Harmonization of multi-site diffusion tensor imaging data

Brain Network Functional Connectivity in Children With a Concussion

BACKGROUND AND OBJECTIVES

Pediatric concussion can disrupt functional brain network connectivity, but prospective longitudinal research is needed to clarify recovery and identify moderators of change. This study investigated network functional connectivity (FC) up to 6 months after pediatric concussion.

METHODS

This prospective longitudinal concurrent cohort observational study consecutively recruited children (aged 8 to 17 years) at 5 Canadian pediatric hospital emergency departments within 48 hours of sustaining a concussion or mild orthopaedic injury (OI). Children completed 3T MRI scanning postacutely (2 to 33 days) and at either 3 or 6 months after injury (randomly assigned at the postacute visit). Reliable change between retrospective preinjury (based on parent report) and 1-month postinjury symptom ratings based on parent and child report was used to classify concussion with or without persisting symptoms. Within-network and between-network FC was computed for 8 brain networks from resting-state fMRI scans and analyzed using linear mixed-effects models, with multiple comparison correction.

RESULTS

Groups (385 with concussion/198 with OI; 59% male; 69% White; age 12.42 ± 2.29 years) did not differ in within-network FC. Relative to OI, connectivity between the visual and ventral attention networks was lower after concussion, d (95% CI) = -0.46 (-0.79 to -0.14), across time. Connectivity between the visual and default mode networks was lower at 6 months after concussion, -0.60 (-0.92 to -0.27). At 3 months after concussion, connectivity between the frontoparietal and ventral attention networks was lower in younger children, -0.98 (-1.58 to -0.37), but higher in older children, 0.81 (0.20 to 1.42). For symptom groups based on parent report, connectivity between the dorsal and ventral attention networks was higher in female children at 3 months after concussion without persisting symptoms relative to concussion with persisting symptoms, 1.25 (2.05 to 0.46), and OI, 0.87 (0.25 to 1.49).

DISCUSSION

Time after injury, age at injury, biological sex, and persistent symptom status are important moderators of FC after pediatric concussion for children seen in emergency department settings. Postacute FC may not enhance clinical diagnosis. Although within-network connectivity is preserved, between-network connectivity differences emerge after most children clinically recover and persist up to 6 months after pediatric concussion, providing a potential objective biomarker for lasting changes in brain function.

The MR neuroimaging protocol for the Accelerating Medicines Partnership® Schizophrenia Program

Neuroimaging with MRI has been a frequent component of studies of individuals at clinical high risk (CHR) for developing psychosis, with goals of understanding potential brain regions and systems impacted in the CHR state and identifying prognostic or predictive biomarkers that can enhance our ability to forecast clinical outcomes. To date, most studies involving MRI in CHR are likely not sufficiently powered to generate robust and generalizable neuroimaging results. Here, we describe the prospective, advanced, and modern neuroimaging protocol that was implemented in a complex multi-site, multi-vendor environment, as part of the large-scale Accelerating Medicines Partnership® Schizophrenia Program (AMP® SCZ), including the rationale for various choices. This protocol includes T1- and T2-weighted structural scans, resting-state fMRI, and diffusion-weighted imaging collected at two time points, approximately 2 months apart. We also present preliminary variance component analyses of several measures, such as signal- and contrast-to-noise ratio (SNR/CNR) and spatial smoothness, to provide quantitative data on the relative percentages of participant, site, and platform (i.e., scanner model) variance. Site-related variance is generally small (typically <10%). For the SNR/CNR measures from the structural and fMRI scans, participant variance is the largest component (as desired; 40-76%). However, for SNR/CNR in the diffusion scans, there is substantial platform-related variance (>55%) due to differences in the diffusion imaging hardware capabilities of the different scanners. Also, spatial smoothness generally has a large platform-related variance due to inherent, difficult to control, differences between vendors in their acquisitions and reconstructions. These results illustrate some of the factors that will need to be considered in analyses of the AMP SCZ neuroimaging data, which will be the largest CHR cohort to date.Watch Dr. Harms discuss this article at https://vimeo.com/1059777228?share=copy#t=0 .

Multi-center brain age prediction via dual-modality fusion convolutional network

Accurate prediction of brain age is crucial for identifying deviations between typical individual brain development trajectories and neuropsychiatric disease progression. Although current research has made progress, the effective application of brain age prediction models to multi-center datasets, particularly those with small-sample sizes, remains a significant challenge that is yet to be addressed. To this end, we propose a multi-center data correction method, which employs a domain adaptation correction strategy with Wasserstein distance of optimal transport, along with maximum mean discrepancy to improve the generalizability of brain-age prediction models on small-sample datasets. Additionally, most of the existing brain age models based on neuroimage identify the task of predicting brain age as a regression or classification problem, which may affect the accuracy of the prediction. Therefore, we propose a brain dual-modality fused convolutional neural network model (BrainDCN) for brain age prediction, and optimize this model by introducing a joint loss function of mean absolute error and cross-entropy, which identifies the prediction of brain age as both a regression and classification task. Furthermore, to highlight age-related features, we construct weighting matrices and vectors from a single-center training set and apply them to multi-center datasets to weight important features. We validate the BrainDCN model on the CamCAN dataset and achieve the lowest average absolute error compared to state-of-the-art models, demonstrating its superiority. Notably, the joint loss function and weighted features can further improve the prediction accuracy. More importantly, our proposed multi-center correction method is tested on four neuroimaging datasets and achieves the lowest average absolute error compared to widely used correction methods, highlighting the superior performance of the method in cross-center data integration and analysis. Furthermore, the application to multi-center schizophrenia data shows a mean accelerated aging compared to normal controls. Thus, this research establishes a pivotal methodological foundation for multi-center brain age prediction studies, exhibiting considerable applicability in clinical contexts, which are predominantly characterized by small-sample datasets.

Development and validation of a prediction model for malignant sinonasal tumors based on MR radiomics and machine learning

OBJECTIVES

This study aimed to utilize MR radiomics-based machine learning classifiers on a large-sample, multicenter dataset to develop an optimal model for predicting malignant sinonasal tumors and tumor-like lesions.

METHODS

This study included 1711 adult patients (875 benign and 836 malignant) with sinonasal tumors or tumor-like lesions from three institutions. Patients from institution 1 (n = 1367) constituted both the training and validation cohorts, while those from institution 2 and 3 (n = 158/186) made up the test cohorts. Manual segmentation of the region of interest of the tumor was performed on T1WI, T2WI, and contrast-enhanced T1WI (CE-T1WI). Data normalization, dimensional reductions, feature selection, and classifications were performed using ten machine-learning classifiers. Four fusion models, namely T1WI + T2WI, T1WI + CE-T1WI, T2WI + CE-T1WI, and T1WI + T2WI + CE-T1WI, were constructed using the top ten features with the highest contribution in feature selection in the optimal models of T1WI, T2WI, and CE-T1WI. The Delong test compared areas under the curve (AUC) between models.

RESULTS

The AUCs of training/validation/test1/test2 datasets for T1WI, T2WI, and CE-T1WI were 0.900/0.842/0.872/0.839, 0.876/0.789/0.842/0.863, and 0.899/0.824/0.831/0.707, respectively. The fusion model from T1WI + T2WI + CE-T1WI had the highest AUC. The AUCs of training/validation/test1/test2 datasets were 0.947/0.849/0.871/0.887. The T1WI + T2WI + CE-T1WI model demonstrated a significantly higher AUC than the T2WI + CE-T1WI model in both cohorts (p < 0.05) and outperformed the T2WI model in test 1 (p = 0.008) and the T1WI model in test 2 (p = 0.006).

CONCLUSIONS

This fusion model based on radiomics from T1WI + T2WI + CE-T1WI images and machine learning can improve the power in predicting malignant sinonasal tumors with high accuracy, resilience, and robustness.

CLINICAL RELEVANCE STATEMENT

Our study proposes a radiomics-based machine learning fusion model from T1- and T2-weighted images and contrast-enhanced T1-weighted images, which can non-invasively identify the nature of sinonasal tumors and improve the performance in predicting malignant sinonasal tumors.

KEY POINTS

Differentiating benign and malignant sinonasal tumors is difficult due to similar clinical presentations. A radiomics model from T1 + T2 + contrast-enhanced T1 images can identify the nature of sinonasal tumors. This model can help distinguish benign and malignant sinonasal tumors.

Site effects in multisite fetal brain MRI: morphological insights into early brain development

OBJECTIVE

To evaluate multisite effects on fetal brain MRI. Specifically, to identify crucial acquisition factors affecting fetal brain structural measurements and developmental patterns, while assessing the effectiveness of existing harmonization methods in mitigating site effects.

MATERIALS AND METHODS

Between May 2017 and March 2022, T2-weighted fast spin-echo sequences in-utero MRI were performed on healthy fetuses from retrospectively recruited pregnant volunteers on four different scanners at four sites. A generalized additive model (GAM) was used to quantitatively assess site effects, including field strength (FS), manufacturer (M), in-plane resolution (R), and slice thickness (ST), on subcortical volume and cortical morphological measurements, including cortical thickness, curvature, and sulcal depth. Growth models were selected to elucidate the developmental trajectories of these morphological measurements. Welch's test was performed to evaluate the influence of site effects on developmental trajectories. The comBat-GAM harmonization method was applied to mitigate site-related biases.

RESULTS

The final analytic sample consisted of 340 MRI scans from 218 fetuses (mean GA, 30.1 weeks ± 4.4 [range, 21.7-40 weeks]). GAM results showed that lower FS and lower spatial resolution led to overestimations in selected brain regions of subcortical volumes and cortical morphological measurements. Only the peak cortical thickness in developmental trajectories was significantly influenced by the effects of FS and R. Notably, ComBat-GAM harmonization effectively removed site effects while preserving developmental patterns.

