9) years, hippocampal atrophy at 4·2 (3·6–5·1) years, and memory impairment at 3·3 (2·5–4·5) years before the onset of dementia (clinical dementia rating score 1). Aβ deposition is slow and protracted, likely to extend for more than two decades. Such predictions of the rate of preclinical changes and the onset of the clinical phase of AD will facilitate the design and timing of therapeutic interventions aimed at modifying the course of this illness. Science and Industry Endowment Fund (Australia), The Commonwealth Scientific and Industrial Research Organisation (Australia), The National Health and Medical Research Council of Australia Program and Project Grants, the Austin Hospital Medical Research Foundation, Victorian State Government, The Alzheimer's Drug Discovery Foundation, and the Alzheimer's Association.

PurposePrevious studies have shown that Aβ-amyloid (Aβ) likely promotes tau to spread beyond the medial temporal lobe. However, the Aβ levels necessary for tau to spread in the neocortex is still unclear.MethodsFour hundred sixty-six participants underwent tau imaging with [18F]MK6420 and Aβ imaging with [18F]NAV4694. Aβ scans were quantified on the Centiloid (CL) scale with a cut-off of 25 CL for abnormal levels of Aβ (A+). Tau scans were quantified in three regions of interest (ROI) (mesial temporal (Me); temporoparietal neocortex (Te); and rest of neocortex (R)) and four mesial temporal region (entorhinal cortex, amygdala, hippocampus, and parahippocampus). Regional tau thresholds were established as the 95%ile of the cognitively unimpaired A- subjects. The prevalence of abnormal tau levels (T+) along the Centiloid continuum was determined.ResultsThe plots of prevalence of T+ show earlier and greater increase along the Centiloid continuum in the medial temporal area compared to neocortex. Prevalence of T+ was low but associated with Aβ level between 10 and 40 CL reaching 23% in Me, 15% in Te, and 11% in R. Between 40 and 70 CL, the prevalence of T+ subjects per CL increased fourfold faster and at 70 CL was 64% in Me, 51% in Te, and 37% in R. In cognitively unimpaired, there were no T+ in R below 50 CL. The highest prevalence of T+ were found in the entorhinal cortex, reaching 40% at 40 CL and 80% at 60 CL.ConclusionOutside the entorhinal cortex, abnormal levels of cortical tau on PET are rarely found with Aβ below 40 CL. Above 40 CL prevalence of T+ accelerates in all areas. Moderate Aβ levels are required before abnormal neocortical tau becomes detectable.

To improve understanding of Alzheimer’s disease, large observational studies are needed to increase power for more nuanced analyses. Combining data across existing observational studies represents one solution. However, the disparity of such datasets makes this a non-trivial task. Here, a machine learning approach was applied to impute longitudinal neuropsychological test scores across two observational studies, namely the Australian Imaging, Biomarkers and Lifestyle Study (AIBL) and the Alzheimer's Disease Neuroimaging Initiative (ADNI) providing an overall harmonised dataset. MissForest, a machine learning algorithm, capitalises on the underlying structure and relationships of data to impute test scores not measured in one study aligning it to the other study. Results demonstrated that simulated missing values from one dataset could be accurately imputed, and that imputation of actual missing data in one dataset showed comparable discrimination (p < 0.001) for clinical classification to measured data in the other dataset. Further, the increased power of the overall harmonised dataset was demonstrated by observing a significant association between CVLT-II test scores (imputed for ADNI) with PET Amyloid-β in MCI APOE -ε4 homozygotes in the imputed data (N = 65) but not for the original AIBL dataset (N = 11). These results suggest that MissForest can provide a practical solution for data harmonization using imputation across studies to improve power for more nuanced analyses.

