OBJECTIVE:To examine potential genetic relationships between migraine and the two distinct phenotypes posterior circulation ischemic stroke (PCiS) and anterior circulation ischemic stroke (ACiS), we generated migraine polygenic risk scores (PRSs) and compared these between PCiS and ACiS, and separately vs. non-stroke control subjects.METHODS:Acute ischemic stroke cases were classified as PCiS or ACiS based on lesion location on diffusion-weighted MRI. Exclusion criteria were lesions in both vascular territories or uncertain territory; supratentorial PCiS with ipsilateral fetal posterior cerebral artery; and cases with atrial fibrillation. We generated migraine PRS for three migraine phenotypes (any migraine; migraine without aura; migraine with aura) using publicly available GWAS data and compared mean PRSs separately for PCiS and ACiS vs. non-stroke control subjects, and between each stroke phenotype.RESULTS:Our primary analyses included 464 PCiS and 1079 ACiS patients with genetic European ancestry. Compared to non-stroke control subjects (n=15396), PRSs of any migraine were associated with increased risk of PCiS (p=0.01-0.03) and decreased risk of ACiS (p=0.010-0.039). Migraine without aura PRSs were significantly associated with PCiS (p=0.008-0.028), but not with ACiS. When comparing PCiS vs. ACiS directly, migraine PRSs were higher in PCiS vs. ACiS for any migraine (p=0.001-0.010) and migraine without aura (p=0.032-0.048). Migraine with aura PRS did not show a differential association in our analyses.CONCLUSIONS:Our results suggest a stronger genetic overlap between unspecified migraine and migraine without aura with PCiS compared to ACiS. Possible shared mechanisms include dysregulation of cerebral vessel endothelial function.

Background: Magnetic resonance imaging (MRI) serves as a cornerstone in defining stroke phenotype and etiological subtype through examination of ischemic stroke lesion appearance and is therefore an essential tool in linking genetic traits and stroke. Building on baseline MRI examinations from the centralized and structured radiological assessments of ischemic stroke patients in the Stroke Genetics Network, the results of the MRI-Genetics Interface Exploration (MRI-GENIE) study are described in this work. Methods: The MRI-GENIE study included patients with symptoms caused by ischemic stroke (N = 3,301) from 12 international centers. We established and used a structured reporting protocol for all assessments. Two neuroradiologists, using a blinded evaluation protocol, independently reviewed the baseline diffusion-weighted images (DWIs) and magnetic resonance angiography images to determine acute lesion and vascular occlusion characteristics. Results: In this systematic multicenter radiological analysis of clinical MRI from 3,301 acute ischemic stroke patients according to a structured prespecified protocol, we identified that anterior circulation infarcts were most prevalent (67.4%), that infarcts in the middle cerebral artery (MCA) territory were the most common, and that the majority of large artery occlusions 0 to 48 h from ictus were in the MCA territory. Multiple acute lesions in one or several vascular territories were common (11%). Of 2,238 patients with unilateral DWI lesions, 52.6% had left-sided infarct lateralization (P = 0.013 for χ2 test). Conclusions: This large-scale analysis of a multicenter MRI-based cohort of AIS patients presents a unique imaging framework facilitating the relationship between imaging and genetics for advancing the knowledge of genetic traits linked to ischemic stroke.

Objective Posterior circulation ischemic stroke (PCiS) constitutes 20–30% of ischemic stroke cases. Detailed information about differences between PCiS and anterior circulation ischemic stroke (ACiS) remains scarce. Such information might guide clinical decision making and prevention strategies. We studied risk factors and ischemic stroke subtypes in PCiS vs. ACiS and lesion location on magnetic resonance imaging (MRI) in PCiS. Methods Out of 3,301 MRIs from 12 sites in the National Institute of Neurological Disorders and Stroke (NINDS) Stroke Genetics Network (SiGN), we included 2,381 cases with acute DWI lesions. The definition of ACiS or PCiS was based on lesion location. We compared the groups using Chi-squared and logistic regression. Results PCiS occurred in 718 (30%) patients and ACiS in 1663 (70%). Diabetes and male sex were more common in PCiS vs. ACiS (diabetes 27% vs. 23%, p < 0 .05 ; male sex 68% vs. 58%, p < 0.001). Both were independently associated with PCiS (diabetes, OR = 1.29; 95% CI 1.04–1.61; male sex, OR = 1.46; 95% CI 1.21–1.78). ACiS more commonly had large artery atherosclerosis (25% vs. 20%, p < 0.01) and cardioembolic mechanisms (17% vs. 11%, p < 0.001) compared to PCiS. Small artery occlusion was more common in PCiS vs. ACiS (20% vs. 14%, p < 0.001). Small artery occlusion accounted for 47% of solitary brainstem infarctions. Conclusion Ischemic stroke subtypes differ between the two phenotypes. Diabetes and male sex have a stronger association with PCiS than ACiS. Definitive MRI-based PCiS diagnosis aids etiological investigation and contributes additional insights into specific risk factors and mechanisms of injury in PCiS.

