Multimodal neuroimaging computing: a review of the applications in neuropsychiatric disorders

Abundant pleiotropy across neuroimaging modalities identified through a multivariate genome-wide association study

Genetic pleiotropy is abundant across spatially distributed brain characteristics derived from one neuroimaging modality (e.g. structural, functional or diffusion magnetic resonance imaging [MRI]). A better understanding of pleiotropy across modalities could inform us on the integration of brain function, micro- and macrostructure. Here we show extensive genetic overlap across neuroimaging modalities at a locus and gene level in the UK Biobank (N = 34,029) and ABCD Study (N = 8607). When jointly analysing phenotypes derived from structural, functional and diffusion MRI in a genome-wide association study (GWAS) with the Multivariate Omnibus Statistical Test (MOSTest), we boost the discovery of loci and genes beyond previously identified effects for each modality individually. Cross-modality genes are involved in fundamental biological processes and predominantly expressed during prenatal brain development. We additionally boost prediction of psychiatric disorders by conditioning independent GWAS on our multimodal multivariate GWAS. These findings shed light on the shared genetic mechanisms underlying variation in brain morphology, functional connectivity, and tissue composition.

Neuroimmune activation and increased brain aging in chronic pain patients after the COVID-19 pandemic onset

The COVID-19 pandemic has exerted a global impact on both physical and mental health, and clinical populations have been disproportionally affected. To date, however, the mechanisms underlying the deleterious effects of the pandemic on pre-existing clinical conditions remain unclear. Here we investigated whether the onset of the pandemic was associated with an increase in brain/blood levels of inflammatory markers and MRI-estimated brain age in patients with chronic low back pain (cLBP), irrespective of their infection history. A retrospective cohort study was conducted on 56 adult participants with cLBP (28 'Pre-Pandemic', 28 'Pandemic') using integrated Positron Emission Tomography/ Magnetic Resonance Imaging (PET/MRI) and the radioligand [11C]PBR28, which binds to the neuroinflammatory marker 18 kDa Translocator Protein (TSPO). Image data were collected between November 2017 and January 2020 ('Pre-Pandemic' cLBP) or between August 2020 and May 2022 ('Pandemic' cLBP). Compared to the Pre-Pandemic group, the Pandemic patients demonstrated widespread and statistically significant elevations in brain TSPO levels (P =.05, cluster corrected). PET signal elevations in the Pandemic group were also observed when 1) excluding 3 Pandemic subjects with a known history of COVID infection, or 2) using secondary outcome measures (volume of distribution -VT- and VT ratio - DVR) in a smaller subset of participants. Pandemic subjects also exhibited elevated serum levels of inflammatory markers (IL-16; P <.05) and estimated BA (P <.0001), which were positively correlated with [11C]PBR28 SUVR (r's ≥ 0.35; P's < 0.05). The pain interference scores, which were elevated in the Pandemic group (P <.05), were negatively correlated with [11C]PBR28 SUVR in the amygdala (r = -0.46; P<.05). This work suggests that the pandemic outbreak may have been accompanied by neuroinflammation and increased brain age in cLBP patients, as measured by multimodal imaging and serum testing. This study underscores the broad impact of the pandemic on human health, which extends beyond the morbidity solely mediated by the virus itself.

A Comprehensive Review of Sonographic Assessment of Peripheral Slow-Flow Vascular Malformations

This comprehensive review explores the role of sonographic assessment in diagnosing and characterizing peripheral slow-flow vascular malformations (PSFVM). The review begins with an introduction providing the background and significance of PSFVM, defining these vascular anomalies, and emphasizing the importance of sonography in their diagnosis. The objectives focus on a thorough examination of existing literature, assessing the effectiveness of sonography in delineating morphological and hemodynamic features crucial for accurate classification. The summary of key findings highlights the diagnostic accuracy of sonography while acknowledging its limitations. Implications for clinical practice emphasize the practical utility of sonography in early diagnosis and preoperative planning, suggesting integration into multimodal approaches. The conclusion underscores the need for standardized criteria, ongoing education, and future research, positioning sonography as a valuable tool in the comprehensive management of PSFVM.

Early prediction of dementia using fMRI data with a graph convolutional network approach

Objective. Alzheimer's disease is a progressive neurodegenerative dementia that poses a significant global health threat. It is imperative and essential to detect patients in the mild cognitive impairment (MCI) stage or even earlier, enabling effective interventions to prevent further deterioration of dementia. This study focuses on the early prediction of dementia utilizing Magnetic Resonance Imaging (MRI) data, using the proposed Graph Convolutional Networks (GCNs).Approach. Specifically, we developed a functional connectivity (FC) based GCN framework for binary classifications using resting-state fMRI data. We explored different types and processing methods of FC and evaluated the performance on the OASIS-3 dataset. We developed the GCN model for two different purposes: (1) MCI diagnosis: classifying MCI from normal controls (NCs); and (2) dementia risk prediction: classifying NCs from subjects who have the potential for developing MCI but have not been clinically diagnosed as MCI.Main results. The results of the experiments revealed several important findings: First, the proposed GCN outperformed both the baseline GCN and Support Vector Machine (SVM). It achieved the best average accuracy of 80.3% (11.7% higher than the baseline GCN and 23.5% higher than SVM) and the highest accuracy of 91.2%. Secondly, the GCN framework with (absolute) individual FC performed slightly better than that with global FC generally. However, GCN using global graphs with appropriate connectivity can achieve equivalent or superior performance to individual graphs in some cases, which highlights the significance of suitable connectivity for achieving performance. Additionally, the results indicate that the self-network connectivity of specific brain network regions (such as default mode network, visual network, ventral attention network and somatomotor network) may play a more significant role in GCN classification.Significance. Overall, this study offers valuable insights into the application of GCNs in brain analysis and early diagnosis of dementia. This contributes significantly to the understanding of MCI and has substantial potential for clinical applications in early diagnosis and intervention for dementia and other neurodegenerative diseases. Our code for GCN implementation is available at:https://github.com/Shuning-Han/FC-based-GCN.