CONCLUSION

Our findings pinpointed the key acquisition factors in in-utero fetal brain MRI and underscored the necessity of data harmonization when pooling multisite data for fetal brain morphology investigations.

KEY POINTS

Question How do specific site MRI acquisition factors affect fetal brain imaging? Finding Lower FS and spatial resolution overestimated subcortical volumes and cortical measurements. Cortical thickness in developmental trajectories was influenced by FS and in-plane resolution. Clinical relevance This study provides important guidelines for the fetal MRI community when scanning fetal brains and underscores the necessity of data harmonization of cross-center fetal studies.

Beyond case-control study in neuroimaging for psychiatric disorders: Harmonizing and utilizing the brain images from multiple sites

Recent magnetic resonance imaging (MRI) research has advanced our understanding of brain pathophysiology in psychiatric disorders. This progress necessitates re-evaluation of the diagnostic system for psychiatric disorders based on MRI-based biomarkers, with implications for precise clinical diagnosis and optimal therapeutics. To achieve this goal, large-scale multi-site studies are essential to develop a standardized MRI database, with the analysis of several thousands of images and the incorporation of new data. A critical challenge in these studies is to minimize sampling and measurement biases in MRI studies to accurately capture the diversity of disease-derived biomarkers. Various techniques have been employed to consolidate datasets from multiple sites in case-control studies. Traveling subject harmonization stands out as a powerful tool that can differentiate measurement bias from sample variety and sampling bias. A non-linear statistical model for a normative trajectory across the lifespan also strengthens the database to mitigate sampling bias from known factors such as age and sex. These approaches can enhance the alterations between psychiatric disorders and integrate new data and follow-up scans into existing life-course trajectory, enhancing the reliability of machine learning classification and subtyping. Although this approach has been developed using T1-weighted structural image features, future research may extend this framework to other modalities and measures. The required sample size and methodological establishment are needed for future investigations, leading to novel insights into the brain pathophysiology of psychiatric disorders and the development of optimal therapeutics for bedside clinical applications. Sharing big data and their findings also need to be considered.

Neural basis for individual differences in the attention-enhancing effects of methylphenidate

Stimulant drugs that boost dopamine, like methylphenidate (MP), enhance attention and are effective treatments for attention-deficit hyperactivity disorder (ADHD). Yet there is large individual variation in attentional capacity and response to MP. It is unclear whether this variation is driven by individual differences in relative density of dopamine receptor subtypes, magnitude of dopamine increases induced by MP, or both. Here, we extensively characterized the brain dopamine system with positron emission tomography (PET) imaging (including striatal dopamine D1 and D2/3 receptor availability and MP-induced dopamine increases) and measured attention task-evoked fMRI brain activity in two separate sessions (placebo and 60 mg oral MP; single-blind, counterbalanced) in 37 healthy adults. A network of lateral frontoparietal and visual cortices was sensitive to increasing attentional (and working memory) load, whose activity positively correlated with performance across individuals (partial r = 0.474, P = 0.008; controlling for age). MP-induced change in activity within this network correlated with MP-induced change in performance (partial r = 0.686, P < 0.001). The ratio of D1-to-D2/3 receptors in dorsomedial caudate positively correlated with baseline attentional network activity and negatively correlated with MP-induced changes in activity (all pFWE < 0.02). MP-induced changes in attentional load network activity mediated the association between D1-to-D2/3 ratio and MP-induced improvements in performance (mediation estimate = 23.20 [95%CI: -153.67 -81.79], P = 0.004). MP attention-boosting effects were not linked to the magnitude of striatal dopamine increases, but rather showed dependence on an individual's baseline receptor density. Individuals with lower D1-to-D2/3 ratios tended to have lower frontoparietal activity during sustained attention and experienced greater improvement in brain function and task performance with MP.

Advancements in Surgical Therapies for Drug-Resistant Epilepsy: A Paradigm Shift towards Precision Care

Epilepsy, a prevalent neurological disorder characterized by recurrent seizures, affects millions worldwide, with a significant proportion resistant to pharmacological treatments. Surgical interventions have emerged as pivotal in managing drug-resistant epilepsy (DRE), aiming to reduce seizure frequency or achieve seizure freedom. Traditional resective surgeries have evolved with technological advances, enhancing precision and safety. Neurostimulation techniques, such as responsive neurostimulation (RNS) and deep brain stimulation (DBS), now provide personalized, real-time seizure management, offering alternatives to traditional surgery. Minimally invasive ablative methods, such as laser interstitial thermal therapy (LITT) and Magnetic Resonance-guided Focused Ultrasound (MRgFUS), allow for targeted destruction of epileptogenic tissue with reduced risks and faster recovery times. The use of stereo-electroencephalography (SEEG) and robotic assistance has further refined surgical precision, enhancing outcomes. These advancements mark a paradigm shift towards precision medicine in epilepsy care, promising improved seizure management and quality of life for patients globally. This review outlines the latest innovations in epilepsy surgery, emphasizing their mechanisms and clinical implications to improve outcomes for patients with DRE.

Harmonizing flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization

Lack of standardization and various intrinsic parameters for magnetic resonance (MR) image acquisition results in heterogeneous images across different sites and devices, which adversely affects the generalization of deep neural networks. To alleviate this issue, this work proposes a novel unsupervised harmonization framework that leverages normalizing flows to align MR images, thereby emulating the distribution of a source domain. The proposed strategy comprises three key steps. Initially, a normalizing flow network is trained to capture the distribution characteristics of the source domain. Then, we train a shallow harmonizer network to reconstruct images from the source domain via their augmented counterparts. Finally, during inference, the harmonizer network is updated to ensure that the output images conform to the learned source domain distribution, as modeled by the normalizing flow network. Our approach, which is unsupervised, source-free, and task-agnostic is assessed in the context of both adults and neonatal cross-domain brain MRI segmentation, as well as neonatal brain age estimation, demonstrating its generalizability across tasks and population demographics. The results underscore its superior performance compared to existing methodologies. The code is available at https://github.com/farzad-bz/Harmonizing-Flows.

Two-year impact of COVID-19: Longitudinal MRI brain changes and neuropsychiatric trajectories

AIM

Up to 10% of SARS-CoV-2 infected individuals suffer from post-COVID-19 condition, marked by fatigue and cognitive dysfunction as major symptoms. Longitudinal studies on neuropsychological and clinical trajectories and related brain changes are scarce. Here, we aimed to examine their evolution up to 2 years post-infection.

METHODS

In a multi-center, longitudinal study of 79 post-COVID patients (mean age 46, 48 female) with persistent symptoms and 21 age- and sex-matched never-infected, healthy controls (mean age 42, eight female), we analyzed neuropsychological performance, self-reported outcomes and associated neuroimaging alterations of resting-state functional and structural magnetic resonance imaging data 23 months post-infection.

RESULTS

In post-COVID patients 23 months after SARS-CoV-2 infection we observed (1) that fatigue severity had reduced but still remained present in most patients, (2) widespread brain changes involving the brainstem, the pre- and postcentral gyrus and the limbic olfactory network, (3) a weakening of self-reported fatigue and its cerebral associations. Notably, findings of brain aberrations were more pronounced in hospitalized patients.

CONCLUSION

Our findings indicate that complex brain adaptations take place up to 2 years following SARS-CoV-2 infection. Some regions manifest enduring abnormalities while others undergo restitution. The attenuation of radio-clinical associations suggests a compensatory function for these regions, pointing to non-brain intrinsic factors to sustain persistent fatigue.

How growing up without siblings affects the adult brain and behaviour in the CHIMGEN cohort

With the worldwide increase in only-child families, it is crucial to understand the effects of growing up without siblings (GWS) on the adult brain, behaviour and the underlying pathways. Using the CHIMGEN cohort, we investigated the associations of GWS with adult brain structure, function, connectivity, cognition, personality and mental health, as well as the pathway from GWS to GWS-related growth environments to brain and to behaviour development, in 2,397 pairs of individuals with and without siblings well matched in covariates. We found associations linking GWS to higher language fibre integrity, lower motor fibre integrity, larger cerebellar volume, smaller cerebral volume and lower frontotemporal spontaneous brain activity. Contrary to the stereotypical impression of associations between GWS and problem behaviours, we found positive correlations of GWS with neurocognition and mental health. Despite direct effects, GWS affects most brain and behavioural outcomes through modifiable environments, such as socioeconomic status, maternal care and family support, suggesting targets for interventions to enhance children's healthy growth.

Harmonization of Structural Brain Connectivity through Distribution Matching

The increasing prevalence of multi-site diffusion-weighted magnetic resonance imaging (dMRI) studies potentially offers enhanced statistical power to investigate brain structure. However, these studies face challenges due to variations in scanner hardware and acquisition protocols. While several methods for dMRI data harmonization exist, few specifically address structural brain connectivity. We introduce a new distribution-matching approach to harmonizing structural brain connectivity across different sites and scanners. We evaluate our method using structural brain connectivity data from three distinct datasets (OASIS-3, ADNI-2, and PREVENT-AD), comparing its performance to the widely used ComBat method and the more recent CovBat approach. We examine the impact of harmonization on the correlation of brain connectivity with the Mini-Mental State Examination score and age. Our results demonstrate that our distribution-matching technique more effectively harmonizes structural brain connectivity, often producing stronger and more significant correlations compared to alternative methods. Qualitative assessments illustrate the desired distributional alignment across datasets, while quantitative evaluations confirm robust performance. This work contributes to the growing field of dMRI harmonization, potentially improving the reliability and comparability of structural connectivity studies that combine data from different sources in neuroscientific and clinical research.