Anatomical magnetic resonance imaging (MRI), diffusion MRI and resting state functional MRI (rs-fMRI) have been used for Alzheimer's disease (AD) classification. These scans are typically used to build models for discriminating AD patients from control subjects, but it is not clear if these models can also discriminate AD in diverse clinical populations as found in memory clinics. To study this, we trained MRI-based AD classification models on a single centre data set consisting of AD patients (N = 76) and controls (N = 173), and used these models to assign AD scores to subjective memory complainers (N = 67), mild cognitive impairment (MCI) patients (N = 61), and AD patients (N = 61) from a multi-centre memory clinic data set. The anatomical MRI scans were used to calculate grey matter density, subcortical volumes and cortical thickness, the diffusion MRI scans were used to calculate fractional anisotropy, mean, axial and radial diffusivity, and the rs-fMRI scans were used to calculate functional connectivity between resting state networks and amplitude of low frequency fluctuations. Within the multi-centre memory clinic data set we removed scan site differences prior to applying the models. For all models, on average, the AD patients were assigned the highest AD scores, followed by MCI patients, and later followed by SMC subjects. The anatomical MRI models performed best, and the best performing anatomical MRI measure was grey matter density, separating SMC subjects from MCI patients with an AUC of 0.69, MCI patients from AD patients with an AUC of 0.70, and SMC patients from AD patients with an AUC of 0.86. The diffusion MRI models did not generalise well to the memory clinic data, possibly because of large scan site differences. The functional connectivity model separated SMC subjects and MCI patients relatively good (AUC = 0.66). The multimodal MRI model did not improve upon the anatomical MRI model. In conclusion, we showed that the grey matter density model generalises best to memory clinic subjects. When also considering the fact that grey matter density generally performs well in AD classification studies, this feature is probably the best MRI-based feature for AD diagnosis in clinical practice.

Frontotemporal dementia is a highly heritable and devastating neurodegenerative disease. About 10-20% of all frontotemporal dementia is caused by known pathogenic mutations, but a reliable tool to predict clinical conversion in mutation carriers is lacking. In this retrospective proof-of-concept case-control study, we investigate whether MRI-based and cognition-based classifiers can predict which mutation carriers from genetic frontotemporal dementia families will develop symptoms ('convert') within 4 years. From genetic frontotemporal dementia families, we included 42 presymptomatic frontotemporal dementia mutation carriers. We acquired anatomical, diffusion-weighted imaging, and resting-state functional MRI, as well as neuropsychological data. After 4 years, seven mutation carriers had converted to frontotemporal dementia ('converters'), while 35 had not ('non-converters'). We trained regularized logistic regression models on baseline MRI and cognitive data to predict conversion to frontotemporal dementia within 4 years, and quantified prediction performance using area under the receiver operating characteristic curves. The prediction model based on fractional anisotropy, with highest contribution of the forceps minor, predicted conversion to frontotemporal dementia beyond chance level (0.81 area under the curve, family-wise error corrected P = 0.025 versus chance level). Other MRI-based and cognitive features did not outperform chance level. Even in a small sample, fractional anisotropy predicted conversion in presymptomatic frontotemporal dementia mutation carriers beyond chance level. After validation in larger data sets, conversion prediction in genetic frontotemporal dementia may facilitate early recruitment into clinical trials.

