Background: Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies... Show moreBackground: Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group. Methods: We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality. Results: We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for D-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance. Conclusion: These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable. Show less
MR fingerprinting (MRF) is a promising method for quantitative characterization of tissues. Often, voxel-wise measurements are made, assuming a single tissue-type per voxel. Alternatively, the... Show moreMR fingerprinting (MRF) is a promising method for quantitative characterization of tissues. Often, voxel-wise measurements are made, assuming a single tissue-type per voxel. Alternatively, the Sparsity Promoting Iterative Joint Non-negative least squares Multi-Component MRF method (SPIJN-MRF) facilitates tissue parameter estima-tion for identified components as well as partial volume segmentations. The aim of this paper was to evaluate the accuracy and repeatability of the SPIJN-MRF parameter estimations and partial volume segmentations. This was done (1) through numerical simulations based on the BrainWeb phantoms and (2) using in vivo acquired MRF data from 5 subjects that were scanned on the same week-day for 8 consecutive weeks. The partial volume segmen-tations of the SPIJN-MRF method were compared to those obtained by two conventional methods: SPM12 and FSL. SPIJN-MRF showed higher accuracy in simulations in comparison to FSL-and SPM12-based segmentations: Fuzzy Tanimoto Coefficients (FTC) comparing these segmentations and Brainweb references were higher than 0.95 for SPIJN-MRF in all the tissues and between 0.6 and 0.7 for SPM12 and FSL in white and gray matter and between 0.5 and 0.6 in CSF. For the in vivo MRF data, the estimated relaxation times were in line with literature and minimal variation was observed. Furthermore, the coefficient of variation (CoV) for estimated tissue volumes with SPIJN-MRF were 10.5% for the myelin water, 6.0% for the white matter, 5.6% for the gray matter, 4.6% for the CSF and 1.1% for the total brain volume. CoVs for CSF and total brain volume measured on the scanned data for SPIJN-MRF were in line with those obtained with SPM12 and FSL. The CoVs for white and gray mat-ter volumes were distinctively higher for SPIJN-MRF than those measured with SPM12 and FSL. In conclusion, the use of SPIJN-MRF provides accurate and precise tissue relaxation parameter estimations taking into account intrinsic partial volume effects. It facilitates obtaining tissue fraction maps of prevalent tissues including myelin water which can be relevant for evaluating diseases affecting the white matter. Show less
Results of neuroimaging datasets aggregated from multiple sites may be biased by site-specific profiles in participants' demographic and clinical characteristics, as well as MRI acquisition... Show moreResults of neuroimaging datasets aggregated from multiple sites may be biased by site-specific profiles in participants' demographic and clinical characteristics, as well as MRI acquisition protocols and scanning platforms. We compared the impact of four different harmonization methods on results obtained from analyses of cortical thickness data: (1) linear mixed-effects model (LME) that models site-specific random intercepts (LME INT), (2) LME that models both site-specific random intercepts and age-related random slopes (LME INT+ SLP), (3) ComBat, and (4) ComBat with a generalized additive model (ComBat-GAM). Our test case for comparing harmonization methods was cortical thickness data aggregated from 29 sites, which included 1,340 cases with posttraumatic stress disorder (PTSD) (6.2-81.8 years old) and 2,057 trauma-exposed controls without PTSD (6.3-85.2 years old). We found that, compared to the other data harmonization methods, data processed with ComBat-GAM was more sensitive to the detection of significant case-control differences (X-2 (3) = 63.704, p < 0.001) as well as casecontrol differences in age-related cortical thinning (X-2 (3) = 12.082, p = 0.007). Both ComBat and ComBat-GAM outperformed LME methods in detecting sex differences (X-2 (3) = 9.114, p = 0.028) in regional cortical thickness. ComBat-GAM also led to stronger estimates of age-related declines in cortical thickness (corrected p-values < 0.001), stronger estimates of case-related cortical thickness reduction (corrected p-values < 0.001), weaker estimates of age-related declines in cortical thickness in cases than controls (corrected p-values < 0.001), stronger estimates of cortical thickness reduction in females than males (corrected p-values < 0.001), and stronger estimates of cortical thickness reduction in females relative to males in cases than controls (corrected p-values < 0.001). Our results support the use of ComBat-GAM to minimize confounds and increase statistical power when harmonizing data with non-linear effects, and the use of either ComBat or ComBat-GAM for harmonizing data with linear effects. Show less
Hesse, L.S.; Aliasi, M.; Moser, F.; Haak, M.C.; Xie, W.D.; Jenkinson, M.; ... ; INTERGROWTH-21st Consortium 2022
