Arterial spin labeling (ASL) has undergone significant development since its inception, with a focus on improving standardization and reproducibility of its acquisition and quantification. In a ...community-wide effort towards robust and reproducible clinical ASL image processing, we developed the software package ExploreASL, allowing standardized analyses across centers and scanners.
The procedures used in ExploreASL capitalize on published image processing advancements and address the challenges of multi-center datasets with scanner-specific processing and artifact reduction to limit patient exclusion. ExploreASL is self-contained, written in MATLAB and based on Statistical Parameter Mapping (SPM) and runs on multiple operating systems. To facilitate collaboration and data-exchange, the toolbox follows several standards and recommendations for data structure, provenance, and best analysis practice.
ExploreASL was iteratively refined and tested in the analysis of >10,000 ASL scans using different pulse-sequences in a variety of clinical populations, resulting in four processing modules: Import, Structural, ASL, and Population that perform tasks, respectively, for data curation, structural and ASL image processing and quality control, and finally preparing the results for statistical analyses on both single-subject and group level. We illustrate ExploreASL processing results from three cohorts: perinatally HIV-infected children, healthy adults, and elderly at risk for neurodegenerative disease. We show the reproducibility for each cohort when processed at different centers with different operating systems and MATLAB versions, and its effects on the quantification of gray matter cerebral blood flow.
ExploreASL facilitates the standardization of image processing and quality control, allowing the pooling of cohorts which may increase statistical power and discover between-group perfusion differences. Ultimately, this workflow may advance ASL for wider adoption in clinical studies, trials, and practice.
OBJECTIVE:We tested whether brain gray matter (GM) imaging measures can differentiate between multiple sclerosis (MS) and neuromyelitis optica (NMO) using random-forest classification.
METHODS:Ninety ...participants (25 patients with MS, 30 patients with NMO, and 35 healthy controls HCs) were studied in Tehran, Iran, and 54 (24 patients with MS, 20 patients with NMO, and 10 HCs) in Padua, Italy. Participants underwent brain T1 and T2/fluid-attenuated inversion recovery MRI. Volume, thickness, and surface of 50 cortical GM regions and volumes of the deep GM nuclei were calculated and used to construct 3 random-forest models to classify patients as either NMO or MS, and separate each patient group from HCs. Clinical diagnosis was the gold standard against which the accuracy was calculated.
RESULTS:The classifier distinguished patients with MS, who showed greater atrophy especially in deep GM, from those with NMO with an average accuracy of 74% (sensitivity/specificity77/72; p < 0.01). When we used thalamic volume (the most discriminating GM measure) together with the white matter lesion volume, the accuracy of the classification of MS vs NMO was 80%. The classifications of MS vs HCs and NMO vs HCs achieved higher accuracies (92% and 88%).
CONCLUSIONS:GM imaging biomarkers, automatically obtained from clinical scans, can be used to distinguish NMO from MS, even in a 2-center setting, and may facilitate the differential diagnosis in clinical practice.
CLASSIFICATION OF EVIDENCE:This study provides Class II evidence that GM imaging biomarkers can distinguish patients with NMO from those with MS.
With the shift of research focus towards the pre-dementia stage of Alzheimer's disease (AD), there is an urgent need for reliable, non-invasive biomarkers to predict amyloid pathology. The aim of ...this study was to assess whether easily obtainable measures from structural MRI, combined with demographic data, cognitive data and apolipoprotein E (APOE) ε4 genotype, can be used to predict amyloid pathology using machine-learning classification.
We examined 810 subjects with structural MRI data and amyloid markers from the European Medical Information Framework for Alzheimer's Disease Multimodal Biomarker Discovery study, including subjects with normal cognition (CN, n = 337, age 66.5 ± 7.2, 50% female, 27% amyloid positive), mild cognitive impairment (MCI, n = 375, age 69.1 ± 7.5, 53% female, 63% amyloid positive) and AD dementia (n = 98, age 67.0 ± 7.7, 48% female, 97% amyloid positive). Structural MRI scans were visually assessed and Freesurfer was used to obtain subcortical volumes, cortical thickness and surface area measures. We first assessed univariate associations between MRI measures and amyloid pathology using mixed models. Next, we developed and tested an automated classifier using demographic, cognitive, MRI and APOE ε4 information to predict amyloid pathology. A support vector machine (SVM) with nested 10-fold cross-validation was applied to identify a set of markers best discriminating between amyloid positive and amyloid negative subjects.