Background: Fundamental advances in stroke care will require pooling imaging phenotype data from multiple centers, to complement the current aggregation of genomic, environmental, and clinical information. Sharing clinically acquired MRI data from multiple hospitals is challenging due to inherent heterogeneity of clinical data, where the same MRI series may be labeled differently depending on vendor and hospital. Furthermore, the de-identification process may remove data describing the MRI series, requiring human review. However, manually annotating the MRI series is not only laborious and slow but prone to human error. In this work, we present a recurrent convolutional neural network (RCNN) for automated classification of the MRI series. Methods: We randomly selected 1000 subjects from the MRI-GENetics Interface Exploration study and partitioned them into 800 training, 100 validation and 100 testing subjects. We categorized the MRI series into 24 groups (see Table). The RCNN used a modified AlexNet to extract features from 2D slices. AlexNet was pretrained on ImageNet photographs. Since clinical MRI are 3D and 4D, a gated recurrent unit neural network was used to aggregate information from multiple 2D slices to make the final prediction. Results: We achieved a classification accuracy (correct/total cases) of 99.8%, 98.5% and 97.5% on the training, validation and testing set, respectively. The averaged F1-score (percent overlap between predicted cases and actual cases) over all categories were 99.8% 98.2% and 94.4% on the training, validation and testing set. Conclusion: We showed that automated annotation of MRI series by repurposing deep-learning techniques used for photographic image recognition tasks is feasible. Such methods can be used to facilitate high throughput curation of MRI data acquired across multiple centers and enable scientifically productive collaboration by researchers and, ultimately enhancing big data stroke research.

Early and accurate mild cognitive impairment (MCI) detection within a heterogeneous, nonclinical population is needed to improve care for persons at risk of developing dementia. Magnetic resonance imaging (MRI)-based classification may aid early diagnosis of MCI, but has only been applied within clinical cohorts. We aimed to determine the generalizability of MRI-based classification probability scores to detect MCI on an individual basis within a general population. To determine classification probability scores, an AD, mild-AD, and moderate-AD detection model were created with anatomical and diffusion MRI measures calculated from a clinical Alzheimer's Disease (AD) cohort and subsequently applied to a population-based cohort with 48 MCI and 617 normal aging subjects. Each model's ability to detect MCI was quantified using area under the receiver operating characteristic curve (AUC) and compared with an MCI detection model trained and applied to the population-based cohort. The AD-model and mild-AD identified MCI from controls better than chance level (AUC = 0.600, p = 0.025; AUC = 0.619, p = 0.008). In contrast, the moderate-AD-model was not able to separate MCI from normal aging (AUC = 0.567, p = 0.147). The MCI-model was able to separate MCI from controls better than chance (p = 0.014) with mean AUC values comparable with the AD-model (AUC = 0.611, p = 1.0). Within our population-based cohort, classification models detected MCI better than chance. Nevertheless, classification performance rates were moderate and may be insufficient to facilitate robust MRI-based MCI detection on an individual basis. Our data indicate that multiparametric MRI-based classification algorithms, that are effective in clinical cohorts, may not straightforwardly translate to applications in a general population.

Background Cerebral amyloid angiopathy (CAA) is a major cause of lobar intracerebral hemorrhage in elderly adults; however, presymptomatic diagnosis of CAA is difficult. Hereditary cerebral hemorrhage with amyloidosis–Dutch type (HCHWA‐D) is a rare autosomal‐dominant disease that leads to pathology similar to sporadic CAA. Presymptomatic HCHWA‐D mutation carriers provide a unique opportunity to study CAA‐related changes before any symptoms have occurred. In this study we investigated early CAA‐related alterations in the white matter. Methods and Results We investigated diffusion magnetic resonance imaging (dMRI) data for 15 symptomatic and 11 presymptomatic HCHWA‐D mutation carriers and 30 noncarrier control participants using 4 different approaches. We looked at (1) the relation between age and global dMRI measures for mutation carriers versus controls, (2) voxel‐wise dMRI, (3) independent component‐clustered dMRI measures, and (4) structural connectomics between presymptomatic or symptomatic carriers and controls. Fractional anisotropy decreased, and mean diffusivity and peak width of the skeletonized mean diffusivity increased significantly over age for mutation carriers compared with controls. In addition, voxel‐wise and independent component‐wise fractional anisotropy, and mean diffusivity, and structural connectomics were significantly different between HCHWA‐D patients and control participants, mainly in the periventricular frontal and occipital regions and in the occipital lobe. We found no significant differences between presymptomatic carriers and control participants. Conclusions The dMRI technique is sensitive in detecting alterations in symptomatic HCHWA‐d carriers but did not show alterations in presymptomatic carriers. This result indicates that dMRI may be less suitable for identifying early white matter changes in CAA.