Cocaine Use Prediction With Tensor-Based Machine Learning on Multimodal MRI Connectome Data

This letter considers the use of machine learning algorithms for predicting cocaine use based on magnetic resonance imaging (MRI) connectomic data. The study used functional MRI (fMRI) and diffusion MRI (dMRI) data collected from 275 individuals, which was then parcellated into 246 regions of interest (ROIs) using the Brainnetome atlas. After data preprocessing, the data sets were transformed into tensor form. We developed a tensor-based unsupervised machine learning algorithm to reduce the size of the data tensor from 275 (individuals) × 2 (fMRI and dMRI) × 246 (ROIs) × 246 (ROIs) to 275 (individuals) × 2 (fMRI and dMRI) × 6 (clusters) × 6 (clusters). This was achieved by applying the high-order Lloyd algorithm to group the ROI data into six clusters. Features were extracted from the reduced tensor and combined with demographic features (age, gender, race, and HIV status). The resulting data set was used to train a Catboost model using subsampling and nested cross-validation techniques, which achieved a prediction accuracy of 0.857 for identifying cocaine users. The model was also compared with other models, and the feature importance of the model was presented. Overall, this study highlights the potential for using tensor-based machine learning algorithms to predict cocaine use based on MRI connectomic data and presents a promising approach for identifying individuals at risk of substance abuse.

Chromatic fusion: Generative multimodal neuroimaging data fusion provides multi-informed insights into schizophrenia

This work proposes a novel generative multimodal approach to jointly analyze multimodal data while linking the multimodal information to colors. We apply our proposed framework, which disentangles multimodal data into private and shared sets of features from pairs of structural (sMRI), functional (sFNC and ICA), and diffusion MRI data (FA maps). With our approach, we find that heterogeneity in schizophrenia is potentially a function of modality pairs. Results show (1) schizophrenia is highly multimodal and includes changes in specific networks, (2) non-linear relationships with schizophrenia are observed when interpolating among shared latent dimensions, and (3) we observe a decrease in the modularity of functional connectivity and decreased visual-sensorimotor connectivity for schizophrenia patients for the FA-sFNC and sMRI-sFNC modality pairs, respectively. Additionally, our results generally indicate decreased fractional corpus callosum anisotropy, and decreased spatial ICA map and voxel-based morphometry strength in the superior frontal lobe as found in the FA-sFNC, sMRI-FA, and sMRI-ICA modality pair clusters. In sum, we introduce a powerful new multimodal neuroimaging framework designed to provide a rich and intuitive understanding of the data which we hope challenges the reader to think differently about how modalities interact.

Bridging the Gap between Basic Research and Clinical Practice: The Growing Role of Translational Neurorehabilitation

Translational neuroscience is intended as a holistic approach in the field of brain disorders, starting from the basic research of cerebral morphology and with the function of implementing it into clinical practice. This concept can be applied to the rehabilitation field to promote promising results that positively influence the patient's quality of life. The last decades have seen great scientific and technological improvements in the field of neurorehabilitation. In this paper, we discuss the main issues related to translational neurorehabilitation, from basic research to current clinical practice, and we also suggest possible future scenarios.

A Transcriptomic Atlas of the Human Brain Reveals Genetically Determined Aspects of Neuropsychiatric Health

Imaging features associated with neuropsychiatric traits can provide valuable insights into underlying pathophysiology. Using data from the UK biobank, we perform tissue-specific TWAS on over 3,500 neuroimaging phenotypes to generate a publicly accessible resource detailing the neurophysiologic consequences of gene expression. As a comprehensive catalog of neuroendophenotypes, this resource represents a powerful neurologic gene prioritization schema that can improve our understanding of brain function, development, and disease. We show that our approach generates reproducible results in internal and external replication datasets. Notably, genetically determined expression alone is shown here to enable high-fidelity reconstruction of brain structure and organization. We demonstrate complementary benefits of cross-tissue and single-tissue analyses towards an integrated neurobiology and provide evidence that gene expression outside the central nervous system provides unique insights into brain health. As an application, we show that over 40% of genes previously associated with schizophrenia in the largest GWAS meta-analysis causally affect neuroimaging phenotypes noted to be altered in schizophrenic patients.

A revisit of the amygdala theory of autism: Twenty years after

The human amygdala has long been implicated to play a key role in autism spectrum disorder (ASD). Yet it remains unclear to what extent the amygdala accounts for the social dysfunctions in ASD. Here, we review studies that investigate the relationship between amygdala function and ASD. We focus on studies that employ the same task and stimuli to directly compare people with ASD and patients with focal amygdala lesions, and we also discuss functional data associated with these studies. We show that the amygdala can only account for a limited number of deficits in ASD (primarily face perception tasks but not social attention tasks), a network view is, therefore, more appropriate. We next discuss atypical brain connectivity in ASD, factors that can explain such atypical brain connectivity, and novel tools to analyze brain connectivity. Lastly, we discuss new opportunities from multimodal neuroimaging with data fusion and human single-neuron recordings that can enable us to better understand the neural underpinnings of social dysfunctions in ASD. Together, the influential amygdala theory of autism should be extended with emerging data-driven scientific discoveries such as machine learning-based surrogate models to a broader framework that considers brain connectivity at the global scale.

fMRI BOLD and MEG theta power reflect complementary aspects of activity during lexicosemantic decision in adolescents with ASD

Neuroimaging studies of autism spectrum disorder (ASD) have been predominantly unimodal. While many fMRI studies have reported atypical activity patterns for diverse tasks, the MEG literature in ASD remains comparatively small. Our group recently reported atypically increased event-related theta power in individuals with ASD during lexicosemantic processing. The current multimodal study examined the relationship between fMRI BOLD signal and anatomically-constrained MEG (aMEG) theta power. Thirty-three adolescents with ASD and 23 typically developing (TD) peers took part in both fMRI and MEG scans, during which they distinguished between standard words (SW), animal words (AW), and pseudowords (PW). Regions-of-interest (ROIs) were derived based on task effects detected in BOLD signal and aMEG theta power. BOLD signal and theta power were extracted for each ROI and word condition. Compared to TD participants, increased theta power in the ASD group was found across several time windows and regions including left fusiform and inferior frontal, as well as right angular and anterior cingulate gyri, whereas BOLD signal was significantly increased in the ASD group only in right anterior cingulate gyrus. No significant correlations were observed between BOLD signal and theta power. Findings suggest that the common interpretation of increases in BOLD signal and theta power as 'activation' require careful differentiation, as these reflect largely distinct aspects of regional brain activity. Some group differences in dynamic neural processing detected with aMEG that are likely relevant for lexical processing may be obscured by the hemodynamic signal source and low temporal resolution of fMRI.