Assessing measurement consistency of a diffusion tensor imaging (DTI) quality control (QC) anisotropy phantom

OBJECTIVES

We evaluated a quality control (QC) phantom designed to mimic diffusion characteristics and white matter fiber tracts in the brain. We hypothesized that acquisition of diffusion tensor imaging (DTI) data on different vendors and over multiple repeated measures would not contribute to significant variability in calculated diffusion tensor scalar metrics such as fractional anisotropy (FA) and mean diffusivity (MD).

MATERIALS AND METHODS

The DTI QC phantom was scanned using a 32-direction DTI sequence on General Electric (GE), Siemens, and Philips 3 Tesla scanners. Motion probing gradients (MPGs) were investigated as a source of variance in our statistical design, and data were acquired on GE and Siemens scanners using GE, Siemens, and Philips vendor MPGs for 32 directions. In total, 8 repeated scans were made for each GE/Siemens combination of vendor and MPGs with 8 repeated scans on a Philips machine using its stock DTI sequence. Data were analyzed using 2-way ANOVAs to investigate repeat scan and vendor variances and 3-way ANOVAs with repeat, MPG, and vendor as factors.

RESULTS

No statistical differences (i.e., P > 0.05) were found in any DTI scalar metrics (FA, MD) or for any factor, suggesting system constancy across imaging platforms and the specified phantom's reliability and reproducibility across vendors and conditions.

DISCUSSION

A DTI QC phantom demonstrates that DTI measurements maintain their consistency across different MRI systems and can contribute to a standard that is more reliable for quantitative MRI analyses.

Cross-ancestry and sex-stratified genome-wide association analyses of amygdala and subnucleus volumes

The amygdala is a small but critical multi-nucleus structure for emotion, cognition and neuropsychiatric disorders. Although genetic associations with amygdala volumetric traits have been investigated in sex-combined European populations, cross-ancestry and sex-stratified analyses are lacking. Here we conducted cross-ancestry and sex-stratified genome-wide association analyses for 21 amygdala volumetric traits in 6,923 Chinese and 48,634 European individuals. We identified 191 variant-trait associations (P < 2.38 × 10-9), including 47 new associations (12 new loci) in sex-combined univariate analyses and seven additional new loci in sex-combined and sex-stratified multivariate analyses. We identified 12 ancestry-specific and two sex-specific associations. The identified genetic variants include 16 fine-mapped causal variants and regulate amygdala and fetal brain gene expression. The variants were enriched for brain development and colocalized with mood, cognition and neuropsychiatric disorders. These results indicate that cross-ancestry and sex-stratified genetic association analyses may provide insight into the genetic architectures of amygdala and subnucleus volumes.

White Matter, Cognition, and Electrophysiological Variables in Bipolar Disorder: Using Multimodal Integration of Biomarker Variables Associated With Bipolar Disorder to Elucidate Deficits

AIM

This study aimed to evaluate associations in bipolar disorder (BD) across multimodal measures of white matter microstructure (using diffusion tensor imaging; DTI), cognitive, behavioral, and brain electrophysiological measures (using electroencephalography; EEG).

METHODS

Subjects were recruited through the Psychosis and Affective Research Domains and Intermediate Phenotypes Consortium (n = 45 bipolar with psychosis, n = 40 bipolar without psychosis, n = 66 healthy subjects). DTI data were used to quantify the white matter variables, fractional anisotropy (FA) and radial diffusivity (RD). The Brief Assessment of Cognition in Schizophrenia (BACS), Stop Signal Task (SST), pro- and anti-saccades, auditory event-related potentials (ERPs), and intrinsic brain activity were used as estimates of brain function.

RESULTS

The combined BD group differed from healthy controls, but no differences between BD with and without psychosis were observed. BD-related white matter abnormalities were seen across multiple tracts: right cingulum-cingulate gyrus, bilateral anterior thalamic radiation, bilateral superior longitudinal fasciculus, right inferior longitudinal fasciculus, and forceps major. Results also showed modestly compromised cognitive performance and elevated intrinsic EEG activity associated with BD.

CONCLUSIONS

Further analysis indicated worse white matter integrity related to higher intrinsic EEG and modestly higher ERPs. These multimodal analyses are likely to aid in creating future informative diagnostic, etiological, and treatment targets for BD.

Brain structural correlates of an impending initial major depressive episode

Neuroimaging research has yet to elucidate whether reported gray matter volume (GMV) alterations in major depressive disorder (MDD) exist already before the onset of the first episode. Recruitment of presently healthy individuals with a subsequent transition to MDD (converters) is extremely challenging but crucial to gain insights into neurobiological vulnerability. Hence, we compared converters to patients with MDD and sustained healthy controls (HC) to distinguish pre-existing neurobiological markers from those emerging later in the course of depression. Combining two clinical cohorts (n = 1709), voxel-based morphometry was utilized to analyze GMV of n = 45 converters, n = 748 patients with MDD, and n = 916 HC in a region-of-interest approach and exploratory whole-brain. By contrasting the subgroups and considering both remission state and reported recurrence at a 2-year clinical follow-up, we stepwise disentangled effects of (1) vulnerability, (2) the acute depressive state, and (3) an initial vs. a recurrent episode. Analyses revealed higher amygdala GMV in converters relative to HC (ptfce-FWE = 0.037, d = 0.447) and patients (ptfce-FWE = 0.005, d = 0.508), remaining significant when compared to remitted patients with imminent recurrence. Lower GMV in the dorsolateral prefrontal cortex (ptfce-FWE < 0.001, d = 0.188) and insula (ptfce-FWE = 0.010, d = 0.186) emerged in patients relative to HC but not to converters, driven by patients with acute MDD. By examining one of the largest available converter samples in psychiatric neuroimaging, this study allowed a first determination of neural markers for an impending initial depressive episode. Our findings suggest a temporary vulnerability, which in combination with other common risk factors might facilitate prediction and in turn improve prevention of depression.

Uncovering atrophy progression pattern and mechanisms in individuals at risk of Alzheimer's disease

Alzheimer's disease is associated with pre-symptomatic changes in brain morphometry and accumulation of abnormal tau and amyloid-beta pathology. Studying the development of brain changes prior to symptoms onset may lead to early diagnostic biomarkers and a better understanding of Alzheimer's disease pathophysiology. Alzheimer's disease pathology is thought to arise from a combination of protein accumulation and spreading via neural connections, but how these processes influence brain atrophy progression in the pre-symptomatic phases remains unclear. Individuals with a family history of Alzheimer's disease (FHAD) have an elevated risk of Alzheimer's disease, providing an opportunity to study the pre-symptomatic phase. Here, we used structural MRI from three databases (Alzheimer's Disease Neuroimaging Initiative, Pre-symptomatic Evaluation of Experimental or Novel Treatments for Alzheimer Disease and Montreal Adult Lifespan Study) to map atrophy progression in FHAD and Alzheimer's disease and assess the constraining effects of structural connectivity on atrophy progression. Cross-sectional and longitudinal data up to 4 years were used to perform atrophy progression analysis in FHAD and Alzheimer's disease compared with controls. PET radiotracers were also used to quantify the distribution of abnormal tau and amyloid-beta protein isoforms at baseline. We first derived cortical atrophy progression maps using deformation-based morphometry from 153 FHAD, 156 Alzheimer's disease and 116 controls with similar age, education and sex at baseline. We next examined the spatial relationship between atrophy progression and spatial patterns of tau aggregates and amyloid-beta plaques deposition, structural connectivity and neurotransmitter receptor and transporter distributions. Our results show that there were similar patterns of atrophy progression in FHAD and Alzheimer's disease, notably in the cingulate, temporal and parietal cortices, with more widespread and severe atrophy in Alzheimer's disease. Both tau and amyloid-beta pathology tended to accumulate in regions that were structurally connected in FHAD and Alzheimer's disease. The pattern of atrophy and its progression also aligned with existing structural connectivity in FHAD. In Alzheimer's disease, our findings suggest that atrophy progression results from pathology propagation that occurred earlier, on a previously intact connectome. Moreover, a relationship was found between serotonin receptor spatial distribution and atrophy progression in Alzheimer's disease. The current study demonstrates that regions showing atrophy progression in FHAD and Alzheimer's disease present with specific connectivity and cellular characteristics, uncovering some of the mechanisms involved in pre-clinical and clinical neurodegeneration.

Riemannian manifold-based disentangled representation learning for multi-site functional connectivity analysis

Functional connectivity (FC), derived from resting-state functional magnetic resonance imaging (rs-fMRI), has been widely used to characterize brain abnormalities in disorders. FC is usually defined as a correlation matrix that is a symmetric positive definite (SPD) matrix lying on the Riemannian manifold. Recently, a number of learning-based methods have been proposed for FC analysis, while the geometric properties of Riemannian manifold have not yet been fully explored in previous studies. Also, most existing methods are designed to target one imaging site of fMRI data, which may result in limited training data for learning reliable and robust models. In this paper, we propose a novel Riemannian Manifold-based Disentangled Representation Learning (RM-DRL) framework which is capable of learning invariant representations from fMRI data across multiple sites for brain disorder diagnosis. In RM-DRL, we first employ an SPD-based encoder module to learn a latent unified representation of FC from different sites, which can preserve the Riemannian geometry of the SPD matrices. In latent space, a disentangled representation module is then designed to split the learned features into domain-specific and domain-invariant parts, respectively. Finally, a decoder module is introduced to ensure that sufficient information can be preserved during disentanglement learning. These designs allow us to introduce four types of training objectives to improve the disentanglement learning. Our RM-DRL method is evaluated on the public multi-site ABIDE dataset, showing superior performance compared with several state-of-the-art methods.