Neuroimaging MRI data in scientific research is increasingly pooled, but the reliability of such studies may be hampered by the use of different hardware elements. This might introduce bias, for example when cross-sectional studies pool data acquired with different head coils, or when longitudinal clinical studies change head coils halfway. In the present study, we aimed to estimate this possible bias introduced by using different head coils to create awareness and to avoid misinterpretation of results. We acquired, with both an 8 channel and 32 channel head coil, T1-weighted, diffusion tensor imaging and resting state fMRI images at 3T MRI (Philips Achieva) with stable acquisition parameters in a large group of cognitively healthy participants (n = 77). Standard analysis methods, i.e., voxel-based morphometry, tract-based spatial statistics and resting state functional network analyses, were used in a within-subject design to compare 8 and 32 channel head coil data. Signal-to-noise ratios (SNR) for both head coils showed similar ranges, although the 32 channel SNR profile was more homogeneous. Our data demonstrates specific patterns of gray and white matter volume differences between head coils (relative volume change of 6 to 9%), related to altered image contrast and therefore, altered tissue segmentation. White matter connectivity (fractional anisotropy and diffusivity measures) showed hemispherical dependent differences between head coils (relative connectivity change of 4 to 6%), and functional connectivity in resting state networks was higher using the 32 channel head coil in posterior cortical areas (relative change up to 27.5%). This study shows that, even when acquisition protocols are harmonized, the results of standardized analysis models can be severely affected by the use of different head coils. Researchers should be aware of this when combining multiple neuroimaging MRI datasets, to prevent coil-related bias and avoid misinterpretation of their findings.

As age and Parkinson's disease (PD) both play a role in the degeneration of brain white matter, we aimed to investigate a possible interaction effect of age and disease presence on white matter integrity in patients with PD. We studied white matter hyperintensity volume, global fractional anisotropy, mean diffusivity and mean magnetization transfer ratio of normal appearing white matter in 163 patients with PD and 218 age- and gender-matched healthy control subjects. We investigated the relationship between age and these parameters in both groups, and interaction between age and disease presence. Patients with PD had a higher load of white matter hyperintensities with a preferential periventricular and anterior distribution as compared with healthy control subjects. Visuospatial functioning was related to total and postural instability and gait difficulty was related to periventricular white matter hyperintensity volume in patients with PD. The age-related decline of white matter integrity was similar for both groups. Global microstructural integrity of the normal appearing white matter did not differ between patients and healthy control subjects, suggesting that PD-specific changes do not exceed normal age-associated change in white matter without lesions.

Background and purpose Functional outcomes after ischaemic stroke are worse in women, despite adjusting for differences in comorbidities and treatment approaches. White matter microvascular integrity represents one risk factor for poor long-term functional outcomes after ischaemic stroke. The aim of the study is to characterise sex-specific differences in microvascular integrity in individuals with acute ischaemic stroke. Methods A retrospective analysis of subjects with acute ischaemic stroke and brain MRI with diffusion-weighted (DWI) and dynamic-susceptibility contrast-enhanced (DSC) perfusion-weighted imaging obtained within 9 hours of last known well was performed. In the hemisphere contralateral to the acute infarct, normal-appearing white matter (NAWM) microvascular integrity was measured using the K 2 coefficient and apparent diffusion coefficient (ADC) values. Regression analyses for predictors of K 2 coefficient, DWI volume and good outcome (90-day modified Rankin scale (mRS) score <2) were performed. Results 105 men and 79 women met inclusion criteria for analysis. Despite no difference in age, women had increased NAWM K 2 coefficient (1027.4 vs 692.7×10 –6 /s; p=0.006). In women, atrial fibrillation (β=583.6; p=0.04) and increasing NAWM ADC (β=4.4; p=0.02) were associated with increased NAWM K 2 coefficient. In multivariable regression analysis, the K 2 coefficient was an independent predictor of DWI volume in women (β=0.007; p=0.01) but not men. Conclusions In women with acute ischaemic stroke, increased NAWM K 2 coefficient is associated with increased infarct volume and chronic white matter structural integrity. Prospective studies investigating sex-specific differences in white matter microvascular integrity are needed.