Preterm birth imposes a high risk for developing neuromotor delay. Earlier prediction of adverse outcome in preterm infants is crucial for referral to earlier intervention. This study aimed to predict abnormal motor outcome at 2 years from early brain diffusion magnetic resonance imaging (MRI) acquired between 29 and 35 weeks postmenstrual age (PMA) using a deep learning convolutional neural network (CNN) model. Seventy-seven very preterm infants (born <31 weeks gestational age (GA)) in a prospective longitudinal cohort underwent diffusion MR imaging (3T Siemens Trio; 64 directions, b ​= ​2000 ​s/mm2). Motor outcome at 2 years corrected age (CA) was measured by Neuro-Sensory Motor Developmental Assessment (NSMDA). Scores were dichotomised into normal (functional score: 0, normal; n ​= ​48) and abnormal scores (functional score: 1–5, mild-profound; n ​= ​29). MRIs were pre-processed to reduce artefacts, upsampled to 1.25 ​mm isotropic resolution and maps of fractional anisotropy (FA) were estimated. Patches extracted from each image were used as inputs to train a CNN, wherein each image patch predicted either normal or abnormal outcome. In a postprocessing step, an image was classified as predicting abnormal outcome if at least 27% (determined by a grid search to maximise the model performance) of its patches predicted abnormal outcome. Otherwise, it was considered as normal. Ten-fold cross-validation was used to estimate performance. Finally, heatmaps of model predictions for patches in abnormal scans were generated to explore the locations associated with abnormal outcome. For the identification of infants with abnormal motor outcome based on the FA data from early MRI, we achieved mean sensitivity 70% (standard deviation SD 19%), mean specificity 74% (SD 39%), mean AUC (area under the receiver operating characteristic curve) 72% (SD 14%), mean F1 score of 68% (SD 13%) and mean accuracy 73% (SD 19%) on an unseen test data set. Patch-based prediction heatmaps showed that the patches around the motor cortex and somatosensory regions were most frequently identified by the model with high precision (74%) as a location associated with abnormal outcome. Part of the cerebellum, and occipital and frontal lobes were also highly associated with abnormal NSMDA/motor outcome. This study established the potential of an early brain MRI-based deep learning CNN model to identify preterm infants at risk of a later motor impairment and to identify brain regions predictive of adverse outcome. Results suggest that predictions can be made from FA maps of diffusion MRIs well before term equivalent age (TEA) without any prior knowledge of which MRI features to extract and associated feature extraction steps. This method, therefore, is suitable for any case of brain condition/abnormality. Future studies should be conducted on a larger cohort to re-validate the robustness and effectiveness of these models. •A CNN model is able to predict motor outcome from the brain diffusion MRI.•Motor cortex and somatosensory regions had the highest association with abnormality.•Significant implications for targeted early interventions in preterm infants.