A generalizable normative deep autoencoder for brain morphological anomaly detection: application to the multi-site StratiBip dataset on bipolar disorder in an external validation framework

The heterogeneity of psychiatric disorders makes researching disorder-specific neurobiological markers an ill-posed problem. Here, we face the need for disease stratification models by presenting a generalizable multivariate normative modelling framework for characterizing brain morphology, applied to bipolar disorder (BD). We used deep autoencoders in an anomaly detection framework, combined for the first time with a confounder removal step that integrates training and external validation. The model was trained with healthy control (HC) data from the human connectome project and applied to multi-site external data of HC and BD individuals. We found that brain deviating scores were greater, more heterogeneous, and with increased extreme values in the BD group, with volumes prominently from the basal ganglia, hippocampus, and adjacent regions emerging as significantly deviating. Similarly, individual brain deviating maps based on modified z scores expressed higher abnormalities occurrences, but their overall spatial overlap was lower compared to HCs. Our generalizable framework enabled the identification of brain deviating patterns differing between the subject and the group levels, a step forward towards the development of more effective and personalized clinical decision support systems and patient stratification in psychiatry.

Objective Determination of Site-of-Lesion in Auditory Neuropathy

OBJECTIVES

Auditory neuropathy (AN), a complex hearing disorder, presents challenges in diagnosis and management due to limitations of current diagnostic assessment. This study aims to determine whether diffusion-weighted magnetic resonance imaging (MRI) can be used to identify the site and severity of lesions in individuals with AN.

METHODS

This case-control study included 10 individuals with AN of different etiologies, 7 individuals with neurofibromatosis type 1 (NF1), 5 individuals with cochlear hearing loss, and 37 control participants. Participants were recruited through the University of Melbourne's Neuroaudiology Clinic and the Murdoch Children's Research Institute specialist outpatient clinics. Diffusion-weighted MRI data were collected for all participants and the auditory pathways were evaluated using the fixel-based analysis metric of apparent fiber density. Data on each participant's auditory function were also collected including hearing thresholds, otoacoustic emissions, auditory evoked potentials, and speech-in-noise perceptual ability.

RESULTS

Analysis of diffusion-weighted MRI showed abnormal white matter fiber density in distinct locations within the auditory system depending on etiology. Compared with controls, individuals with AN due to perinatal oxygen deprivation showed no white matter abnormalities ( p > 0.05), those with a neurodegenerative conditions known/predicted to cause VIII cranial nerve axonopathy showed significantly lower white matter fiber density in the vestibulocochlear nerve ( p < 0.001), while participants with NF1 showed lower white matter fiber density in the auditory brainstem tracts ( p = 0.003). In addition, auditory behavioral measures of speech perception in noise and gap detection were correlated with fiber density results of the VIII nerve.

CONCLUSIONS

Diffusion-weighted MRI reveals different patterns of anatomical abnormality within the auditory system depending on etiology. This technique has the potential to guide management recommendations for individuals with peripheral and central auditory pathway abnormality.

The impact of the novel CovBat harmonization method on enhancing radiomics feature stability and machine learning model performance: A multi-center, multi-device study

PURPOSE

This study aims to assess whether the novel CovBat harmonization method can further reduce radiomics feature variability from different imaging devices in multi-center studies and improve machine learning model performance compared to the ComBat method.

MATERIALS

Non-contrast abdominal CT scans of 1,000 healthy subjects from three medical institutions (from four manufacturers and eight different models) were retrospectively included: Hospital A (n = 513), Hospital B (n = 338), and Hospital C (n = 149). 93 radiomics features were extracted from liver and spleen tissues using PyRadiomics. Performing a binary classification task of liver and spleen tissues on the pooled data from the three institutions: (1) Unharmonized, (2) ComBat, and (3) CovBat. Models were built separately for each radiomics feature classes (First-order, GLCM, GLRLM, GLSZM, NGTD, GLDM), as well as a combined model integrating all feature classes. The Kruskal-Wallis test and principal component analysis (PCA) were used to assess the variability of radiomics features among the groups. Multiple linear regression models were used to analyze the sources of variation. Accuracy, sensitivity, specificity, F1-score, and area under the curve (AUC) were used to evaluate model performance.

RESULTS

After ComBat and CovBat harmonization, the number of consistent features increased by 68.82 % and 73.12 %, respectively, and the feature variability due to hardware differences decreased from 12.32-25.38 % to 1.89-2.01 % with ComBat and 1.19-1.88 % with CovBat. The AUC of the machine learning models improved significantly: Combined (Unharmonized: 0.93, ComBat: 0.99, CovBat: 1.00), First-order (0.93, 0.98, 0.98), GLCM (0.81, 0.93, 0.98), GLRLM (0.78, 0.96, 0.98), NGTDM (0.75, 0.96, 0.98), GLSZM (0.78, 0.93, 0.97), and GLDM (0.83, 0.94, 0.97). DeLong's test showed that the results before and after harmonization were statistically significant (P < 0.05).

CONCLUSION

CovBat further reduced radiomics feature variability caused by different CT scanners and significantly improved the performance of machine learning models, although the degree of improvement varied across different feature categories.

Comparative analysis of machine learning models for predicting pathological complete response to neoadjuvant chemotherapy in breast cancer: An MRI radiomics approach

PURPOSE

The aim of this work is to compare different machine learning models for predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer using radiomics features from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).

METHOD

The study included 55 patients with breast cancer, among whom 18 achieved pCR and 37 did not respond completely to NAC (non-pCR). After some pre-processing steps, 1446 features were extracted and corrected for batch effects using ComBat. Five machine learning algorithms, namely random forest (RF), decision tree (DT), logistic regression (LR), k-nearest neighbors (k-NN), and extreme gradient boosting (XGB), were evaluated using area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and F1 score as classification metrics. A Leave-Group-Out cross validation (LGOCV) was applied in the outer loop.

RESULTS

RF and DT models exhibited the highest performances compared to the other algorithms. DT achieved an accuracy of 0.96 ± 0.07, and RF achieved 0.95 ± 0.05. The AUC values for RF and DT were 0.98 ± 0.06 and 0.94 ± 0.07, respectively. LR and k-NN demonstrated lower performance across all metrics, while XGB showed competitive results but slightly lower than RF and DT.

CONCLUSIONS

This study demonstrates the potential of radiomics and machine learning for predicting pCR to NAC in breast cancer. RF and DT models proved to be the most effective in capturing underlying patterns in radiomics data. Further research is required to validate and strengthen the proposed approach and explore its applicability in diverse radiomics datasets and clinical scenarios.

Whole-brain gray matter volume and fractional anisotropy of the posterior thalamic radiation and sagittal stratum in healthy adults correlate with the local environment

The impacts of air pollution, local climate, and urbanization on human health have been well-documented in recent studies. In this study, we combined magnetic resonance imaging (MRI) brain analysis with a questionnaire survey on the local environment in 141 healthy middle-aged men and women. Our findings reveal that a favorable environment is positively correlated with gray matter volume (GMV) in the frontal and occipital lobes, cerebellum, and whole brain, as well as with fractional anisotropy (FA) in the fornix (including the fornix stria terminalis), posterior thalamic radiation (PTR), sagittal stratum (SS), and whole brain. Among these, significant correlations between the local environment and whole-brain and cerebellar GMV, PTR, and SS FA remained after Bonferroni correction. Additionally, the positive relationship between the local environment and whole-brain GMV was further supported by principal component analysis (PCA). This is the first study to demonstrate that healthy adult brain structure, as indicated by GMV and FA values, can be influenced by the local environment.

Association Between Single Nucleotide Polymorphisms in the Aquaporin-4 Gene and Longitudinal Changes in White Matter Free Water and Cognitive Function in Non-Demented Older Adults

We investigated whether aquaporin-4 (AQP4) single-nucleotide polymorphisms (SNPs) influence Alzheimer's disease (AD) progression through changes in the glymphatic system. We included 242 non-dementia participants and chose six SNPs previously shown to be related to AD. We analyzed the associations between AQP4 SNPs and glymphatic markers, including enlarged perivascular spaces (PVS), white matter free water (FW), and diffusion tensor image analysis along the perivascular space (DTI-ALPS), in both cross-sectional and longitudinal data. We investigated whether AQP4-related glymphatic markers are associated with AD pathology progression and cognitive impairment, and whether they mediate the relationship between AQP4 SNPs and AD progression. There was no association between AQP4 SNPs and glymphatic markers at baseline. Carriers of the AQP4 SNP rs72878794 minor allele status exhibited slower FW increase in the amyloid-positive group (SNP*time: β = -0.0040, t(46.25) = -2.062, p = 0.045, 95% CI = -0.0078 ~ -0.0001), whereas the rs9951307 minor allele carrier showed a faster FW increase in the amyloid-negative group (SNP*time: β =0.0033, t(81.19) = 2.245, p = 0.027, 95% CI = 0.0004 ~ 0.0062). The higher FW was associated with faster cognitive decline at follow-ups. AQP4 SNPs influence interstitial fluid accumulation, contributing to cognitive decline but not amyloid deposition in AD. Further studies are needed to clarify the pathways linking AQP4 SNPs and AD progression.

White matter microstructure in school-age children with down syndrome

Down syndrome (DS) is the most common genetic cause of intellectual disability, but our understanding of white matter microstructure in children with DS remains limited. Previous studies have reported reductions in white matter integrity, but nearly all studies to date have been conducted in adults or relied solely on diffusion tensor imaging (DTI), which lacks the ability to disentangle underlying properties of white matter organization. This study examined white matter microstructural differences in 7- to 12-year-old children with DS (n = 23), autism (n = 27), and typical development (n = 50) using DTI as well as High Angular Resolution Diffusion Imaging, and Neurite Orientation and Dispersion Imaging. There was a spatially specific pattern of results that showed a dissociation between intra- and inter-hemispheric pathways. Intra-hemispheric pathways (e.g., inferior fronto-occipital fasciculus, superior longitudinal fasciculus) exhibited reduced organization and structural integrity. Inter-hemispheric pathways (e.g., corpus callosum projections) and motor pathways (e.g., corticospinal tract) showed denser neurite packing and lower neurite dispersion. The current findings provide early insight into white matter development in school-aged children with DS and have the potential to further elucidate microstructural differences and inform more targeted clinical trials than what has previously been observed through DTI models alone.