BACKGROUND AND PURPOSE:Accurate automated infarct segmentation is needed for acute ischemic stroke studies relying on infarct volumes as an imaging phenotype or biomarker that require large numbers of subjects. This study investigated whether an ensemble of convolutional neural networks trained on multiparametric DWI maps outperforms single networks trained on solo DWI parametric maps. MATERIALS AND METHODS:Convolutional neural networks were trained on combinations of DWI, ADC, and low b-value-weighted images from 116 subjects. The performances of the networks (measured by the Dice score, sensitivity, and precision) were compared with one another and with ensembles of 5 networks. To assess the generalizability of the approach, we applied the best-performing model to an independent Evaluation Cohort of 151 subjects. Agreement between manual and automated segmentations for identifying patients with large lesion volumes was calculated across multiple thresholds (21, 31, 51, and 70 cm3). RESULTS:An ensemble of convolutional neural networks trained on DWI, ADC, and low b-value-weighted images produced the most accurate acute infarct segmentation over individual networks (P < .001). Automated volumes correlated with manually measured volumes (Spearman ρ = 0.91, P < .001) for the independent cohort. For the task of identifying patients with large lesion volumes, agreement between manual outlines and automated outlines was high (Cohen κ, 0.86-0.90; P < .001). CONCLUSIONS:Acute infarcts are more accurately segmented using ensembles of convolutional neural networks trained with multiparametric maps than by using a single model trained with a solo map. Automated lesion segmentation has high agreement with manual techniques for identifying patients with large lesion volumes.

Background Multimodal MRI-based classification may aid early frontotemporal dementia (FTD) diagnosis. Recently, presymptomatic FTD mutation carriers, who have a high risk of developing FTD, were separated beyond chance level from controls using MRI-based classification. However, it is currently unknown how these scores from classification models progress as mutation carriers approach symptom onset. In this longitudinal study, we investigated multimodal MRI-based classification scores between presymptomatic FTD mutation carriers and controls. Furthermore, we contrasted carriers that converted during follow-up (‘converters’) and non-converting carriers (‘non-converters’). Methods We acquired anatomical MRI, diffusion tensor imaging and resting-state functional MRI in 55 presymptomatic FTD mutation carriers and 48 healthy controls at baseline, and at 2, 4, and 6 years of follow-up as available. At each time point, FTD classification scores were calculated using a behavioural variant FTD classification model. Classification scores were tested in a mixed-effects model for mean differences and differences over time. Results Presymptomatic mutation carriers did not have higher classification score increase over time than controls (p=0.15), although carriers had higher FTD classification scores than controls on average (p=0.032). However, converters (n=6) showed a stronger classification score increase over time than non-converters (p<0.001). Conclusions Our findings imply that presymptomatic FTD mutation carriers may remain similar to controls in terms of MRI-based classification scores until they are close to symptom onset. This proof-of-concept study shows the promise of longitudinal MRI data acquisition in combination with machine learning to contribute to early FTD diagnosis.

Background and Purpose— We evaluated deep learning algorithms’ segmentation of acute ischemic lesions on heterogeneous multi-center clinical diffusion-weighted magnetic resonance imaging (MRI) data sets and explored the potential role of this tool for phenotyping acute ischemic stroke. Methods— Ischemic stroke data sets from the MRI-GENIE (MRI-Genetics Interface Exploration) repository consisting of 12 international genetic research centers were retrospectively analyzed using an automated deep learning segmentation algorithm consisting of an ensemble of 3-dimensional convolutional neural networks. Three ensembles were trained using data from the following: (1) 267 patients from an independent single-center cohort, (2) 267 patients from MRI-GENIE, and (3) mixture of (1) and (2). The algorithms’ performances were compared against manual outlines from a separate 383 patient subset from MRI-GENIE. Univariable and multivariable logistic regression with respect to demographics, stroke subtypes, and vascular risk factors were performed to identify phenotypes associated with large acute diffusion-weighted MRI volumes and greater stroke severity in 2770 MRI-GENIE patients. Stroke topography was investigated. Results— The ensemble consisting of a mixture of MRI-GENIE and single-center convolutional neural networks performed best. Subset analysis comparing automated and manual lesion volumes in 383 patients found excellent correlation (ρ=0.92; P <0.0001). Median (interquartile range) diffusion-weighted MRI lesion volumes from 2770 patients were 3.7 cm 3 (0.9–16.6 cm 3 ). Patients with small artery occlusion stroke subtype had smaller lesion volumes ( P <0.0001) and different topography compared with other stroke subtypes. Conclusions— Automated accurate clinical diffusion-weighted MRI lesion segmentation using deep learning algorithms trained with multi-center and diverse data is feasible. Both lesion volume and topography can provide insight into stroke subtypes with sufficient sample size from big heterogeneous multi-center clinical imaging phenotype data sets.