Brain amyloid β (Aβ) deposition and neurodegeneration have been documented in about 50–60% of cognitively healthy elderly individuals (aged 60 years or older). The long-term cognitive consequences of the presence of Alzheimer's disease pathology and neurodegeneration, and whether they have an independent or synergistic effect on cognition, are unclear. We aimed to characterise the long-term clinical and cognitive trajectories of healthy elderly individuals using a two-marker (Alzheimer's disease pathology and neurodegeneration) imaging construct. Between Nov 3, 2006, and Nov 25, 2014, 573 cognitively healthy individuals in Melbourne and Perth, Australia, (mean age 73·1 years [SD 6·2]; 58% women) were enrolled in the Australian Imaging, Biomarker and Lifestyle (AIBL) study. Alzheimer's disease pathology (A) was determined by measuring Aβ deposition by PET, and neurodegeneration (N) was established by measuring hippocampal volume using MRI. Individuals were categorised as A−N−, A+N−, A+N+, or suspected non-Alzheimer's disease pathophysiology (A−N+, SNAP). Clinical progression, hippocampal volume, standard neuropsychological tests, and domain-specific and global cognitive composite scores were assessed over 6 years of follow-up. Linear mixed effect models and a Cox proportional hazards model of survival were used to evaluate, compare, and contrast the clinical, cognitive, and volumetric trajectories of patients in the four AN categories. 50 (9%) healthy individuals were classified as A+N+, 87 (15%) as A+N−, 310 (54%) as A−N−, and 126 (22%) as SNAP. APOE ε4 was more frequent in participants in the A+N+ (27; 54%) and A+N− (42; 48%) groups than in the A−N− (66; 21%) and SNAP groups (23; 18%). The A+N− and A+N+ groups had significantly faster cognitive decline than the A−N− group (0·08 SD per year for AIBL-Preclinical AD Cognitive Composite [PACC]; p<0·0001; and 0·25; p<0·0001; respectively). The A +N+ group also had faster hippocampal atrophy than the A−N− group (0·04 cm3 per year; p=0·02). The SNAP group generally did not show significant decline over time compared with the A−N− group (0·03 SD per year [p=0·19] for AIBL-PACC and a 0·02 cm3 per year increase [p=0·16] for hippocampal volume), although SNAP was sometimes associated with lower baseline cognitive scores (0·20 SD less than A−N− for AIBL-PACC). Within the follow-up, 24% (n=12) of individuals in the A+N+ group and 16% (n=14) in the A+N− group progressed to amnestic mild cognitive impairment or Alzheimer's disease, compared with 9% (n=11) in the SNAP group. Brain amyloidosis, a surrogate marker of Alzheimer's disease pathology, is a risk factor for cognitive decline and for progression from preclinical stages to symptomatic stages of the disease, with neurodegeneration acting as a compounding factor. However, neurodegeneration alone does not confer a significantly different risk of cognitive decline from that in the group with neither brain amyloidosis or neurodegeneration. CSIRO Flagship Collaboration Fund and the Science and Industry Endowment Fund (SIEF), National Health and Medical Research Council, the Dementia Collaborative Research Centres programme, McCusker Alzheimer's Research Foundation, and Operational Infrastructure Support from the Government of Victoria.

Understanding structure–function relationships in the brain after stroke is reliant not only on the accurate anatomical delineation of the focal ischemic lesion, but also on previous infarcts, remote changes and the presence of white matter hyperintensities. The robust definition of primary stroke boundaries and secondary brain lesions will have significant impact on investigation of brain–behavior relationships and lesion volume correlations with clinical measures after stroke. Here we present an automated approach to identify chronic ischemic infarcts in addition to other white matter pathologies, that may be used to aid the development of post-stroke management strategies. Our approach uses Bayesian–Markov Random Field (MRF) classification to segment probable lesion volumes present on fluid attenuated inversion recovery (FLAIR) MRI. Thereafter, a random forest classification of the information from multimodal (T1-weighted, T2-weighted, FLAIR, and apparent diffusion coefficient (ADC)) MRI images and other context-aware features (within the probable lesion areas) was used to extract areas with high likelihood of being classified as lesions. The final segmentation of the lesion was obtained by thresholding the random forest probabilistic maps. The accuracy of the automated lesion delineation method was assessed in a total of 36 patients (24 male, 12 female, mean age: 64.57±14.23yrs) at 3months after stroke onset and compared with manually segmented lesion volumes by an expert. Accuracy assessment of the automated lesion identification method was performed using the commonly used evaluation metrics. The mean sensitivity of segmentation was measured to be 0.53±0.13 with a mean positive predictive value of 0.75±0.18. The mean lesion volume difference was observed to be 32.32%±21.643% with a high Pearson's correlation of r=0.76 (p<0.0001). The lesion overlap accuracy was measured in terms of Dice similarity coefficient with a mean of 0.60±0.12, while the contour accuracy was observed with a mean surface distance of 3.06mm±3.17mm. The results signify that our method was successful in identifying most of the lesion areas in FLAIR with a low false positive rate. [Display omitted] •Segmentation of chronic ischemic and other lesions impacting poststroke depression.•Hierarchical segmentation of the probable lesion from FLAIR using Bayesian-MRF.•Random-forest (RF) probabilistic classification on probable lesion class.•Context-rich features used in RF include multimodal MRI and lesion likelihood.