The quantification of subcortical volume development from 3D fetal ultrasound can provide important diagnostic information during pregnancy monitoring. However, manual segmentation of subcortical... Show moreThe quantification of subcortical volume development from 3D fetal ultrasound can provide important diagnostic information during pregnancy monitoring. However, manual segmentation of subcortical structures in ultrasound volumes is time-consuming and challenging due to low soft tissue contrast, speckle and shadowing artifacts. For this reason, we developed a convolutional neural network (CNN) for the automated segmentation of the choroid plexus (CP), lateral posterior ventricle horns (LPVH), cavum septum pellucidum et vergae (CSPV), and cerebellum (CB) from 3D ultrasound. As ground-truth labels are scarce and expensive to obtain, we applied few-shot learning, in which only a small number of manual annotations (n = 9) are used to train a CNN. We compared training a CNN with only a few individually annotated volumes versus many weakly labelled volumes obtained from atlas-based segmentations. This showed that segmentation performance close to intra-observer variability can be obtained with only a handful of manual annotations. Finally, the trained models were applied to a large number (n = 278) of ultrasound image volumes of a diverse, healthy population, obtaining novel US-specific growth curves of the respective structures during the second trimester of gestation. Show less
The cytoarchitectonically tripartite organization of the inferior parietal cortex (IPC) into the rostral, the middle and the caudal clusters has been generally ignored when associating different... Show moreThe cytoarchitectonically tripartite organization of the inferior parietal cortex (IPC) into the rostral, the middle and the caudal clusters has been generally ignored when associating different functions to this part of the cortex, resulting in inconsistencies about how IPC is understood. In this study, we investigated the patterns of functional connectivity of the caudal IPC in a task requiring cognitive control, using multiband EPI. This part of the cortex demonstrated functional connectivity patterns dissimilar to a cognitive control area and at the same time the caudal IPC showed negative functional associations with both task-related brain areas and the precuneus cortex, which is active during resting state. We found evidence suggesting that the traditional categorization of different brain areas into either task-related or resting state-related networks cannot accommodate the functions of the caudal IPC. This underlies the hypothesis about a new brain functional category as a modulating cortical area proposing that its involvement in task performance, in a modulating manner, is marked by deactivation in the patterns of functional associations with parts of the brain that are recognized to be involved in doing a task, proportionate to task difficulty; however, its patterns of functional connectivity in some other respects do not correspond to the resting state-related parts of the cortex. Show less
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... Show moreArterial 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. Show less
Nagtegaal, M.; Koken, P.; Amthor, T.; Bresser, J. de; Madler, B.; Vos, F.; Doneva, M. 2020
Demyelination is the key pathological process in multiple sclerosis (MS). The extent of demyelination can be quantified with magnetic resonance imaging by assessing the myelin water fraction (MWF).... Show moreDemyelination is the key pathological process in multiple sclerosis (MS). The extent of demyelination can be quantified with magnetic resonance imaging by assessing the myelin water fraction (MWF). However, long computation times and high noise sensitivity hinder the translation of MWF imaging to clinical practice. In this work, we introduce a more efficient and noise robust method to determine the MWF using a joint sparsity constraint and a pre-computed B-1(+)-T-2 dictionary.A single component analysis with this dictionary is used in an initial step to obtain a B-1(+) map. The T-2 distribution is then determined from a reduced dictionary corresponding to the estimated B-1(+) map using a combination of a non-negativity and a joint sparsity constraint.The non-negativity constraint ensures that a feasible solution with non-negative contribution of each T-2 component is obtained. The joint sparsity constraint restricts the T-2 distribution to a small set of T-2 relaxation times shared between all voxels and reduces the noise sensitivity.The applied Sparsity Promoting Iterative Joint NNLS (SPIJN) algorithm can be implemented efficiently, reducing the computation time by a factor of 50 compared to the commonly used regularized non-negative least squares algorithm. The proposed method was validated in simulations and in 8 healthy subjects with a 3D multiecho gradient- and spin echo scan at 3 T. In simulations, the absolute error in the MWF decreased from 0.031 to 0.013 compared to the regularized NNLS algorithm for SNR = 250. The in vivo results were consistent with values reported in literature and improved MWF-quantification was obtained especially in the frontal white matter. The maximum standard deviation in mean MWF in different regions of interest between subjects was smaller for the proposed method (0.0193) compared to the regularized NNLS algorithm (0.0266). In conclusion, the proposed method for MWF estimation is less computationally expensive and less susceptible to noise compared to state of the art methods. These improvements might be an important step towards clinical translation of MWF measurements. Show less
Nagtegaal, M.; Koken, P.; Amthor, T.; Bresser, J. de; Madler, B.; Vos, F.; Doneva, M. 2020