BACKGROUND:Frontotemporal dementia (FTD) and Alzheimer's disease (AD) are associated with divergent differences in grey matter volume, white matter diffusion, and functional connectivity. However, it is unknown at what disease stage these differences emerge. Here, we investigate whether divergent differences in grey matter volume, white matter diffusion, and functional connectivity are already apparent between cognitively healthy carriers of pathogenic FTD mutations, and cognitively healthy carriers at increased AD risk. METHODS:We acquired multimodal magnetic resonance imaging (MRI) brain scans in cognitively healthy subjects with (n=39) and without (n=36) microtubule-associated protein Tau (MAPT) or progranulin (GRN) mutations, and with (n=37) and without (n=38) apolipoprotein E ε4 (APOE4) allele. We evaluated grey matter volume using voxel-based morphometry, white matter diffusion using tract-based spatial statistics (TBSS), and region-to-network functional connectivity using dual regression in the default mode network and salience network. We tested for differences between the respective carriers and controls, as well as for divergence of those differences. For the divergence contrast, we additionally performed region-of-interest TBSS analyses in known areas of white matter diffusion differences between FTD and AD (i.e., uncinate fasciculus, forceps minor, and anterior thalamic radiation). RESULTS:MAPT/GRN carriers did not differ from controls in any modality. APOE4 carriers had lower fractional anisotropy than controls in the callosal splenium and right inferior fronto-occipital fasciculus, but did not show grey matter volume or functional connectivity differences. We found no divergent differences between both carrier-control contrasts in any modality, even in region-of-interest analyses. CONCLUSIONS:Concluding, we could not find differences suggestive of divergent pathways of underlying FTD and AD pathology in asymptomatic risk mutation carriers. Future studies should focus on asymptomatic mutation carriers that are closer to symptom onset to capture the first specific signs that may differentiate between FTD and AD.

In genetic frontotemporal dementia, cross-sectional studies have identified profiles of presymptomatic neuroanatomical loss for C9orf72 repeat expansion, MAPT, and GRN mutations. In this study, we characterize longitudinal gray matter (GM) and white matter (WM) brain changes in presymptomatic frontotemporal dementia. We included healthy carriers of C9orf72 repeat expansion (n = 12), MAPT (n = 15), GRN (n = 33) mutations, and related noncarriers (n = 53), that underwent magnetic resonance imaging at baseline and 2-year follow-up. We analyzed cross-sectional baseline, follow-up, and longitudinal GM and WM changes using voxel-based morphometry and cortical thickness analysis in SPM and tract-based spatial statistics in FSL. Compared with noncarriers, C9orf72 repeat expansion carriers showed lower GM volume in the cerebellum and insula, and WM differences in the anterior thalamic radiation, at baseline and follow-up. MAPT mutation carriers showed emerging GM temporal lobe changes and longitudinal WM degeneration of the uncinate fasciculus. GRN mutation carriers did not show presymptomatic neurodegeneration. This study shows distinct presymptomatic cross-sectional and longitudinal patterns of GM and WM changes across C9orf72 repeat expansion, MAPT, and GRN mutation carriers compared with noncarriers.

BACKGROUND/OBJECTIVE:Overlapping clinical symptoms often complicate differential diagnosis between patients with Alzheimer's disease (AD) and behavioral variant frontotemporal dementia (bvFTD). Magnetic resonance imaging (MRI) reveals disease specific structural and functional differences that aid in differentiating AD from bvFTD patients. However, the benefit of combining structural and functional connectivity measures to-on a subject-basis-differentiate these dementia-types is not yet known.METHODS:Anatomical, diffusion tensor (DTI), and resting-state functional MRI (rs-fMRI) of 30 patients with early stage AD, 23 with bvFTD, and 35 control subjects were collected and used to calculate measures of structural and functional tissue status. All measures were used separately or selectively combined as predictors for training an elastic net regression classifier. Each classifier's ability to accurately distinguish dementia-types was quantified by calculating the area under the receiver operating characteristic curves (AUC).RESULTS:Highest AUC values for AD and bvFTD discrimination were obtained when mean diffusivity, full correlations between rs-fMRI-derived independent components, and fractional anisotropy (FA) were combined (0.811). Similarly, combining gray matter density (GMD), FA, and rs-fMRI correlations resulted in highest AUC of 0.922 for control and bvFTD classifications. This, however, was not observed for control and AD differentiations. Classifications with GMD (0.940) and a GMD and DTI combination (0.941) resulted in similar AUC values (p = 0.41).CONCLUSION:Combining functional and structural connectivity measures improve dementia-type differentiations and may contribute to more accurate and substantiated differential diagnosis of AD and bvFTD patients. Imaging protocols for differential diagnosis may benefit from also including DTI and rs-fMRI.