: Centiloid was introduced to harmonise β-Amyloid (Aβ) PET quantification across different tracers, scanners and analysis techniques. Unfortunately, Centiloid still suffers from some quantification disparities in longitudinal analysis when normalising data from different tracers or scanners. In this work, we aim to reduce this variability using a different analysis technique applied to the existing calibration data. : All PET images from the Centiloid calibration dataset, along with 3762 PET images from the AIBL study were analysed using the recommended SPM pipeline. The PET images were SUVR normalised using the whole cerebellum. All SUVR normalised PiB images from the calibration dataset were decomposed using non-negative matrix factorisation (NMF). The NMF coefficients related to the first component were strongly correlated with global SUVR and were subsequently used as a surrogate for Aβ retention. For each tracer of the calibration dataset, the components of the NMF were computed in a way such that the coefficients of the first component would match those of the corresponding PiB. Given the strong correlations between the SUVR and the NMF coefficients on the calibration dataset, all PET images from AIBL were subsequently decomposed using the computed NMF, and their coefficients transformed into Centiloids. : Using the AIBL data, the correlation between the standard Centiloid and the novel NMF-based Centiloid was high in each tracer. The NMF-based Centiloids showed a reduction of outliers, and improved longitudinal consistency. Furthermore, it removed the effects of switching tracers from the longitudinal variance of the Centiloid measure, when assessed using a linear mixed effects model. : We here propose a novel image driven method to perform the Centiloid quantification. The methods is highly correlated with standard Centiloids while improving the longitudinal reliability when switching tracers. Implementation of this method across multiple studies may lend to more robust and comparable data for future research.

•The first component of probabilistic principal component analysis can summarise patient states in a single score by capturing variability in Alzheimer’s Disease biomarkers from cohorts such as ADNI.•Per-patient scores are similar to realignment parameters in more complex disease progression models.•We conducted exhaustive experiments to verify the robustness of the computed score to different subsets of biomarkers or measurements missing at random.•Projections of individual trajectories can be refined as follow-up data becomes available, without retraining the entire model. The recent biological redefinition of Alzheimer’s Disease (AD) has spurred the development of statistical models that relate changes in biomarkers with neurodegeneration and worsening condition linked to AD. The ability to measure such changes may facilitate earlier diagnoses for affected individuals and help in monitoring the evolution of their condition. Amongst such statistical tools, disease progression models (DPMs) are quantitative, data-driven methods that specifically attempt to describe the temporal dynamics of biomarkers relevant to AD. Due to the heterogeneous nature of this disease, with patients of similar age experiencing different AD-related changes, a challenge facing longitudinal mixed-effects-based DPMs is the estimation of patient-realigning time-shifts. These time-shifts are indispensable for meaningful biomarker modelling, but may impact fitting time or vary with missing data in jointly estimated models. In this work, we estimate an individual’s progression through Alzheimer’s disease by combining multiple biomarkers into a single value using a probabilistic formulation of principal components analysis. Our results show that this variable, which summarises AD through observable biomarkers, is remarkably similar to jointly estimated time-shifts when we compute our scores for the baseline visit, on cross-sectional data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Reproducing the expected properties of clinical datasets, we confirm that estimated scores are robust to missing data or unavailable biomarkers. In addition to cross-sectional insights, we can model the latent variable as an individual progression score by repeating estimations at follow-up examinations and refining long-term estimates as more data is gathered, which would be ideal in a clinical setting. Finally, we verify that our score can be used as a pseudo-temporal scale instead of age to ignore some patient heterogeneity in cohort data and highlight the general trend in expected biomarker evolution in affected individuals.