In univariate associations, amyloid pathology was associated with lower subcortical volumes and thinner cortex in AD-signature regions in CN and MCI. The multi-variable SVM classifier provided an area under the curve (AUC) of 0.81 ± 0.07 in MCI and an AUC of 0.74 ± 0.08 in CN. In CN, selected features for the classifier included APOE ε4, age, memory scores and several MRI measures such as hippocampus, amygdala and accumbens volumes and cortical thickness in temporal and parahippocampal regions. In MCI, the classifier including demographic and APOE ε4 information did not improve after additionally adding imaging measures.
Amyloid pathology is associated with changes in structural MRI measures in CN and MCI. An automated classifier based on clinical, imaging and APOE ε4 data can identify the presence of amyloid pathology with a moderate level of accuracy. These results could be used in clinical trials to pre-screen subjects for anti-amyloid therapies.
•RFE-SVMs predict future outcome of CIS patients with conservative accuracy estimates between 64.9% and 88.1%.•Recursive feature selection improves classification performance compared to using all ...information.•Relevant features include regional WM lesion load and GM density, as well as the type of CIS onset.•Cross-validation introduces positive bias on accuracy estimate.
Machine learning classification is an attractive approach to automatically differentiate patients from healthy subjects, and to predict future disease outcomes. A clinically isolated syndrome (CIS) is often the first presentation of multiple sclerosis (MS), but it is difficult at onset to predict who will have a second relapse and hence convert to clinically definite MS. In this study, we thus aimed to distinguish CIS converters from non-converters at onset of a CIS, using recursive feature elimination and weight averaging with support vector machines. We also sought to assess the influence of cohort size and cross-validation methods on the accuracy estimate of the classification.
We retrospectively collected 400 patients with CIS from six European MAGNIMS MS centres. Patients underwent brain MRI at onset of a CIS according to local standard-of-care protocols. The diagnosis of clinically definite MS at one-year follow-up was the standard against which the accuracy of the model was tested. For each patient, we derived MRI-based features, such as grey matter probability, white matter lesion load, cortical thickness, and volume of specific cortical and white matter regions. Features with little contribution to the classification model were removed iteratively through an interleaved sample bootstrapping and feature averaging approach. Classification of CIS outcome at one-year follow-up was performed with 2-fold, 5-fold, 10-fold and leave-one-out cross-validation for each centre cohort independently and in all patients together.
The estimated classification accuracy across centres ranged from 64.9% to 88.1% using 2-fold cross-validation and from 73% to 92.9% using leave-one-out cross-validation. The classification accuracy estimate was higher in single-centre, smaller data sets than in combinations of data sets, being the lowest when all patients were merged together.
Regional MRI features such as WM lesions, grey matter probability in the thalamus and the precuneus or cortical thickness in the cuneus and inferior temporal gyrus predicted the occurrence of a second relapse in patients at onset of a CIS using support vector machines. The increased accuracy estimate of the classification achieved with smaller and single-centre samples may indicate a model bias (overfitting) when data points were limited, but also more homogeneous. We provide an overview of classifier performance from a range of cross-validation schemes to give insight into the variability across schemes. The proposed recursive feature elimination approach with weight averaging can be used both in single- and multi-centre data sets in order to bridge the gap between group-level comparisons and making predictions for individual patients.
Understanding the sequence of biological and clinical events along the course of Alzheimer's disease provides insights into dementia pathophysiology and can help participant selection in clinical ...trials. Our objective is to train two data-driven computational models for sequencing these events, the Event Based Model (EBM) and discriminative-EBM (DEBM), on the basis of well-characterized research data, then validate the trained models on subjects from clinical cohorts characterized by less-structured data-acquisition protocols.
Seven independent data cohorts were considered totalling 2389 cognitively normal (CN), 1424 mild cognitive impairment (MCI) and 743 Alzheimer's disease (AD) patients. The Alzheimer's Disease Neuroimaging Initiative (ADNI) data set was used as training set for the constriction of disease models while a collection of multi-centric data cohorts was used as test set for validation. Cross-sectional information related to clinical, cognitive, imaging and cerebrospinal fluid (CSF) biomarkers was used.