Machine learning models to predict neuropsychiatric disorders in various brain tumors

OBJECTIVE

Neuropsychiatric disorders in brain tumor patients are commonly observed. It is difficult to anticipate these disorders in different types of brain tumors. The goal of the study was to see how well machine learning (ML)-based decision algorithms might predict neuropsychiatric problems in different types of brain tumors.

METHODS

145 histopathologically-confirmed primary brain tumors of both gender aged 25-65 years of age, were included for neuropsychiatric assessments. The datasets of brain tumor patients were employed for building the models. Four different decision ML classification trees/models (J48, Random Forest, Random Tree & Hoeffding Tree) with supervised learning were trained, tested, and validated on class labeled data of brain tumor patients. The models were compared in order to determine the best accurate classifier in predicting neuropsychiatric problems in various brain tumors. Following categorical attributes as independent variables (predictors) were included from the data of brain tumor patients: age, gender, depression, dementia, and brain tumor types. With the machine learning decision tree/model techniques, a multi-target classification was performed with classes of neuropsychiatric diseases that were predicted from the selected attributes.

RESULTS

86 percent of patients were depressed, and 55 percent were suffering from dementia. Anger was the most often reported neuropsychiatric condition in brain tumor patients (92.41%), followed by sleep disorders (83%), apathy (80%), and mood swings (76.55%). When compared to other tumor types, glioblastoma patients had a higher rate of depression (20%) and dementia (20.25%). The developed models Random Forest and Random Tree were found successful with an accuracy of up to 94% (10-folds) for the prediction of neuropsychiatric disorders in brain tumor patients. The multiclass target (neuropsychiatric ailments) accuracies were having good measures of precision (0.9-1.0), recall (0.9-1.0), F-measure (0.9-1.0), and ROC area (0.9-1.0) in decision models.

CONCLUSION

Random Forest Trees can be used to accurately predict neuropsychiatric illnesses. Based on the model output, the ML-decision trees will aid the physician in pre-diagnosing the mental issue and deciding on the best therapeutic approach to avoid subsequent neuropsychiatric issues in brain tumor patients.

Neonatal multi-modal cortical profiles predict 18-month developmental outcomes

Developmental delays in infanthood often persist, turning into life-long difficulties, and coming at great cost for the individual and community. By examining the developing brain and its relation to developmental outcomes we can start to elucidate how the emergence of brain circuits is manifested in variability of infant motor, cognitive and behavioural capacities. In this study, we examined if cortical structural covariance at birth, indexing coordinated development, is related to later infant behaviour. We included 193 healthy term-born infants from the Developing Human Connectome Project (dHCP). An individual cortical connectivity matrix derived from morphological and microstructural features was computed for each subject (morphometric similarity networks, MSNs) and was used as input for the prediction of behavioural scores at 18 months using Connectome-Based Predictive Modeling (CPM). Neonatal MSNs successfully predicted social-emotional performance. Predictive edges were distributed between and within known functional cortical divisions with a specific important role for primary and posterior cortical regions. These results reveal that multi-modal neonatal cortical profiles showing coordinated maturation are related to developmental outcomes and that network organization at birth provides an early infrastructure for future functional skills.

Multimodal data integration via mediation analysis with high-dimensional exposures and mediators

Motivated by an imaging proteomics study for Alzheimer's disease (AD), in this article, we propose a mediation analysis approach with high‐dimensional exposures and high‐dimensional mediators to integrate data collected from multiple platforms. The proposed method combines principal component analysis with penalized least squares estimation for a set of linear structural equation models. The former reduces the dimensionality and produces uncorrelated linear combinations of the exposure variables, whereas the latter achieves simultaneous path selection and effect estimation while allowing the mediators to be correlated. Applying the method to the AD data identifies numerous interesting protein peptides, brain regions, and protein–structure–memory paths, which are in accordance with and also supplement existing findings of AD research. Additional simulations further demonstrate the effective empirical performance of the method.

Functional brain activity constrained by structural connectivity reveals cohort-specific features for serum neurofilament light chain

Background

Neuro-axonal brain damage releases neurofilament light chain (NfL) proteins, which enter the blood. Serum NfL has recently emerged as a promising biomarker for grading axonal damage, monitoring treatment responses, and prognosis in neurological diseases. Importantly, serum NfL levels also increase with aging, and the interpretation of serum NfL levels in neurological diseases is incomplete due to lack of a reliable model for age-related variation in serum NfL levels in healthy subjects.

Methods

Graph signal processing (GSP) provides analytical tools, such as graph Fourier transform (GFT), to produce measures from functional dynamics of brain activity constrained by white matter anatomy. Here, we leveraged a set of features using GFT that quantified the coupling between blood oxygen level dependent signals and structural connectome to investigate their associations with serum NfL levels collected from healthy subjects and former athletes with history of concussions.

Results

Here we show that GSP feature from isthmus cingulate in the right hemisphere (r-iCg) is strongly linked with serum NfL in healthy controls. In contrast, GSP features from temporal lobe and lingual areas in the left hemisphere and posterior cingulate in the right hemisphere are the most associated with serum NfL in former athletes. Additional analysis reveals that the GSP feature from r-iCg is associated with behavioral and structural measures that predict aggressive behavior in healthy controls and former athletes.

Conclusions

Our results suggest that GSP-derived brain features may be included in models of baseline variance when evaluating NfL as a biomarker of neurological diseases and studying their impact on personality traits.

Neurofilament light chain (NfL) is a marker released into the blood as a result of central nervous system damage or neurodegeneration. However, we know little about how NfL levels relate to brain structure and activity. Here, we use imaging data and advanced statistical methods to look at the relationship between brain activity and structure in healthy people and former athletes with a history of multiple concussions, and determine whether these can predict NfL levels in the blood. We find the relationship between brain activity and structure and NfL levels is different between the two groups. Our findings help us to understand how brain injury might impact NfL levels and their relationship with brain activity, and could guide how NfL and imaging data are used as tools in research and in the clinic.

Sihag et al. analyse brain imaging data, circulating neurofilament light chain levels and personality scores in a cohort of former athletes with a history of concussions. The authors use graph signal processing to identify brain structural and connectivity features associated with neurofilament levels and with aggressive behaviour.