Investigating dopaminergic abnormalities in schizophrenia and first-episode psychosis with normative modelling and multisite molecular neuroimaging

Molecular neuroimaging techniques, like PET and SPECT, offer invaluable insights into the brain's in-vivo biology and its dysfunction in neuropsychiatric patients. However, the transition of molecular neuroimaging into diagnostics and precision medicine has been limited to a few clinical applications, hindered by issues like practical feasibility, high costs, and high between-subject heterogeneity of neuroimaging measures. In this study, we explore the use of normative modelling (NM) to identify individual patient alterations by describing the physiological variability of molecular functions. NM potentially addresses challenges such as small sample sizes and diverse acquisition protocols typical of molecular neuroimaging studies. We applied NM to two PET radiotracers targeting the dopaminergic system ([11C]-(+)-PHNO and [18F]FDOPA) to create a reference-cohort model of healthy controls. The models were subsequently utilized on different independent cohorts of patients with psychosis in different disease stages and treatment outcomes. Our results showed that patients with psychosis exhibited a higher degree of extreme deviations (~3-fold increase) than controls, although this pattern was heterogeneous, with minimal overlap of extreme deviations topology (max 20%). We also confirmed that striatal [18F]FDOPA signal, when referenced to a normative distribution, can predict treatment response (striatal AUC ROC: 0.77-0.83). In conclusion, our results indicate that normative modelling can be effectively applied to molecular neuroimaging after proper harmonization, enabling insights into disease mechanisms and advancing precision medicine. In addition, the method is valuable in understanding the heterogeneity of patient populations and can contribute to maximising cost efficiency in studies aimed at comparing cases and controls.

Temporal and spatial variability of large-scale dynamic brain networks in ASD

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by significant impairments in social-cognitive functioning. Prior studies have identified abnormal brain functional connectivity (FC) patterns in individuals with ASD, which are associated with core symptoms and serve as potential biomarkers for diagnosis. However, the patterns of temporal and spatial variability in dynamic functional connectivity networks (dFCNs) in ASD and their relationship with ASD behaviors remain underexplored. This study uses fuzzy entropy to analyze the temporal variability and spatial variability of dFCNs, aiming to reveal distinctive FC patterns in ASD and identify new biomarkers. We conducted a comparative analysis between ASD and healthy controls (HCs), examining the association with clinical symptoms. Our findings indicate increased FC temporal variability in sensorimotor, subcortical, and cerebellar networks in ASD compared to HCs. Additionally, increased spatial variability was observed primarily in visual, limbic, subcortical, and cerebellar networks. Notably, these variability patterns correlated with symptom severity in ASD. Utilizing these spatiotemporal variability features, we developed multi-site classification models that achieved high accuracy (81.25%) in identifying ASD. These results provide novel insights into the neural mechanisms and clinical characteristics of ASD, suggesting that integrated spatiotemporal dFCN features may enhance diagnostic accuracy.

Atypical hierarchical brain connectivity in autism: Insights from stepwise causal analysis using Liang information flow

Autism spectrum disorder (ASD) is associated with atypical brain connectivity, yet its hierarchical organization remains underexplored. In this study, we applied the Liang information flow method to analyze stepwise causal functional connectivity in ASD, offering a novel approach to understanding how different brain networks interact. Using resting-state fMRI data from ASD individuals and healthy controls, we observed significant alterations in both positive and negative causal connections across the ventral attention network, limbic network, frontal-parietal network, and default mode network. These disruptions were detected at multiple hierarchical levels, indicating changes in communication patterns across brain regions. By leveraging features of hierarchical causal connectivity, we achieved high classification accuracy between ASD and healthy individuals. Additionally, changes in network node degrees were found to correlate with ASD clinical symptoms, particularly social and communication behaviors. Our findings provide new insights into disrupted hierarchical brain connectivity in ASD and demonstrate the potential of this approach for distinguishing ASD from typical development.

Reproducible Brain Charts: An open data resource for mapping brain development and its associations with mental health

Major mental disorders are increasingly understood as disorders of brain development. Large and heterogeneous samples are required to define generalizable links between brain development and psychopathology. To this end, we introduce the Reproducible Brain Charts (RBC), an open data resource that integrates data from 5 large studies of brain development in youth from three continents (N=6,346; 45% Female). Confirmatory bifactor models were used to create harmonized psychiatric phenotypes that capture major dimensions of psychopathology. Following rigorous quality assurance, neuroimaging data were carefully curated and processed using consistent pipelines in a reproducible manner with DataLad, the Configurable Pipeline for the Analysis of Connectomes (C-PAC), and FreeSurfer. Initial analyses of RBC data emphasize the benefit of careful quality assurance and data harmonization in delineating developmental effects and associations with psychopathology. Critically, all RBC data - including harmonized psychiatric phenotypes, unprocessed images, and fully processed imaging derivatives - are openly shared without a data use agreement via the International Neuroimaging Data-sharing Initiative. Together, RBC facilitates large-scale, reproducible, and generalizable research in developmental and psychiatric neuroscience.

Disrupted intersubject variability architecture in structural and functional brain connectomes in major depressive disorder

BACKGROUND

Major depressive disorder (MDD) is a heterogeneous condition characterized by significant intersubject variability in clinical presentations. Recent neuroimaging studies have indicated that MDD involves altered brain connectivity across widespread regions. However, the variability in abnormal connectivity among MDD patients remains understudied.

METHODS

Utilizing a large, multi-site dataset comprising 1,276 patients with MDD and 1,104 matched healthy controls, this study aimed to investigate the intersubject variability of structural covariance (IVSC) and functional connectivity (IVFC) in MDD.

RESULTS

Patients with MDD demonstrated higher IVSC in the precuneus and lingual gyrus, but lower IVSC in the medial frontal gyrus, calcarine, cuneus, and cerebellum anterior lobe. Conversely, they exhibited an overall increase in IVFC across almost the entire brain, including the middle frontal gyrus, anterior cingulate cortex, hippocampus, insula, striatum, and precuneus. Correlation and mediation analyses revealed that abnormal IVSC was positively correlated with gray matter atrophy and mediated the relationship between abnormal IVFC and gray matter atrophy. As the disease progressed, IVFC increased in the left striatum, insula, right lingual gyrus, posterior cingulate, and left calcarine. Pharmacotherapy significantly reduced IVFC in the right insula, superior temporal gyrus, and inferior parietal lobule. Furthermore, we found significant but distinct correlations between abnormal IVSC and IVFC and the distribution of neurotransmitter receptors, suggesting potential molecular underpinnings. Further analysis confirmed that abnormal patterns of IVSC and IVFC were reproducible and MDD specificity.

CONCLUSIONS

These results elucidate the heterogeneity of abnormal connectivity in MDD, underscoring the importance of addressing this heterogeneity in future research.

MRI in Oral Tongue Squamous Cell Carcinoma: A Radiomic Approach in the Local Recurrence Evaluation

(1) Background: Oral tongue squamous cell carcinoma (OTSCC) is a prevalent malignancy with high loco-regional recurrence. Advanced imaging biomarkers are critical for stratifying patients at a high risk of recurrence. This study aimed to develop MRI-based radiomic models to predict loco-regional recurrence in OTSCC patients undergoing surgery. (2) Methods: We retrospectively selected 92 patients with OTSCC who underwent MRI, followed by surgery and cervical lymphadenectomy. A total of 31 patients suffered from a loco-regional recurrence. Radiomic features were extracted from preoperative post-contrast high-resolution MRI and integrated with clinical and pathological data to develop predictive models, including radiomic-only and combined radiomic-clinical approaches, trained and validated with stratified data splitting. (3) Results: Textural features, such as those derived from the Gray-Level Size-Zone Matrix, Gray-Level Dependence Matrix, and Gray-Level Run-Length Matrix, showed significant associations with recurrence. The radiomic-only model achieved an accuracy of 0.79 (95% confidence interval: 0.69, 0.87) and 0.74 (95% CI: 0.54, 0.89) in the training and validation set, respectively. Combined radiomic and clinical models, incorporating features like the pathological depth of invasion and lymph node status, provided comparable diagnostic performances. (4) Conclusions: MRI-based radiomic models demonstrated the potential for predicting loco-regional recurrence, highlighting their increasingly important role in advancing precision oncology for OTSCC.

The Psychosis MRI Shared Data Resource (Psy-ShareD)

Neuroimaging research in the field of schizophrenia and other psychotic disorders has sought to investigate neuroanatomical markers, relative to healthy control groups. In recent decades, a large number of structural magnetic resonance imaging (MRI) studies have been funded and undertaken, but their small sample sizes and heterogeneous methods have led to inconsistencies across findings. To tackle this, efforts have been made to combine datasets across studies and sites. While notable recent multicentre initiatives and the resulting meta- and mega-analytical outputs have progressed the field, efforts have generally been restricted to MRI scans in one or two illness stages, often overlook patient heterogeneity, and study populations have rarely been globally representative of the diversity of patients who experience psychosis. Furthermore, access to these datasets is often restricted to consortia members who can contribute data, likely from research institutions located in high-income countries. The Psychosis MRI Shared Data Resource (Psy-ShareD) is a new open access structural MRI data sharing partnership that will host pre-existing structural T1-weighted MRI data collected across multiple sites worldwide, including the Global South. MRI T1 data included in Psy-ShareD will be available in image and feature-level formats, having been harmonised using state-of-the-art approaches. All T1 data will be linked to demographic and illness-related (diagnosis, symptoms, medication status) measures, and in a number of datasets, IQ and cognitive data, and medication history will also be available, allowing subgroup and dimensional analyses. Psy-ShareD will be free-to-access for all researchers. Importantly, comprehensive data catalogues, scientific support and training resources will be available to facilitate use by early career researchers and build capacity in the field. We are actively seeking new collaborators to contribute further T1 data. Collaborators will benefit in terms of authorships, as all publications arising from Psy-ShareD will include data contributors as authors.