Event sequences obtained with EBM and DEBM showed differences in the ordering of single biomarkers but according to both the first biomarkers to become abnormal were those related to CSF, followed by cognitive scores, while structural imaging showed significant volumetric decreases at later stages of the disease progression. Staging of test set subjects based on sequences obtained with both models showed good linear correlation with the Mini Mental State Examination score (R2EBM = 0.866; R2DEBM = 0.906). In discriminant analyses, significant differences (p-value ≤ 0.05) between the staging of subjects from training and test sets were observed in both models. No significant difference between the staging of subjects from the training and test was observed (p-value > 0.05) when considering a subset composed by 562 subjects for which all biomarker families (cognitive, imaging and CSF) are available.
Event sequence obtained with DEBM recapitulates the heuristic models in a data-driven fashion and is clinically plausible. We demonstrated inter-cohort transferability of two disease progression models and their robustness in detecting AD phases. This is an important step towards the adoption of data-driven statistical models into clinical domain.
•Data-driven event sequences describe evolution of relevant biomarkers in AD.•Agreement between event sequences and heuristic AD progression models•Accuracy in classifying subjects from clinical cohorts up to 91%•Staging of subjects and MMSE scores of individuals show linear relation.•Transferability of AD progression models based on research data to clinical cohorts
As disease progression remains poorly understood in multiple sclerosis (MS), we aim to investigate the sequence in which different disease milestones occur using a novel data-driven approach.
We ...analysed a cohort of 295 relapse-onset MS patients and 96 healthy controls, and considered 28 features, capturing information on T2-lesion load, regional brain and spinal cord volumes, resting-state functional centrality (“hubness”), microstructural tissue integrity of major white matter (WM) tracts and performance on multiple cognitive tests. We used a discriminative event-based model to estimate the sequence of biomarker abnormality in MS progression in general, as well as specific models for worsening physical disability and cognitive impairment.
We demonstrated that grey matter (GM) atrophy of the cerebellum, thalamus, and changes in corticospinal tracts are early events in MS pathology, whereas other WM tracts as well as the cognitive domains of working memory, attention, and executive function are consistently late events. The models for disability and cognition show early functional changes of the default-mode network and earlier changes in spinal cord volume compared to the general MS population. Overall, GM atrophy seems crucial due to its early involvement in the disease course, whereas WM tract integrity appears to be affected relatively late despite the early onset of WM lesions.
Data-driven modelling revealed the relative occurrence of both imaging and non-imaging events as MS progresses, providing insights into disease propagation mechanisms, and allowing fine-grained staging of patients for monitoring purposes
Epilepsy surgery results in seizure freedom in the majority of drug-resistant patients. To improve surgery outcome we studied whether MEG metrics combined with machine learning can improve ...localization of the epileptogenic zone, thereby enhancing the chance of seizure freedom.
Presurgical interictal MEG recordings of 94 patients (64 seizure-free >1y post-surgery) were analyzed to extract four metrics in source space: delta power, low-to-high-frequency power ratio, functional connectivity (phase lag index), and minimum spanning tree betweenness centrality. At the group level, we estimated the overlap of the resection area with the five highest values for each metric and determined whether this overlap differed between surgery outcomes. At the individual level, those metrics were used in machine learning classifiers (linear support vector machine (SVM) and random forest) to distinguish between resection and non-resection areas and between surgery outcome groups.
The highest values, for all metrics, overlapped with the resection area in more than half of the patients, but the overlap did not differ between surgery outcome groups. The classifiers distinguished the resection areas from non-resection areas with 59.94% accuracy (95% confidence interval: 59.67-60.22%) for SVM and 60.34% (59.98-60.71%) for random forest, but could not differentiate seizure-free from not seizure-free patients 43.77% accuracy (42.08-45.45%) for SVM and 49.03% (47.25-50.82%) for random forest.
All four metrics localized the resection area but did not distinguish between surgery outcome groups, demonstrating that metrics derived from interictal MEG correspond to expert consensus based on several presurgical evaluation modalities, but do not yet localize the epileptogenic zone. Metrics should be improved such that they correspond to the resection area in seizure-free patients but not in patients with persistent seizures. It is important to test such localization strategies at an individual level, for example by using machine learning or individualized models, since surgery is individually tailored.
•Data from the European Prevention of Alzheimer’s Dementia (EPAD) cohort are analyzed.•CSF p-tau relates to gray matter connectivity alterations in preclinical AD.•Amyloid and tau show differential ...effects on network connectivity.