•Largest multi-centre harmonisation study of Amyloid PET images.•Systematic evaluation of different harmonisation strategies.•Using NMF improves inter-tracer agreement, AD-NC effect size, correlation with MMSE, and longitudinal consistency. The Centiloid scale was developed to harmonise the quantification of β-amyloid (Aβ) PET images across tracers, scanners, and processing pipelines. However, several groups have reported differences across tracers and scanners even after centiloid conversion. In this study, we aim to evaluate the impact of different pre and post-processing harmonisation steps on the robustness of longitudinal Centiloid data across three large international cohort studies. All Aβ PET data in AIBL (N = 3315), ADNI (N = 3442) and OASIS3 (N = 1398) were quantified using the MRI-based Centiloid standard SPM pipeline and the PET-only pipeline CapAIBL. SUVR were converted into Centiloids using each tracer's respective transform. Global Aβ burden from pre-defined target cortical regions in Centiloid units were quantified for both raw PET scans and PET scans smoothed to a uniform 8 mm full width half maximum (FWHM) effective smoothness. For Florbetapir, we assessed the performance of using both the standard Whole Cerebellum (WCb) and a composite white matter (WM)+WCb reference region. Additionally, our recently proposed quantification based on Non-negative Matrix Factorisation (NMF) was applied to all spatially and SUVR normalised images. Correlation with clinical severity measured by the Mini-Mental State Examination (MMSE) and effect size, as well as tracer agreement in 11C-PiB-18F-Florbetapir pairs and longitudinal consistency were evaluated. The smoothing to a uniform resolution partially reduced longitudinal variability, but did not improve inter-tracer agreement, effect size or correlation with MMSE. Using a Composite reference region for 18F-Florbetapir improved inter-tracer agreement, effect size, correlation with MMSE, and longitudinal consistency. The best results were however obtained when using the NMF method which outperformed all other quantification approaches in all metrics used. FWHM smoothing has limited impact on longitudinal consistency or outliers. A Composite reference region including subcortical WM should be used for computing both cross-sectional and longitudinal Florbetapir Centiloid. NMF improves Centiloid quantification on all metrics examined.

Identifying diffuse axonal injury (DAI) in patients with traumatic brain injury (TBI) presenting with normal appearing radiological MRI presents a significant challenge. Neuroimaging methods such as diffusion MRI and probabilistic tractography, which probe the connectivity of neural networks, show significant promise. We present a machine learning approach to classify TBI participants primarily with mild traumatic brain injury (mTBI) based on altered structural connectivity patterns derived through the network based statistical analysis of structural connectomes generated from TBI and age-matched control groups. In this approach, higher order diffusion models were used to map white matter connections between 116 cortical and subcortical regions. Tracts between these regions were generated using probabilistic tracking and mean fractional anisotropy (FA) measures along these connections were encoded in the connectivity matrices. Network-based statistical analysis of the connectivity matrices was performed to identify the network differences between a representative subset of the two groups. The affected network connections provided the feature vectors for principal component analysis and subsequent classification by random forest. The validity of the approach was tested using data acquired from a total of 179 TBI patients and 146 controls participants. The analysis revealed altered connectivity within a number of intra- and inter-hemispheric white matter pathways associated with DAI, in consensus with existing literature. A mean classification accuracy of 68.16%±1.81% and mean sensitivity of 80.0%±2.36% were achieved in correctly classifying the TBI patients evaluated on the subset of the participants that was not used for the statistical analysis, in a 10-fold cross-validation framework. These results highlight the potential for statistical machine learning approaches applied to structural connectomes to identify patients with diffusive axonal injury. [Display omitted] •Method to identify diffuse axonal injury in mild traumatic brain injury (mTBI) patients from structural connectivity patterns.•Network-based statistics (NBS) is used to find significant network differences in mTBI and controls.•Fractional anisotropy (FA) features of the different structural connections obtained from NBS used as features.•Random forest classifier discriminates between mTBI and controls based on FA features.•Discriminative and significant network differences obtained from feature importance of random forest.