Patient-centered brain transcriptomic and multimodal imaging determinants of clinical progression, physical activity, and treatment needs in Parkinson's disease

We continue to lack a clear understanding on how the biological and clinical complexity of Parkinson's disease emerges from molecular to macroscopic brain interactions. Here, we use personalized multiscale spatiotemporal computational brain models to characterize for the first time the synergistic links between genes, several multimodal neuroimaging-derived biological factors, clinical profiles, and therapeutic needs in PD. We identified genes modulating PD-caused brain reorganization in dopamine transporter level, neuronal activity integrity, microstructure, dendrite density and tissue atrophy. Inter-individual heterogeneity in the identified gene-mediated biological mechanisms was associated with five distinct configurations of PD motor and non-motor symptoms. Notably, the protein-protein interaction networks underlying both brain phenotypic and symptom configurations in PD revealed distinct hub genes including MYC, CCNA2, CCDK1, SRC, STAT3 and PSMD4. We also studied the biological mechanisms associated with physical activities performance, observing that leisure and work activities are strongly related to neurotypical cholesterol homeostasis and inflammatory response processes, respectively. Finally, patient-tailored in silico gene perturbations revealed a set of putative disease-modifying drugs with potential to effectively treat PD across different biological levels, most of which are associated with dopamine reuptake and anti-inflammation. Our study constitutes the first self-contained multiscale spatiotemporal computational approach providing comprehensive insights into the complex multifactorial pathogenesis of PD, unraveling key biological modulators of physical and clinical deterioration, and serving as a blueprint for optimum drug selection at personalized level.

Dysfunction in the hierarchy of morphometric similarity network in Alzheimer's disease and its correlation with cognitive performance and gene expression profiles

BACKGROUND

Previous research has shown abnormal functional network gradients in Alzheimer's disease (AD). Structural network gradient is capable of capturing continuous changes in brain morphology and has the ability to elucidate the underlying processes of neurodevelopment. However, it remains unclear whether structural network gradients are altered in AD and what associations exist between these changes and cognitive function, and gene expression profiles.

METHODS

By constructing an individualized structural network gradient decomposition framework, we calculated the morphological similarity network (MSN) gradients for 404 subjects (186 AD patients and 218 normal controls). We investigated AD-related alterations in MSN gradients, along with the associations between MSN gradients and cognitive function, MSN topological properties, and gene expression profiles.

RESULTS

Our findings indicated that the principal MSN gradient alterations in AD were primarily characterized by an increase in the primary and secondary sensory cortices and a decrease in the association cortex 1. The primary and higher-order cortices exhibited opposite associations with cognition, including executive function, language skills, and memory processes. Moreover, the principal MSN gradients were found to significantly predict cognitive function in AD. The altered gradient pattern was 14.8% attributable to gene expression profiles, and the genes demonstrating the highest correlation are involved in metabolic activity and synaptic signaling.

CONCLUSIONS

Our results offered novel insights into the underlying mechanisms of structural brain network impairment in AD patients, enhancing our understanding of the neurobiological processes responsible for impaired cognition in patients with AD, and offering a new dimensional structural biomarker for AD.

Individualized resting-state functional connectivity abnormalities unveil two major depressive disorder subtypes with contrasting abnormal patterns of abnormality

Modern neuroimaging research has recognized that major depressive disorder (MDD) is a connectome disorder, characterized by altered functional connectivity across large-scale brain networks. However, the clinical heterogeneity, likely stemming from diverse neurobiological disturbances, complicates findings from standard group comparison methods. This variability has driven the search for MDD subtypes using objective neuroimaging markers. In this study, we sought to identify potential MDD subtypes from subject-level abnormalities in functional connectivity, leveraging a large multi-site dataset of resting-state MRI from 1276 MDD patients and 1104 matched healthy controls. Subject-level extreme functional connections, determined by comparing against normative ranges derived from healthy controls using tolerance intervals, were used to identify biological subtypes of MDD. We identified a set of extreme functional connections that were predominantly between the visual network and the frontoparietal network, the default mode network and the ventral attention network, with the key regions in the anterior cingulate cortex, bilateral orbitofrontal cortex, and supramarginal gyrus. In MDD patients, these extreme functional connections were linked to age of onset and reward-related processes. Using these features, we identified two subtypes with distinct patterns of functional connectivity abnormalities compared to healthy controls (p < 0.05, Bonferroni correction). When considering all patients together, no significant differences were found. These subtypes significantly enhanced case-control discriminability and showed strong internal discriminability between subtypes. Furthermore, the subtypes were reproducible across varying parameters, study sites, and in untreated patients. Our findings provide new insights into the taxonomy and have potential implications for both diagnosis and treatment of MDD.

Radiomics-Based Differentiation of Glioblastoma and Metastatic Disease: Impact of Different T1-Contrast-Enhanced Sequences on Radiomics Features and Model Performance

BACKGROUND AND PURPOSE

Even though glioblastoma (GB) and brain metastases (BM) can be differentiated using radiomics, it remains unclear if the model performance may vary based on the contrast-enhanced sequence used. Our aim was to evaluate the radiomics-based model performance for differentiation between GB and brain metastases BM using MPRAGE and volumetric interpolated breath-hold examination (VIBE) T1-contrast-enhanced sequence.

MATERIALS AND METHODS

T1 contrast-enhanced (T1-CE) MPRAGE and VIBE sequences acquired in 108 patients (31 GBs and 77 BM) during the same MRI session were retrospectively evaluated. After standardized image preprocessing and segmentation, radiomics features were extracted from necrotic and enhancing tumor components. Pearson correlation analysis of radiomics features from tumor subcomponents was also performed. A total of 90 machine learning pipelines were evaluated using a 5-fold cross-validation. Performance was measured by mean area under the curve (AUC)-receiver operating characteristic (ROC), log loss, and Brier scores.

RESULTS

A feature-wise comparison showed that the radiomics features between sequences were strongly correlated, with the highest correlation for shape-based features. The mean AUC across the top 10 pipelines ranged between 0.851 and 0.890 with T1-CE MPRAGE and between 0.869 and 0.907 with the T1-CE VIBE sequence. The top-performing models for the MPRAGE sequence commonly used support vector machines, while those for the VIBE sequence used either support vector machines or random forest. Common feature-reduction methods for top-performing models included linear combination filter and least absolute shrinkage and selection operator for both sequences. For the same machine learning feature-reduction pipeline, model performances were comparable (AUC-ROC difference range, -0.078-0.046).

CONCLUSIONS

Radiomics features derived from T1-CE MPRAGE and VIBE sequences are strongly correlated and may have similar overall classification performance for differentiating GB from BM.

Diffusion-Weighted Magnetic Resonance Imaging: A Diagnostic Tool for Auditory (Axonal) Neuropathy

BACKGROUND

Axonal neuropathies are disorders that impair neural transmission, leading to substantial sensory deficits. In the auditory system, axonal degeneration can disrupt auditory processing, causing significant hearing difficulties. Understanding the extent of axonal degeneration and its impact on auditory function is crucial for improving diagnosis and management. This study aims to quantify axonal degeneration in the VIIIth nerve using diffusion-weighted MRI and to correlate these findings with auditory function.

METHODS

Fifty-two children and adults participated. A total of, 27 with normal hearing, 7 with cochlear hearing loss and 18 with auditory neuropathy (AN). Hearing thresholds and dMRI data was collected for all participants and the VIIIth nerve was evaluated using the fixel-based analysis metric of Apparent Fibre Density (AFD).

RESULTS

AFD was significantly lower in participants with AN compared to participants with normal hearing and cochlear hearing loss (p < 0.05). 9/18 participants with AN exhibited AFD values ≥ 2 standard deviations below the normal range. Additionally, AFD was strongly correlated with hearing thresholds in participants with no evidence of cochlear dysfunction (r = -0.776, p < 0.001), suggesting reduced auditory nerve fibre density is associated with impaired sound detection.

CONCLUSIONS

dMRI-derived AFD is a sensitive marker for axonal degeneration in the VIIIth nerve. This study provides the first in vivo evidence linking VIIIth nerve microstructure with hearing thresholds, highlighting the potential of dMRI in diagnosing and monitoring AN. The findings suggest that dMRI could be a valuable tool in clinical settings for assessing auditory nerve health and guiding treatment strategies for individuals with AN.

Myocardial perfusion SPECT radiomic features reproducibility assessment: Impact of image reconstruction and harmonization

BACKGROUND

Coronary artery disease (CAD) has one of the highest mortality rates in humans worldwide. Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) provides clinicians with myocardial metabolic information non-invasively. However, there are some limitations to interpreting SPECT images performed by physicians or automatic quantitative approaches. Radiomics analyzes images objectively by extracting quantitative features and can potentially reveal biological characteristics that the human eye cannot detect. However, the reproducibility and repeatability of some radiomic features can be highly susceptible to segmentation and imaging conditions.

PURPOSE

We aimed to assess the reproducibility of radiomic features extracted from uncorrected MPI-SPECT images reconstructed with 15 different settings before and after ComBat harmonization, along with evaluating the effectiveness of ComBat in realigning feature distributions.