Psychopathy in women: insights from neuroscience and ways forward for research

Psychopathy is a severe form of personality disturbance, resulting in a detrimental impact on individuals, healthcare systems, and society as a whole. Until relatively recently, most research in psychopathy has focused on male samples, not least because of its link with criminal behavior and the large proportion of violent crime committed by men. However, psychopathy in women also leads to considerable problems at an individual and societal level, including substance misuse, poor treatment outcomes, and contribution to ever-increasing numbers of female prisoners. Despite this, due to relative neglect, most research into adult female psychopathy is underpowered and outdated. We argue that the field needs revitalizing, with a focus on the developmental nature of the condition and neurocognitive research. Recent work international consortia into conduct disorder in female youth-a precursor of psychopathy in female adults-gives cause for optimism. Here, we outline key strategies for enriching research in this important field with contemporary approaches to other psychiatric conditions.

From Picoscale Pathology to Decascale Disease: Image Registration with a Scattering Transform and Varifolds for Manipulating Multiscale Data

Advances in neuroimaging have yielded extensive variety in the scale and type of data available. Effective integration of such data promises deeper understanding of anatomy and disease-with consequences for both diagnosis and treatment. Often catered to particular datatypes or scales, current computational tools and mathematical frameworks remain inadequate for simultaneously registering these multiple modes of "images" and statistically analyzing the ensuing menagerie of data. Here, we present (1) a registration algorithm using a "scattering transform" to align high and low resolution images and (2) a varifold-based modeling framework to compute 3D spatial statistics of multiscale data. We use our methods to quantify microscopic tau pathology across macroscopic 3D regions of the medial temporal lobe to address a major challenge in the diagnosis of Alzheimer's Disease-the reliance on invasive methods to detect microscopic pathology.

Safety and data quality of EEG recorded simultaneously with multi-band fMRI

PURPOSE

Simultaneously recorded electroencephalography and functional magnetic resonance imaging (EEG-fMRI) is highly informative yet technically challenging. Until recently, there has been little information about EEG data quality and safety when used with newer multi-band (MB) fMRI sequences. Here, we measure the relative heating of a MB protocol compared with a standard single-band (SB) protocol considered to be safe. We also evaluated EEG quality recorded concurrently with the MB protocol on humans.

MATERIALS AND METHODS

We compared radiofrequency (RF)-related heating at multiple electrodes and magnetic field magnitude, B1+RMS, of a MB fMRI sequence with whole-brain coverage (TR = 440 ms, MB factor = 4) against a previously recommended, safe SB sequence using a phantom outfitted with a 64-channel EEG cap. Next, 9 human subjects underwent eyes-closed resting state EEG-fMRI using the MB sequence. Additionally, in three of the subjects resting state EEG was recorded also during the SB sequence and in an fMRI-free condition to directly compare EEG data quality across scanning conditions. EEG data quality was assessed by the ability to remove gradient and cardioballistic artifacts along with a clean spectrogram.

RESULTS

The heating induced by the MB sequence was lower than that of the SB sequence by a factor of 0.73 ± 0.38. This is consistent with an expected heating ratio of 0.64, calculated from the square of the ratio of B1+RMS values of the sequences. In the resting state EEG data, gradient and cardioballistic artifacts were successfully removed using traditional template subtraction. All subjects showed an individual alpha peak in the spectrogram with a posterior topography characteristic of eyes-closed EEG. The success of artifact rejection for the MB sequence was comparable to that in traditional SB sequences.

CONCLUSIONS

Our study shows that B1+RMS is a useful indication of the relative heating of fMRI protocols. This observation indicates that simultaneous EEG-fMRI recordings using this MB sequence can be safe in terms of RF-related heating, and that EEG data recorded using this sequence is of acceptable quality after traditional artifact removal techniques.

Proof-of-concept evidence for trimodal simultaneous investigation of human brain function

The link between spatial (where) and temporal (when) aspects of the neural correlates of most psychological phenomena is not clear. Elucidation of this relation, which is crucial to fully understand human brain function, requires integration across multiple brain imaging modalities and cognitive tasks that reliably modulate the engagement of the brain systems of interest. By overcoming the methodological challenges posed by simultaneous recordings, the present report provides proof‐of‐concept evidence for a novel approach using three complementary imaging modalities: functional magnetic resonance imaging (fMRI), event‐related potentials (ERPs), and event‐related optical signals (EROS). Using the emotional oddball task, a paradigm that taps into both cognitive and affective aspects of processing, we show the feasibility of capturing converging and complementary measures of brain function that are not currently attainable using traditional unimodal or other multimodal approaches. This opens up unprecedented possibilities to clarify spatiotemporal integration of brain function.

Light-weight cross-view hierarchical fusion network for joint localization and identification in Alzheimer's disease with adaptive instance-declined pruning

Magnetic resonance imaging (MRI) has been widely used in assessing development of Alzheimer's disease (AD) by providing structural information of disease-associated regions (e.g. atrophic regions). In this paper, we propose a light-weight cross-view hierarchical fusion network (CvHF-net), consisting of local patch and global subject subnets, for joint localization and identification of the discriminative local patches and regions in the whole brain MRI, upon which feature representations are then jointly learned and fused to construct hierarchical classification models for AD diagnosis. Firstly, based on the extracted class-discriminative 3D patches, we employ the local patch subnets to utilize multiple 2D views to represent 3D patches by using an attention-aware hierarchical fusion structure in a divide-and-conquer manner. Since different local patches are with various abilities in AD identification, the global subject subnet is developed to bias the allocation of available resources towards the most informative parts among these local patches to obtain global information for AD identification. Besides, an instance declined pruning algorithm is embedded in the CvHF-net for adaptively selecting most discriminant patches in a task-driven manner. The proposed method was evaluated on the AD Neuroimaging Initiative dataset and the experimental results show that our proposed method can achieve good performance on AD diagnosis.

Strategies to solve the reverse inference fallacy in future MRI studies of schizophrenia: a review

Few advances in schizophrenia research have been translated into clinical practice, despite 60 years of serum biomarkers studies and 50 years of genetic studies. During the last 30 years, neuroimaging studies on schizophrenia have gradually increased, partly due to the beautiful prospect that the pathophysiology of schizophrenia could be explained entirely by the Human Connectome Project (HCP). However, the fallacy of reverse inference has been a critical problem of the HCP. For this reason, there is a dire need for new strategies or research "bridges" to further schizophrenia at the biological level. To understand the importance of research "bridges," it is vital to examine the strengths and weaknesses of the recent literature. Hence, in this review, our team has summarized the recent literature (1995-2018) about magnetic resonance imaging (MRI) of schizophrenia in terms of regional and global structural and functional alterations. We have also provided a new proposal that may supplement the HCP for studying schizophrenia. As postulated, despite the vast number of MRI studies in schizophrenia, the lack of homogeneity between the studies, along with the relatedness of schizophrenia with other neurological disorders, has hindered the study of schizophrenia. In addition, the reverse inference cannot be used to diagnose schizophrenia, further limiting the clinical impact of findings from medical imaging studies. We believe that multidisciplinary technologies may be used to develop research "bridges" to further investigate schizophrenia at the single neuron or neuron cluster levels. We have postulated about future strategies for overcoming the current limitations and establishing the research "bridges," with an emphasis on multimodality imaging, molecular imaging, neuron cluster signals, single transmitter biomarkers, and nanotechnology. These research "bridges" may help solve the reverse inference fallacy and improve our understanding of schizophrenia for future studies.