Gray matter networks are altered with amyloid accumulation in the earliest stage of AD, and are associated with decline throughout the AD spectrum. It remains unclear to what extent gray matter network abnormalities are associated with hyperphosphorylated-tau (p-tau). We studied the relationship of cerebrospinal fluid (CSF) p-tau181 with gray matter networks in non-demented participants from the European Prevention of Alzheimer’s Dementia (EPAD) cohort, and studied dependencies on amyloid and cognitive status. Gray matter networks were extracted from baseline structural 3D T1w MRI. P-tau181 and abeta were measured with the Roche cobas Elecsys System. We studied the associations of CSF biomarkers levels with several network’s graph properties. We further studied whether the relationships of p-tau 181 and network measures were dependent on amyloid status and cognitive stage (CDR). We repeated these analyses for network properties at a regional level, where we averaged local network values across cubes within each of 116 areas as defined by the automated anatomical labeling (AAL) atlas. Amyloid positivity was associated with higher network size and betweenness centrality, and lower gamma, clustering and small-world coefficients. Higher CSF p-tau 181 levels were related to lower betweenness centrality, path length and lambda coefficients (all p < 0.01). Three-way interactions between p-tau181, amyloid status and CDR were found for path length, lambda and clustering (all p < 0.05): Cognitively unimpaired amyloid-negative participants showed lower path length and lambda values with higher CSF p-tau181 levels. Amyloid-positive participants with impaired cognition demonstrated lower clustering coefficients in association to higher CSF p-tau181 levels.
Our results suggest that alterations in gray matter network clustering coefficient is an early and specific event in AD.
•We show an overview of the MRI image processing and QC pipeline for the open-access EPAD study.•Data sanity is evaluated by comparison with non-imaging dementia indicators.•This work is a ...methodological reference for investigators accessing public EPAD data.
The European Prevention of Alzheimer Dementia (EPAD) is a multi-center study that aims to characterize the preclinical and prodromal stages of Alzheimer’s Disease. The EPAD imaging dataset includes core (3D T1w, 3D FLAIR) and advanced (ASL, diffusion MRI, and resting-state fMRI) MRI sequences.
Here, we give an overview of the semi-automatic multimodal and multisite pipeline that we developed to curate, preprocess, quality control (QC), and compute image-derived phenotypes (IDPs) from the EPAD MRI dataset. This pipeline harmonizes DICOM data structure across sites and performs standardized MRI preprocessing steps. A semi-automated MRI QC procedure was implemented to visualize and flag MRI images next to site-specific distributions of QC features — i.e. metrics that represent image quality. The value of each of these QC features was evaluated through comparison with visual assessment and step-wise parameter selection based on logistic regression. IDPs were computed from 5 different MRI modalities and their sanity and potential clinical relevance were ascertained by assessing their relationship with biological markers of aging and dementia.
The EPAD v1500.0 data release encompassed core structural scans from 1356 participants 842 fMRI, 831 dMRI, and 858 ASL scans. From 1356 3D T1w images, we identified 17 images with poor quality and 61 with moderate quality. Five QC features — Signal to Noise Ratio (SNR), Contrast to Noise Ratio (CNR), Coefficient of Joint Variation (CJV), Foreground-Background energy Ratio (FBER), and Image Quality Rate (IQR) — were selected as the most informative on image quality by comparison with visual assessment. The multimodal IDPs showed greater impairment in associations with age and dementia biomarkers, demonstrating the potential of the dataset for future clinical analyses.
Introduction
Amyloid beta (Aβ) accumulation is the first pathological hallmark of Alzheimer's disease (AD), and it is associated with altered white matter (WM) microstructure. We aimed to investigate ...this relationship at a regional level in a cognitively unimpaired cohort.
Methods
We included 179 individuals from the European Medical Information Framework for AD (EMIF‐AD) preclinAD study, who underwent diffusion magnetic resonance (MR) to determine tract‐level fractional anisotropy (FA); mean, radial, and axial diffusivity (MD/RD/AxD); and dynamic 18Fflutemetamol) positron emission tomography (PET) imaging to assess amyloid burden.
Results
Regression analyses showed a non‐linear relationship between regional amyloid burden and WM microstructure. Low amyloid burden was associated with increased FA and decreased MD/RD/AxD, followed by decreased FA and increased MD/RD/AxD upon higher amyloid burden. The strongest association was observed between amyloid burden in the precuneus and body of the corpus callosum (CC) FA and diffusivity (MD/RD) measures. In addition, amyloid burden in the anterior cingulate cortex strongly related to AxD and RD measures in the genu CC.
Discussion
Early amyloid deposition is associated with changes in WM microstructure. The non‐linear relationship might reflect multiple stages of axonal damage.