MATERIALS AND METHODS

A total of 200 patients (50% normal and 50% abnormal) including rest and stress (without attenuation and scatter corrections) MPI-SPECT images were included. Images were reconstructed using 15 combinations of filter cut-off frequencies, filter orders, filter types, reconstruction algorithms, number of iterations and subsets resulting in 6000 images. Image segmentation was performed on the left ventricle in the first reconstruction for each patient and applied to 14 others. A total of 93 radiomic features were extracted from the segmented area, and ComBat was used to harmonize them. The intraclass correlation coefficient (ICC) and overall concordance correlation coefficient (OCCC) tests were performed before and after ComBat to examine the impact of each parameter on feature robustness and to assess harmonization efficiency. The ANOVA and the Kruskal-Wallis tests were performed to evaluate the effectiveness of ComBat in correcting feature distributions. In addition, the Student's t-test, Wilcoxon rank-sum, and signed-rank tests were implemented to assess the significance level of the impacts made by each parameter of different batches and patient groups (normal vs. abnormal) on radiomic features.

RESULTS

Before applying ComBat, the majority of features (ICC: 82, OCCC: 61) achieved high reproducibility (ICC/OCCC ≥ 0.900) under every batch except Reconstruction. The largest and smallest number of poor features (ICC/OCCC < 0.500) were obtained by IterationSubset and Order batches, respectively. The most reliable features were from the first-order (FO) and gray-level co-occurrence matrix (GLCM) families. Following harmonization, the minimum number of robust features increased (ICC: 84, OCCC: 78). Applying ComBat showed that Order and Reconstruction were the least and the most responsive batches, respectively. The most robust families, in a descending order, were found to be FO, neighborhood gray-tone difference matrix (NGTDM), GLCM, gray-level run length matrix (GLRLM), gray-level size zone matrix (GLSZM), and gray-level dependence matrix (GLDM) under Cut-off, Filter, and Order batches. The Wilcoxon rank-sum test showed that the number of robust features significantly differed under most batches in the Normal and Abnormal groups.

CONCLUSION

The majority of radiomic features show high levels of robustness across different OSEM reconstruction parameters in uncorrected MPI-SPECT. ComBat is effective in realigning feature distributions and enhancing radiomic features reproducibility.

Insomnia Subtypes Have Differentiating Deviations in Brain Structural Connectivity

BACKGROUND

Insomnia disorder is the most common sleep disorder. A better understanding of insomnia-related deviations in the brain could inspire better treatment. Insufficiently recognized heterogeneity within the insomnia population could obscure detection of involved brain circuits. In the current study, we investigated whether structural brain connectivity deviations differed between recently discovered and validated insomnia subtypes.

METHODS

Structural and diffusion-weighted 3T magnetic resonance imaging data from 4 independent studies were harmonized. The sample consisted of 73 control participants without sleep complaints and 204 participants with insomnia who were grouped into 5 insomnia subtypes based on their fingerprint of mood and personality traits assessed with the Insomnia Type Questionnaire. Linear regression correcting for age and sex was used to evaluate group differences in structural connectivity strength, indicated by fractional anisotropy, streamline volume density, and mean diffusivity and evaluated within 3 different atlases.

RESULTS

Insomnia subtypes showed differentiating profiles of deviating structural connectivity that were concentrated in different functional networks. Permutation testing against randomly drawn heterogeneous subsamples indicated significant specificity of deviation profiles in 4 of the 5 subtypes: highly distressed, moderately distressed reward sensitive, slightly distressed low reactive, and slightly distressed high reactive. Connectivity deviation profile significance ranged from p = .001 to p = .049 for different resolutions of brain parcellation and connectivity weight.

CONCLUSIONS

Our results provide an initial indication that different insomnia subtypes exhibit distinct profiles of deviations in structural brain connectivity. Subtyping insomnia may be essential for a better understanding of brain mechanisms that contribute to insomnia vulnerability.

The association among individual gray matter volume of frontal-limbic circuitry, fatigue susceptibility, and comorbid neuropsychiatric symptoms following COVID-19

BACKGROUND

Fatigue is often accompanied by comorbid sleep disturbance and psychiatric distress following the COVID-19 infection. However, identifying individuals at risk for developing post-COVID fatigue remains challenging. This study aimed to identify the neurobiological markers underlying fatigue susceptibility and further investigate their effect on COVID-19-related neuropsychiatric symptoms.

METHODS

Individuals following a mild SARS-CoV-2 infection (COV+) underwent neuropsychiatric measurements (n = 335) and MRI scans (n = 271) within 1 month (baseline), and 191 (70.5 %) of the individuals were followed up 3 months after infection. Sixty-seven healthy controls (COV-) completed the same recruitment protocol.

RESULTS

Whole-brain voxel-wise analysis showed that gray matter volume (GMV) during the acute phase did not differ between the COV+ and COV- groups. GMV in the right dorsolateral prefrontal cortex (DLPFC) and left dorsal anterior cingulate cortex (dACC) were associated with fatigue severity only in the COV+ group at baseline, which were assigned to the frontal system and limbic system, respectively. Furthermore, fatigue mediated the associations between volume differences in fatigue susceptibility and COVID-related sleep, post-traumatic stress disorder, anxiety and depression. Crucially, the initial GMV in the right DLPFC can predict fatigue symptoms 3 months after infection.

CONCLUSIONS

We provide novel evidence on the neuroanatomical basis of fatigue vulnerability and emphasize that acute fatigue is an important link between early GMV in the frontal-limbic regions and comorbid neuropsychiatric symptoms at baseline and 3 months after infection. Our findings highlight the role of the frontal-limbic system in predisposing individuals to develop post-COVID fatigue.

Enhancing MRI radiomics feature reproducibility and classification performance in Parkinson's disease: a harmonization approach to gray-level discretization variability

OBJECTIVE

This study aimed to assess the reproducibility of MRI-derived radiomic features across multiple gray-level discretization levels for classifying Parkinson's disease (PD) subtypes, and to evaluate the impact of ComBat harmonization on feature stability and machine learning performance.

METHODS

T1-weighted MRI scans from 140 PD patients (70 tremor-dominant, 70 postural instability gait difficulty) and 70 healthy controls were obtained from the Parkinson's progression markers initiative (PPMI) database. Radiomic features were extracted from 16 brain regions using 6 discretization levels (8, 16, 32, 64, 128, and 256 bins). ComBat harmonization was applied using a combined batch variable incorporating both scanner models and discretization levels. Intraclass correlation coefficients (ICC) and Kruskal-Wallis tests assessed feature reproducibility before and after harmonization. Support vector machine classifiers were used for PD subtype classification.

RESULTS

ComBat harmonization significantly improved feature reproducibility across all feature groups. The percentage of features showing excellent robustness (ICC ≥ 0.90) increased substantially after harmonization. The proportion of features significantly affected by discretization levels was reduced following harmonization. Classification accuracy improved dramatically, from a range of 0.42-0.49 before harmonization to 0.86-0.96 after harmonization across most discretization levels. AUC values similarly increased from 0.60-0.67 to 0.93-0.99 after harmonization.

CONCLUSIONS

ComBat harmonization significantly enhanced the reproducibility of radiomic features across discretization levels and improved PD subtype classification performance. This study highlights the importance of harmonization in radiomics research for PD and suggests potential clinical applications in personalized treatment planning.

Progression of biological markers in spinocerebellar ataxia type 3: analysis of longitudinal data from the ESMI cohort

Background

Spinocerebellar ataxia type 3 (SCA3) is an autosomal dominantly inherited adult-onset disease. We aimed to describe longitudinal changes in clinical and biological findings and to identify predictors for clinical progression.

Methods

We used data from participants enrolled in the ESMI cohort collected between Nov 09, 2016 and July 18, 2023. The data freeze included data from 14 sites in five European countries and the United States. We assessed ataxia with the Scale for the Assessment and Rating of Ataxia (SARA). We measured disease-specific mutant ataxin-3 protein (ATXN3) and neurofilament light chain (NfL) in plasma and performed MRIs. Data were analysed by regression modelling on a timescale defined by onset. The onset of abnormality of a marker was defined as the time at which its value, as determined by modelling, exceeded the mean ±2 SD of healthy controls. To study responsiveness of markers, we determined the sensitivity to change ratios (SCSs).

Results

Data from 291 SCA3 mutation carriers before and after clinical onset and 121 healthy controls were included. NfL levels became abnormal more than 20 years (-21.5 years [95% CI n.d. -9.5]) before onset. The earliest MRI abnormality was volume loss of medulla oblongata (-4.7 years [95% CI n.d. - 3.3]). The responsiveness of markers depended on the disease stage. Across all stages, pons volume had the highest responsiveness with an SCS of 1.35 [95% CI 1.11 - 1.78] exceeding that of SARA (0.99 [95% CI 0.88 - 1.11]). Lower age (p=0.0459) and lower medulla oblongata volume (p<0.0001) were predictors of SARA progression.

Conclusion

Our study provides quantitative information on the progression of biological markers in SCA3 mutation carriers before and after onset of ataxia, and allowed the identification of predictors for clinical progression. Our data could prove useful for the design of future clinical trials.

A bibliometric analysis of the top 100 most cited articles on corticospinal tract regeneration from 2004 to 2024

Objective

Here, bibliometric and visual analytical techniques were employed to assess the key features of the 100 most cited publications concerning corticospinal tract (CST) regeneration.

Methods

Research was conducted within the Web of Science Core Collection to pinpoint the 100 most cited publications on CST regeneration. From these, comprehensive data encompassing titles, authorship, key terms, publication venues, release timelines, geographic origins, and institutional affiliations were extracted, followed by an in-depth bibliometric examination.