Background: Classification models based on magnetic resonance imaging (MRI) may aid early diagnosis of frontotemporal dementia (FTD) but have only been applied in established FTD cases. Detection of FTD patients in earlier disease stages, such as presymptomatic mutation carriers, may further advance early diagnosis and treatment. In this study, we aim to distinguish presymptomatic FTD mutation carriers from controls on an individual level using multimodal MRI-based classification. Methods: Anatomical MRI, diffusion tensor imaging (DTI) and resting-state functional MRI data were collected in 55 presymptomatic FTDmutation carriers (8 microtubule-associated protein Tau, 35 progranulin, and 12 chromosome 9 open reading frame 72) and 48 familial controls. We calculated grey and white matter density features from anatomical MRI scans, diffusivity features from DTI, and functional connectivity features from resting-state functional MRI. These features were applied in a recently introduced multimodal behavioural variant FTD (bvFTD) classification model, and were subsequently used to train and test unimodal and multimodal carrier-control models. Classification performance was quantified using area under the receiver operator characteristic curves (AUC). Results: The bvFTD model was not able to separate presymptomatic carriers from controls beyond chance level (AUC = 0.570, p = 0.11). In contrast, one unimodal and several multimodal carrier-control models performed significantly better than chance level. The unimodal model included the radial diffusivity feature and had an AUC of 0.646 (p = 0.021). The best multimodal model combined radial diffusivity and white matter density features (AUC = 0.680, p = 0.005). Conclusions: FTD mutation carriers can be separated from controls with a modest AUC even before symptomonset, using a newly created carrier-control classification model, while this was not possible using a recent bvFTD classification model. A multimodal MRI-based classification score may therefore be a useful biomarker to aid earlier FTD diagnosis. The exclusive selection of white matter features in the best performing model suggests that the earliest FTD-related pathological processes occur in white matter.

Recent research in familial frontotemporal dementia (FTD) suggests a relationship between clinical status and levels of circulating neurofilament light chain (NfL) in blood and cerebrospinal fluid (CSF). NfL levels are low in controls and presymptomatic FTD mutation carriers and rise in symptomatic carriers, and may be influenced by genetic subtype. NfL is an integral part of synapses and a structural constituent of the neuroaxonal cytoskeleton and circulating NfL has been linked to axonal damage. Neuroaxonal damage may be visualized through diffusion tensor imaging (DTI). Therefore, examining the relation between NfL levels and DTI-derived measures in all stages of familial FTD may clarify disease mechanisms and aid our knowledge on biomarkers for FTD clinical disease onset. Sixty-two subjects from FTD families (GRN and C9orf72) with an available CSF and diffusion tensor imaging on 3T were included. NfL levels were measured by ELISA. White matter integrity was measured in four parameters (fractional anisotropy and mean, axial, and radial diffusivity) using FSL's tract-based spatial statistics. We performed whole brain correlation analyses with permutation-based testing in GRN (n=23) and C9orf72 (n=14) carrier groups. Twenty white matter tracts of the Johns-Hopkins-University WM atlas were extracted for tract-specific correlation analysis. All statistical analyses were corrected for age, gender, days between CSF and DTI, clinical stage, and multiple comparisons. In GRN mutation carriers (presymptomatic and symptomatic carriers), we found a widespread positive relationship between NfL levels and mean, axial, and especially radial diffusivity in fronto-posterior tracts and a negative relationship with fractional anisotropy in frontal regions (pFWE < 0.05) (Figure 1). Such relationships were not found in C9orf72 carriers. Tract-specific correlations revealed weak to moderate correlation coefficients in GRN carriers, while no significant tract-specific correlations were found in C9orf72 carriers (Table 1).