The activity and connectivity of the facial emotion processing neural circuitry in bipolar disorder: a systematic review

BACKGROUND

Facial emotion processing abnormalities may be a trait feature of bipolar disorder (BD). These social cognitive impairments may be due to alterations in the neural processing of facial affective information in visual ("core"), and limbic and prefrontal ("extended") networks, however, the precise neurobiological mechanism(s) underlying these symptoms are unclear.

METHODS

We conducted a systematic review to appraise the literature on the activity and connectivity of the facial emotion processing neural circuitry in BD. Two reviewers undertook a search of the electronic databases PubMed, Scopus and PsycINFO, to identify relevant literature published since inception up until September 2019. Study eligibility criteria included; BD participants, neuroimaging, and facial emotion processing tasks.

RESULTS

Out of an initial yield of 6121 articles, 66 were eligible for inclusion in this review. We identified differences in neural activity and connectivity within and between occipitotemporal, limbic, and prefrontal regions, in response to facial affective stimuli, in BD compared to healthy controls.

LIMITATIONS

The methodologies used across studies varied considerably.

CONCLUSIONS

The findings from this review suggest abnormalities in both the activity and connectivity of facial emotion processing neural circuitry in BD. It is recommended that future research aims to further define the connectivity and spatiotemporal course of neural events within and between occipitotemporal, limbic, and prefrontal regions.

Hallucination-Specific structure-function associations in schizophrenia

Combining structural (sMRI) and functional magnetic resonance imaging (fMRI) data in schizophrenia patients with and without auditory hallucinations (9 SZ_AVH, 12 SZ_nAVH), 18 patients with bipolar disorder, and 22 healthy controls, we examined whether cortical thinning was associated with abnormal activity in functional brain networks associated with auditory hallucinations. Language-task fMRI data were combined with mean cortical thickness values from 148 brain regions in a constrained principal component analysis (CPCA) to identify brain structure-function associations predictable from group differences. Two components emerged from the multimodal analysis. The "AVH component" highlighted an association of frontotemporal and cingulate thinning with altered brain activity characteristic of hallucinations among patients with AVH. In contrast, the "Bipolar component" distinguished bipolar patients from healthy controls and linked increased activity in the language network with cortical thinning in the left occipital-temporal lobe. Our findings add to a body of evidence of the biological underpinnings of hallucinations and illustrate a method for multimodal data analysis of structure-function associations in psychiatric illness.

Application of deep learning in detecting neurological disorders from magnetic resonance images: a survey on the detection of Alzheimer's disease, Parkinson's disease and schizophrenia

Neuroimaging, in particular magnetic resonance imaging (MRI), has been playing an important role in understanding brain functionalities and its disorders during the last couple of decades. These cutting-edge MRI scans, supported by high-performance computational tools and novel ML techniques, have opened up possibilities to unprecedentedly identify neurological disorders. However, similarities in disease phenotypes make it very difficult to detect such disorders accurately from the acquired neuroimaging data. This article critically examines and compares performances of the existing deep learning (DL)-based methods to detect neurological disorders-focusing on Alzheimer's disease, Parkinson's disease and schizophrenia-from MRI data acquired using different modalities including functional and structural MRI. The comparative performance analysis of various DL architectures across different disorders and imaging modalities suggests that the Convolutional Neural Network outperforms other methods in detecting neurological disorders. Towards the end, a number of current research challenges are indicated and some possible future research directions are provided.

Multimodal dopamine transporter (DAT) imaging and magnetic resonance imaging (MRI) to characterise early Parkinson's disease

Idiopathic Parkinson's disease (PD), the second most common neurodegenerative disorder, is characterised by the progressive loss of dopaminergic nigrostriatal terminals. Currently, in early idiopathic PD, dopamine transporter (DAT)-specific imaging assesses the extent of striatal dopaminergic deficits, and conventional magnetic resonance imaging (MRI) of the brain excludes the presence of significant ischaemic load in the basal ganglia as well as signs indicative of other forms of Parkinsonism. In this article, we discuss the use of multimodal DAT-specific and MRI protocols for insight into the early pathological features of idiopathic PD, including: structural MRI, diffusion tensor imaging, nigrosomal iron imaging and neuromelanin-sensitive MRI sequences. These measures may be acquired serially or simultaneously in a hybrid scanner. From current evidence, it appears that both nigrosomal iron imaging and neuromelanin-sensitive MRI combined with DAT-specific imaging are useful to assist clinicians in diagnosing PD, while conventional structural MRI and diffusion tensor imaging protocols are better suited to a research context focused on characterising early PD pathology. We believe that in the future multimodal imaging will be able to characterise prodromal PD and stratify the clinical stages of PD progression.

Towards a brain-based predictome of mental illness

Neuroimaging-based approaches have been extensively applied to study mental illness in recent years and have deepened our understanding of both cognitively healthy and disordered brain structure and function. Recent advancements in machine learning techniques have shown promising outcomes for individualized prediction and characterization of patients with psychiatric disorders. Studies have utilized features from a variety of neuroimaging modalities, including structural, functional, and diffusion magnetic resonance imaging data, as well as jointly estimated features from multiple modalities, to assess patients with heterogeneous mental disorders, such as schizophrenia and autism. We use the term "predictome" to describe the use of multivariate brain network features from one or more neuroimaging modalities to predict mental illness. In the predictome, multiple brain network-based features (either from the same modality or multiple modalities) are incorporated into a predictive model to jointly estimate features that are unique to a disorder and predict subjects accordingly. To date, more than 650 studies have been published on subject-level prediction focusing on psychiatric disorders. We have surveyed about 250 studies including schizophrenia, major depression, bipolar disorder, autism spectrum disorder, attention-deficit hyperactivity disorder, obsessive-compulsive disorder, social anxiety disorder, posttraumatic stress disorder, and substance dependence. In this review, we present a comprehensive review of recent neuroimaging-based predictomic approaches, current trends, and common shortcomings and share our vision for future directions.