Results

The 100 most cited publications were all published between 2004 and 2024. These seminal papers amassed an aggregate of 18,321 citations, with individual citation counts ranging from 83 to 871 and a median of 136 citations per paper. Schwab M. E., stood out as the most prominent contributor, with significant authorship in 9 of the 100 papers. The United States dominated the geographical distribution, accounting for 49 of the articles. With 17 publications, the University of California System led the institutional rankings. A thorough keyword analysis revealed pivotal themes in the field, encompassing the optic nerve, gene expression, CST integrity and regeneration, diffusion tensor imaging, myelin-associated glycoproteins, inhibitors of neurite outgrowth, and methods of electrical and intracortical microstimulation.

Conclusion

This investigation provides a bibliometric analysis of CST regeneration, underscoring the significant contribution of the United States to this field. Our findings unveiled the dynamics and trends within the field of CST regeneration, providing a scientific foundation for advancing clinical applications. Building on this analysis, the clinical application of CST regeneration should be optimized through interdisciplinary collaboration, enabling the exploration and validation of a variety of therapeutic approaches, including the use of neurotrophic factors, stem cell therapies, biomaterials, and electrical stimulation. Concurrently, additional clinical trials are necessary to test the safety and efficacy of these therapeutic methods and develop assessment tools for monitoring the recovery of patients. Furthermore, rehabilitation strategies should be refined, and professional education and training should be provided to enhance the understanding of CST regeneration treatments among both medical professionals and patients. The implementation of these strategies promises to enhance therapeutic outcomes and the quality of life of patients with spinal cord injury (SCI).

Distinguishing Early from Late Mild Cognitive Impairment Using Magnetic Resonance Free-Water Diffusion Tensor Imaging

Mild Cognitive Impairment (MCI) is a transitional stage between normal aging and Alzheimer's disease. Differentiating early MCI (EMCI) from late MCI (LMCI) is crucial for early diagnosis and intervention. This study used free-water diffusion tensor imaging (fw-DTI) to investigate white matter differences and voxel-based correlations with Mini-Mental State Examination (MMSE) scores. Data from the Alzheimer's Disease Neuroimaging Initiative included 476 healthy controls (CN), 137 EMCI participants, and 62 LMCI participants. Significant MMSE differences were found between the CN and MCI groups, but not between EMCI and LMCI. However, distinct white matter changes were observed: LMCI showed a higher f-index and lower fw-fractional anisotropy (fw-FA) compared to EMCI in several white matter regions. These findings indicate specific white matter tracts involved in MCI progression. Voxel-based correlations between fw-DTI metrics and MMSE scores further supported these results. In conclusion, this study provides crucial insights into white matter changes associated with EMCI and LMCI, offering significant implications for future research and clinical practice.

Decoding Early Psychoses: Unraveling Stable Microstructural Features Associated With Psychopathology Across Independent Cohorts

BACKGROUND

Patients with early psychosis (EP) (within 3 years after psychosis onset) show significant variability, which makes predicting outcomes challenging. Currently, little evidence exists for stable relationships between neural microstructural properties and symptom profiles across EP diagnoses, which limits the development of early interventions.

METHODS

A data-driven approach, partial least squares correlation, was used across 2 independent datasets to examine multivariate relationships between white matter properties and symptomatology and to identify stable and generalizable signatures in EP. The primary cohort included patients with EP from the Human Connectome Project for Early Psychosis (n = 124). The replication cohort included patients with EP from the Feinstein Institute for Medical Research (n = 78) as part of the MEND (Multimodal Evaluation of Neural Disorders) Project. Both samples included individuals with schizophrenia, schizoaffective disorder, and psychotic mood disorders.

RESULTS

In both cohorts, a significant latent component corresponded to a symptom profile that combined negative symptoms, primarily diminished expression, with specific somatic symptoms. Both latent components captured comprehensive features of white matter disruption, primarily a combination of subcortical and frontal association fibers. Strikingly, the partial least squares model trained on the primary cohort accurately predicted microstructural features and symptoms in the replication cohort. Findings were not driven by diagnosis, medication, or substance use.

CONCLUSIONS

This data-driven transdiagnostic approach revealed a stable and replicable neurobiological signature of microstructural white matter alterations in EP across diagnoses and datasets, showing strong covariance of these alterations with a unique profile of negative and somatic symptoms. These findings suggest the clinical utility of applying data-driven approaches to reveal symptom domains that share neurobiological underpinnings.

Neuroanatomical heterogeneity drives divergent cognitive and motor trajectories in Parkinson's disease subtypes

INTRODUCTION

Cognitive symptoms of Parkinson's disease (PD) may initially present subtly, often overshadowed by more noticeable motor symptoms. However, as PD progresses, predicting which individuals will experience significant cognitive decline becomes challenging due to variability, suggesting distinct PD subtypes with varying cognitive trajectories. This study aimed to identify early PD subtypes based on patterns of gray matter atrophy in brain regions associated with cognition and assess their distinct patterns of cognitive change over time. Recognizing PD primarily as a movement disorder, we also evaluated their motor symptoms.

METHODS

We analyzed T1-weighted MRI data, cognitive, and motor scores from 114 de novo PD patients and 120 healthy controls. Multivariate gray matter volumetric distances (MGMV) across frontal, subcortical, parietal, temporal, and occipital regions were computed, and K-means clustering was used to identify PD subtypes. Subsequently, cognitive assessments were compared between subtypes at baseline and 48 months using linear mixed-effects models and reliable change indices. Motor-symptom changes were assessed using linear mixed-effects models.

RESULTS

Two PD subtypes were identified from baseline MRI. Subtype 1 showed significantly higher MGMV in frontal (p < 0.001) and subcortical (p < 0.001) regions, indicating atrophy. At 48 months, subtype 1 had poorer global cognitive performance than subtype 2 (p = 0.005) and faster progression of postural instability and gait disturbance (p = 0.04).

CONCLUSIONS

PD subtypes identified early by distinct frontal and subcortical atrophy patterns exhibited divergent trajectories of cognitive decline and worsening motor symptoms over time, underscoring the neuroanatomical heterogeneity that drives clinical variability in PD.

Rightward brain structural asymmetry in young children with autism

To understand the neural mechanism of autism spectrum disorder (ASD) and developmental delay/intellectual disability (DD/ID) that can be associated with ASD, it is important to investigate individuals at an early stage with brain, behavioural and also genetic measures, but such research is still lacking. Here, using the cross-sectional sMRI data of 1030 children under 8 years old, we employed developmental normative models to investigate the atypical development of gray matter volume (GMV) asymmetry in individuals with ASD without DD/ID, ASD with DD/ID and individuals with only DD/ID, and their associations with behavioral and clinical measures and transcription profiles. By extracting the individual deviations of patients from the typical controls with normative models, we found a commonly abnormal pattern of GMV asymmetry across all ASD children: more rightward laterality in the inferior parietal lobe and precentral gyrus, and higher individual variability in the temporal pole. Specifically, ASD with DD/ID children showed a severer and more extensive abnormal pattern in GMV asymmetry deviation values, which was linked with both ASD symptoms and verbal IQ. The abnormal pattern of ASD without DD/ID children showed higher and more extensive individual variability, which was linked with ASD symptoms only. DD/ID children showed no significant differences from healthy population in asymmetry. Lastly, the GMV laterality patterns of all patient groups were significantly associated with both shared and unique gene expression profiles. Our findings provide evidence for rightward GMV asymmetry of some cortical regions in young ASD children (1-7 years) in a large sample (1030 cases), show that these asymmetries are related to ASD symptoms, and identify genes that are significantly associated with these differences.

Machine Learning-Based Radiomics Analysis for Identifying KRAS Mutations in Non-Small-Cell Lung Cancer from CT Images: Challenges, Insights and Implications

Kirsten Rat Sarcoma viral oncogene homolog (KRAS) is a frequently occurring mutation in non-small-cell lung cancer (NSCLC) and influences cancer treatment and disease progression. In this study, a machine learning (ML) pipeline was applied to radiomic features extracted from public and internal CT images to identify KRAS mutations in NSCLC patients. Both datasets were analyzed using parametric (t test) and non-parametric statistical tests (Mann-Whitney U test) and dimensionality reduction techniques. Afterwards, the proposed ML pipeline was applied to both datasets using a five-fold cross-validation on the training set (70/30 train/test split) before being validated on the other dataset. The results show that the radiomic features are significantly different (Mann-Whitney U test; p < 0.05) between the two datasets, despite the use of identical feature extraction methods. Model transferability is therefore difficult to achieve, which became evident during external testing (F1 score = 0.41). Oversampling, undersampling, clustering and harmonization techniques were applied to balance and harmonize the datasets, but did not improve the classification of KRAS mutation presence. In general, due to only a single moderate result (highest test F1 score = 0.67), the accuracy of KRAS prediction is not sufficient for clinical application. In future work, the complexity of KRAS mutation might be addressed by taking submutations into consideration. Larger multicentric datasets with balanced tumor stages, including multi-scanner datasets, seem to be necessary for building robust predictive models.

Impact of COVID-19 School Closures on White Matter Plasticity in the Reading Network

During the COVID-19 pandemic, children worldwide experienced school closures. Several studies have detected a negative impact on reading-related skills in children who experienced these closures during the early stages of reading instruction, but the impact on the reading network in the brain has not been investigated. In the current longitudinal study in a sample of 162 Dutch-speaking children, we found a short-term effect in the growth of phonological awareness in children with COVID-19 school closures compared to children without school closures, but no long-term effects one year later. Similarly, we did not find a long-term effect on the longitudinal development of white matter connectivity in tracts implicated during early reading development. Together, these findings indicate that one year after school closures no effects on the development of phonological awareness and white matter are found, yet it remains an open question whether short-term effects on the reading network could have been present and/or whether other networks (e.g., psychosocial related networks) are potentially more affected.