During adolescence, self-concept develops profoundly, accompanied by major changes in hormone levels. Self-evaluations become more complex, and peers and their opinions increasingly salient.... Show moreDuring adolescence, self-concept develops profoundly, accompanied by major changes in hormone levels. Self-evaluations become more complex, and peers and their opinions increasingly salient. Neuroimaging studies have investigated self- and other-related processing in adolescents, however, the influence of similarity of peers on these processes is still unclear, as well as functional connectivity underlying such processes. We investigated the effect of peer similarity on neural activity and connectivity underlying self- and other-referential processing, by distinguishing between a similar and dissimilar peer when making other-evaluations. Moreover, we explored the association between testosterone and brain activity during self-evaluations. Sixty-six young adolescents underwent functional MRI while performing a trait judgement task in which they indicated whether an adjective described themselves, a similar or a dissimilar classmate. The ventral medial prefrontal cortex (MPFC) showed increased engagement in self-referential processing, and the posterior cingulate cortex and right temporal parietal junction during other-evaluations. However, activity did not differ between the similar and dissimilar other conditions. Functional connectivity of the ventral MPFC included the striatum when evaluating the similar peer and frontoparietal regions when evaluating the dissimilar peer. Furthermore, inter-individual differences in testosterone levels were positively associated with dorsal MPFC activity in males. This study provides insight into the influence of peer similarity on activity and connectivity underlying other-referential processing in young adolescents, and suggests that testosterone affects neural correlates of self-referential processing. Show less
Klaassens, B.L.; Gerven, J.M.A. van; Klaassen, E.S.; Grond, J. van der; Rombouts, S.A.R.B. 2019
Disruption of cholinergic and serotonergic neurotransmitter systems is associated with cognitive, emotional and behavioural symptoms of Alzheimer's disease (AD). To investigate the responsiveness... Show moreDisruption of cholinergic and serotonergic neurotransmitter systems is associated with cognitive, emotional and behavioural symptoms of Alzheimer's disease (AD). To investigate the responsiveness of these systems in AD we measured the effects of a single-dose of the selective serotonin reuptake inhibitor citalopram and acetylcholinesterase inhibitor galantamine in 12 patients with AD and 12 age-matched controls on functional brain connectivity with resting state functional magnetic resonance imaging. In this randomized, double blind, placebo-controlled crossover study, functional magnetic resonance images were repeatedly obtained before and after dosing, resulting in a dataset of 432 scans. Connectivity maps of ten functional networks were extracted using a dual regression method and drug vs. placebo effects were compared between groups with a multivariate analysis with signals coming from cerebrospinal fluid and white matter as covariates at the subject level, and baseline and heart rate measurements as confound regressors in the higher-level analysis (at p < 0.05, corrected). A galantamine induced difference between groups was observed for the cerebellar network. Connectivity within the cerebellar network and between this network and the thalamus decreased after galantamine vs. placebo in AD patients, but not in controls. For citalopram, voxelwise network connectivity did not show significant group x treatment interaction effects. However, we found default mode network connectivity with the precuneus and posterior cingulate cortex to be increased in AD patients, which could not be detected within the control group. Further, in contrast to the AD patients, control subjects showed a consistent reduction in mean connectivity with all networks after administration of citalopram. Since AD has previously been characterized by reduced connectivity between the default mode network and the precuneus and posterior cingulate cortex, the effects of citalopram on the default mode network suggest a restoring potential of selective serotonin reuptake inhibitors in AD. The results of this study also confirm a change in cerebellar connections in AD, which is possibly related to cholinergic decline. Show less
Klaassens, B.L.; Gerven, J.M.A. van; Klaassen, E.S.; Grond, J. van der; Rombouts, S.A.R.B. 2019
Performing quality control to detect image artifacts and data-processing errors is crucial in structural magnetic resonance imaging, especially in developmental studies. Currently, many studies... Show morePerforming quality control to detect image artifacts and data-processing errors is crucial in structural magnetic resonance imaging, especially in developmental studies. Currently, many studies rely on visual inspection by trained raters for quality control. The subjectivity of these manual procedures lessens comparability between studies, and with growing study sizes quality control is increasingly time consuming. In addition, both inter-rater as well as intra-rater variability of manual quality control is high and may lead to inclusion of poor quality scans and exclusion of scans of usable quality. In the current study we present the Qoala-T tool, which is an easy and free to use supervised-learning model to reduce rater bias and misclassification in manual quality control procedures using FreeSurfer-processed scans. First, we manually rated quality of N = 784 FreeSurfer-processed T1-weighted scans acquired in three different waves in a longitudinal study. Different supervised-learning models were then compared to predict manual quality ratings using FreeSurfer segmented output data. Results show that the Qoala-T tool using random forests is able to predict scan quality with both high sensitivity and specificity (mean area under the curve (AUC) = 0.98). In addition, the Qoala-T tool was also able to adequately predict the quality of two novel unseen datasets (total N = 872). Finally, analyses of age effects showed that younger participants were more likely to have lower scan quality, underlining that scan quality might confound findings attributed to age effects. These outcomes indicate that this procedure could further help to reduce variability related to manual quality control, thereby benefiting the comparability of data quality between studies. Show less