A multimodal neuroimaging classifier for alcohol dependence

With progress in magnetic resonance imaging technology and a broader dissemination of state-of-the-art imaging facilities, the acquisition of multiple neuroimaging modalities is becoming increasingly feasible. One particular hope associated with multimodal neuroimaging is the development of reliable data-driven diagnostic classifiers for psychiatric disorders, yet previous studies have often failed to find a benefit of combining multiple modalities. As a psychiatric disorder with established neurobiological effects at several levels of description, alcohol dependence is particularly well-suited for multimodal classification. To this aim, we developed a multimodal classification scheme and applied it to a rich neuroimaging battery (structural, functional task-based and functional resting-state data) collected in a matched sample of alcohol-dependent patients (N = 119) and controls (N = 97). We found that our classification scheme yielded 79.3% diagnostic accuracy, which outperformed the strongest individual modality – grey-matter density – by 2.7%. We found that this moderate benefit of multimodal classification depended on a number of critical design choices: a procedure to select optimal modality-specific classifiers, a fine-grained ensemble prediction based on cross-modal weight matrices and continuous classifier decision values. We conclude that the combination of multiple neuroimaging modalities is able to moderately improve the accuracy of machine-learning-based diagnostic classification in alcohol dependence.

Neuroimaging insights into the link between depression and Insomnia: A systematic review

BACKGROUND

Insomnia is a common symptom of Major Depressive Disorder (MDD) and genome-wide association studies pointed to their strong genetic association. Although the prevalence of insomnia symptoms in MDD is noticeable and evidence supports their strong bidirectional association, the number of available neuroimaging findings on patients of MDD with insomnia symptoms is limited. However, such neuroimaging studies could verily improve our understanding of their shared pathophysiology and advance corresponding theories.

METHODS

Based on the preferred reporting items for systematic reviews and meta-analysis (PRISMA) guideline, we have conducted a literature search using PubMed, EMBASE, and Scopus databases and systematically explored 640 studies using various neuroimaging modalities in MDD patients with different degrees of insomnia symptoms.

RESULTS

Despite inconsistencies, current findings from eight studies suggested structural and functional disturbances in several brain regions including the amygdala, prefrontal cortex and anterior cingulate cortex and insula. The aberrant functional connectivity within and between the main hubs of the salience and default mode networks could potentially yield new insights into the link between MDD and insomnia, which needs further assessment.

LIMITATIONS

The number of studies reviewed herein is limited. The applied methods for assessing structural and functional neural mechanisms of insomnia and depression were variable.

CONCLUSION

Neuroimaging methods demonstrated the overlapping underlying neural mechanisms between MDD and insomnia. Future studies may facilitate better understanding of their pathophysiology to allow development of specific treatment.

Synthesizing diffusion tensor imaging from functional MRI using fully convolutional networks

PURPOSE

Medical image synthesis can simulate a target modality of interest based on existing modalities and has the potential to save scanning time while contributing to efficient data collection. This study proposed a three-dimensional (3D) deep learning architecture based on a fully convolutional network (FCN) to synthesize diffusion-tensor imaging (DTI) from resting-state functional magnetic resonance imaging (fMRI).

METHODS

fMRI signals derived from white matter (WM) exist and can be used for assessing WM alterations. We constructed an initial functional correlation tensor image using the correlation patterns of adjacent fMRI voxels as one input to the FCN. We considered T1-weighted images as an additional input to provide an algorithm with the structural information needed to synthesize DTI. Our architecture was trained and tested using a large-scale open database dataset (training n = 648; testing n = 293).

RESULTS

The average correlation value between synthesized and actual diffusion tensors for 38 WM regions was 0.808, which significantly improves upon an existing study (r = 0.480). We also validated our approach using two open databases. Our proposed method showed a higher correlation with the actual diffusion tensor than the conventional machine-learning method for many WM regions.

CONCLUSIONS

Our method synthesized DTI images from fMRI images using a 3D FCN architecture. We hope to expand our method of synthesizing various other imaging modalities from a single image source.

Learning using privileged information improves neuroimaging-based CAD of Alzheimer's disease: a comparative study

The neuroimaging-based computer-aided diagnosis (CAD) for Alzheimer's disease (AD) has shown its effectiveness in recent years. In general, the multimodal neuroimaging-based CAD always outperforms the approaches based on a single modality. However, single-modal neuroimaging is more favored in clinical practice for diagnosis due to the limitations of imaging devices, especially in rural hospitals. Learning using privileged information (LUPI) is a new learning paradigm that adopts additional privileged information (PI) modality to help to train a more effective learning model during the training stage, but PI itself is not available in the testing stage. Since PI is generally related to the training samples, it is then transferred to the learned model. In this work, a LUPI-based CAD framework for AD is proposed. It can flexibly perform a classifier- or feature-level LUPI, in which the information is transferred from the additional PI modality to the diagnosis modality. A thorough comparison has been made among three classifier-level algorithms and five feature-level LUPI algorithms. The experimental results on the ADNI dataset show that all classifier-level and deep learning based feature-level LUPI algorithms can improve the performance of a single-modal neuroimaging-based CAD for AD by transferring PI. Graphical abstract Graphical abstract for the framework of the LUPI-based CAD for AD.

Translating the hemodynamic response: why focused interdisciplinary integration should matter for the future of functional neuroimaging

The amount of information acquired with functional neuroimaging techniques, particularly fNIRS and fMRI, is rapidly growing and has enormous potential for studying human brain functioning. Therefore, many scientists focus on solving computational neuroimaging and Big Data issues to advance the discipline. However, the main obstacle—the accurate translation of the hemodynamic response (HR) by the investigation of a physiological phenomenon called neurovascular coupling—is still not fully overcome and, more importantly, often overlooked in this context. This article provides a brief and critical overview of significant findings from cellular biology and in vivo brain physiology with a focus on advancing existing HR modelling paradigms. A brief historical timeline of these disciplines of neuroscience is presented for readers to grasp the concept better, and some possible solutions for further scientific discussion are provided.

Multimodal Neuroimaging: Basic Concepts and Classification of Neuropsychiatric Diseases

Neuroimaging techniques are widely used in neuroscience to visualize neural activity, to improve our understanding of brain mechanisms, and to identify biomarkers-especially for psychiatric diseases; however, each neuroimaging technique has several limitations. These limitations led to the development of multimodal neuroimaging (MN), which combines data obtained from multiple neuroimaging techniques, such as electroencephalography, functional magnetic resonance imaging, and yields more detailed information about brain dynamics. There are several types of MN, including visual inspection, data integration, and data fusion. This literature review aimed to provide a brief summary and basic information about MN techniques (data fusion approaches in particular) and classification approaches. Data fusion approaches are generally categorized as asymmetric and symmetric. The present review focused exclusively on studies based on symmetric data fusion methods (data-driven methods), such as independent component analysis and principal component analysis. Machine learning techniques have recently been introduced for use in identifying diseases and biomarkers of disease. The machine learning technique most widely used by neuroscientists is classification-especially support vector machine classification. Several studies differentiated patients with psychiatric diseases and healthy controls with using combined datasets. The common conclusion among these studies is that the prediction of diseases increases when combining data via MN techniques; however, there remain a few challenges associated with MN, such as sample size. Perhaps in the future N-way fusion can be used to combine multiple neuroimaging techniques or nonimaging predictors (eg, cognitive ability) to overcome the limitations of MN.

Hemodynamic effects of sex and handedness on the Wisconsin Card Sorting Test: the contradiction between neuroimaging and behavioural results

This study investigated the potential role of sex and handedness on the performance of a computerised Wisconsin Card Sorting Test (WCST) in healthy participants by applying functional near-infrared spectroscopy (fNIRS). We demonstrated significant (p < 0.05) sex-related differences of hemodynamic response in the prefrontal cortex of 70 healthy participants (female, n = 35 and male, n = 35; right-handed, n = 40 and left-handed, n = 30). In contrast, behavioural results of the WCST do not show sex bias, which is consistent with previous literature. Because of this, we compared ours and sparse previous fNIRS studies on the WCST. We propose that, according to recent studies of neurovascular coupling, this contradiction between neuroimaging and behavioural results may be explained by normal variability in neurovascular dynamics.

Constrained temporal parallel decomposition for EEG-fMRI fusion

OBJECTIVE

Multimodal neuroimaging has become a common practice in neuroscience research. Simultaneous EEG-fMRI is a popular multimodal recording approach due to the complementary spatiotemporal relationship between the two modalities. Several data fusion techniques have been proposed in the literature for EEG-fMRI fusion, including joint-ICA and parallel-ICA frameworks. Previous EEG-fMRI fusion approaches have used sensor-level EEG features. Recently, we introduced source-space ICA for EEG-MEG source reconstruction and component identification, which was shown to be a superior alternative to sensor-space ICA.

APPROACH

Here, we extend source-space ICA to the fusion of EEG-fMRI data. Additionally, we incorporate the use of a paradigm signal (constrained) and a lag-based signal decomposition approach to accommodate recent findings demonstrating the potentially variable lag structure between electrophysiological and BOLD signals. We evaluated this method on simulated concurrent EEG-fMRI during a boxcar task design, as well as real concurrent EEG-fMRI data from three participants performing an N-Back working memory task. The block diagram of the algorithm and corresponding source codes are provided.

MAIN RESULTS

Based on the results of the real working memory task, for all three subjects, one frontal theta component, and one right posterior alpha component had the highest contribution coefficients (~0.5) to the paradigm-related fused component. There were also two more alpha band components with contribution coefficients of 0.3. The highest contributing fMRI component (~0.8) was one known in the literature to be related to the attention network. The second fMRI component was related to the well-known default mode network, with a contribution coefficient of 0.3.

SIGNIFICANCE

The proposed EEG-fMRI fusion approach, is capable of estimating the brain maps of the EEG and fMRI for the fused components and account for the variable lag structure between electrophysiological and BOLD signals.

Comparison of EEG microstates with resting state fMRI and FDG-PET measures in the default mode network via simultaneously recorded trimodal (PET/MR/EEG) data

Simultaneous trimodal positron emission tomography/magnetic resonance imaging/electroencephalography (PET/MRI/EEG) resting state (rs) brain data were acquired from 10 healthy male volunteers. The rs-functional MRI (fMRI) metrics, such as regional homogeneity (ReHo), degree centrality (DC) and fractional amplitude of low-frequency fluctuations (fALFFs), as well as 2-[18F]fluoro-2-desoxy-d-glucose (FDG)-PET standardised uptake value (SUV), were calculated and the measures were extracted from the default mode network (DMN) regions of the brain. Similarly, four microstates for each subject, showing the diverse functional states of the whole brain via topographical variations due to global field power (GFP), were estimated from artefact-corrected EEG signals. In this exploratory analysis, the GFP of microstates was nonparametrically compared to rs-fMRI metrics and FDG-PET SUV measured in the DMN of the brain. The rs-fMRI metrics (ReHO, fALFF) and FDG-PET SUV did not show any significant correlations with any of the microstates. The DC metric showed a significant positive correlation with microstate C (r_s  = 0.73, p = .01). FDG-PET SUVs indicate a trend for a negative correlation with microstates A, B and C. The positive correlation of microstate C with DC metrics suggests a functional relationship between cortical hubs in the frontal and occipital lobes. The results of this study suggest further exploration of this method in a larger sample and in patients with neuropsychiatric disorders. The aim of this exploratory pilot study is to lay the foundation for the development of such multimodal measures to be applied as biomarkers for diagnosis, disease staging, treatment response and monitoring of neuropsychiatric disorders.

A Perspective of the Cross-Tissue Interplay of Genetics, Epigenetics, and Transcriptomics, and Their Relation to Brain Based Phenotypes in Schizophrenia

Genetic association studies of psychiatric disorders have provided unprecedented insight into disease risk profiles with high confidence. Yet, the next research challenge is how to translate this rich information into mechanisms of disease, and further help interventions and treatments. Given other comprehensive reviews elsewhere, here we want to discuss the research approaches that integrate information across various tissue types. Taking schizophrenia as an example, the tissues, cells, or organisms being investigated include postmortem brain tissues or neurons, peripheral blood and saliva, in vivo brain imaging, and in vitro cell lines, particularly human induced pluripotent stem cells (iPSC) and iPSC derived neurons. There is a wealth of information on the molecular signatures including genetics, epigenetics, and transcriptomics of various tissues, along with neuronal phenotypic measurements including neuronal morphometry and function, together with brain imaging and other techniques that provide data from various spatial temporal points of disease development. Through consistent or complementary processes across tissues, such as cross-tissue methylation quantitative trait loci (QTL) and expression QTL effects, systemic integration of such information holds the promise to put the pieces of puzzle together for a more complete view of schizophrenia disease pathogenesis.

Multi-modal brain fingerprinting: A manifold approximation based framework

This work presents an efficient framework, based on manifold approximation, for generating brain fingerprints from multi-modal data. The proposed framework represents images as bags of local features which are used to build a subject proximity graph. Compact fingerprints are obtained by projecting this graph in a low-dimensional manifold using spectral embedding. Experiments using the T1/T2-weighted MRI, diffusion MRI, and resting-state fMRI data of 945 Human Connectome Project subjects demonstrate the benefit of combining multiple modalities, with multi-modal fingerprints more discriminative than those generated from individual modalities. Results also highlight the link between fingerprint similarity and genetic proximity, monozygotic twins having more similar fingerprints than dizygotic or non-twin siblings. This link is also reflected in the differences of feature correspondences between twin/sibling pairs, occurring in major brain structures and across hemispheres. The robustness of the proposed framework to factors like image alignment and scan resolution, as well as the reproducibility of results on retest scans, suggest the potential of multi-modal brain fingerprinting for characterizing individuals in a large cohort analysis.

How random is the random forest? Random forest algorithm on the service of structural imaging biomarkers for Alzheimer's disease: from Alzheimer's disease neuroimaging initiative (ADNI) database

Neuroinformatics is a fascinating research field that applies computational models and analytical tools to high dimensional experimental neuroscience data for a better understanding of how the brain functions or dysfunctions in brain diseases. Neuroinformaticians work in the intersection of neuroscience and informatics supporting the integration of various sub-disciplines (behavioural neuroscience, genetics, cognitive psychology, etc.) working on brain research. Neuroinformaticians are the pathway of information exchange between informaticians and clinicians for a better understanding of the outcome of computational models and the clinical interpretation of the analysis. Machine learning is one of the most significant computational developments in the last decade giving tools to neuroinformaticians and finally to radiologists and clinicians for an automatic and early diagnosis-prognosis of a brain disease. Random forest (RF) algorithm has been successfully applied to high-dimensional neuroimaging data for feature reduction and also has been applied to classify the clinical label of a subject using single or multi-modal neuroimaging datasets. Our aim was to review the studies where RF was applied to correctly predict the Alzheimer's disease (AD), the conversion from mild cognitive impairment (MCI) and its robustness to overfitting, outliers and handling of non-linear data. Finally, we described our RF-based model that gave us the 1st position in an international challenge for automated prediction of MCI from MRI data.

Non-invasive imaging modalities to study neurodegenerative diseases of aging brain

The aim of this article is to highlight current approaches for imaging elderly brain, indispensable for cognitive neuroscience research with emphasis on the basic physical principles of various non-invasive neuroimaging techniques. The first part of this article presents a quick overview of the primary non-invasive neuroimaging modalities used by cognitive neuroscientists such as transcranial magnetic stimulation (TMS), transcranial electrical stimulation (tES), electroencephalography (EEG), magnetoencephalography (MEG), single photon emission computed tomography (SPECT), positron emission tomography (PET), magnetic resonance spectroscopic imaging (MRSI), Profusion imaging, functional magnetic resonance imaging (fMRI), near infrared spectroscopy (NIRS) and diffusion tensor imaging (DTI) along with tractography and connectomics. The second part provides a comprehensive overview of different multimodality imaging techniques for various cognitive neuroscience studies of aging brain.

Structural Neuroimaging of Anorexia Nervosa: Future Directions in the Quest for Mechanisms Underlying Dynamic Alterations

Anorexia nervosa (AN) is a serious eating disorder characterized by self-starvation and extreme weight loss. Pseudoatrophic brain changes are often readily visible in individual brain scans, and AN may be a valuable model disorder to study structural neuroplasticity. Structural magnetic resonance imaging studies have found reduced gray matter volume and cortical thinning in acutely underweight patients to normalize following successful treatment. However, some well-controlled studies have found regionally greater gray matter and persistence of structural alterations following long-term recovery. Findings from diffusion tensor imaging studies of white matter integrity and connectivity are also inconsistent. Furthermore, despite the severity of AN, the number of existing structural neuroimaging studies is still relatively low, and our knowledge of the underlying cellular and molecular mechanisms for macrostructural brain changes is rudimentary. We critically review the current state of structural neuroimaging in AN and discuss the potential neurobiological basis of structural brain alterations in the disorder, highlighting impediments to progress, recent developments, and promising future directions. In particular, we argue for the utility of more standardized data collection, adopting a connectomics approach to understanding brain network architecture, employing advanced magnetic resonance imaging methods that quantify biomarkers of brain tissue microstructure, integrating data from multiple imaging modalities, strategic longitudinal observation during weight restoration, and large-scale data pooling. Our overarching objective is to motivate carefully controlled research of brain structure in eating disorders, which will ultimately help predict therapeutic response and improve treatment.

Novel CNS drug discovery and development approach: model-based integration to predict neuro-pharmacokinetics and pharmacodynamics

INTRODUCTION

CNS drug development has been hampered by inadequate consideration of CNS pharmacokinetic (PK), pharmacodynamics (PD) and disease complexity (reductionist approach). Improvement is required via integrative model-based approaches. Areas covered: The authors summarize factors that have played a role in the high attrition rate of CNS compounds. Recent advances in CNS research and drug discovery are presented, especially with regard to assessment of relevant neuro-PK parameters. Suggestions for further improvements are also discussed. Expert opinion: Understanding time- and condition dependent interrelationships between neuro-PK and neuro-PD processes is key to predictions in different conditions. As a first screen, it is suggested to use in silico/in vitro derived molecular properties of candidate compounds and predict concentration-time profiles of compounds in multiple compartments of the human CNS, using time-course based physiology-based (PB) PK models. Then, for selected compounds, one can include in vitro drug-target binding kinetics to predict target occupancy (TO)-time profiles in humans. This will improve neuro-PD prediction. Furthermore, a pharmaco-omics approach is suggested, providing multilevel and paralleled data on systems processes from individuals in a systems-wide manner. Thus, clinical trials will be better informed, using fewer animals, while also, needing fewer individuals and samples per individual for proof of concept in humans.