Machine Learning With Neuroimaging: Evaluating Its Applications in Psychiatry

Mapping the neurodevelopmental predictors of psychopathology

Neuroimaging research has uncovered a multitude of neural abnormalities associated with psychopathology, but few prediction-based studies have been conducted during adolescence, and even fewer used neurobiological features that were extracted across multiple neuroimaging modalities. This gap in the literature is critical, as deriving accurate brain-based models of psychopathology is an essential step towards understanding key neural mechanisms and identifying high-risk individuals. As such, we trained adaptive tree-boosting algorithms on multimodal neuroimaging features from the Lifespan Human Connectome Developmental (HCP-D) sample that contained 956 participants between the ages of 8 to 22 years old. Our feature space consisted of 1037 anatomical, 1090 functional, and 192 diffusion MRI features, which were used to derive models that separately predicted internalizing symptoms, externalizing symptoms, and the general psychopathology factor. We found that multimodal models were the most accurate, but all brain-based models of psychopathology yielded out-of-sample predictions that were weakly correlated with actual symptoms (r2 < 0.15). White matter microstructural properties, including orientation dispersion indices and intracellular volume fractions, were the most predictive of general psychopathology, followed by cortical thickness and functional connectivity. Spatially, the most predictive features of general psychopathology were primarily localized within the default mode and dorsal attention networks. These results were mostly consistent across all dimensions of psychopathology, except orientation dispersion indices and the default mode network were not as heavily weighted in the prediction of internalizing and externalizing symptoms. Taken with prior literature, it appears that neurobiological features are an important part of the equation for predicting psychopathology but relying exclusively on neural markers is clearly not sufficient, especially among adolescent samples with subclinical symptoms. Consequently, risk factor models of psychopathology may benefit from incorporating additional sources of information that have also been shown to explain individual differences, such as psychosocial factors, environmental stressors, and genetic vulnerabilities.

Development of a harmonized sociodemographic and clinical questionnaire for mental health research: A Delphi-method-based consensus recommendation

OBJECTIVE

Harmonized tools are essential for reliable data sharing and accurate identification of relevant factors in mental health research. The primary objective of this study was to create a harmonized questionnaire to collect demographic, clinical and behavioral data in diverse clinical trials in adult psychiatry.

METHODS

We conducted a literature review and examined 24 questionnaires used in previously published randomized controlled trials in psychiatry, identifying a total of 27 domains previously explored. Using a Delphi-method process, a task force team comprising experts in psychiatry, epidemiology and statistics selected 15 essential domains for inclusion in the final questionnaire.

RESULTS

The final selection resulted in a concise set of 22 questions. These questions cover factors such as age, sex, gender, ancestry, education, living arrangement, employment status, home location, relationship status, and history of medical and mental illness. Behavioral factors like physical activity, diet, smoking, alcohol and illicit drug use were also included, along with one question addressing family history of mental illness. Income was excluded due to high confounding and redundancy, while language was included as a measure of migration status.

CONCLUSION

The recommendation and adoption of this harmonized tool for the assessment of demographic, clinical and behavioral data in mental health research can enhance data consistency and enable comparability across clinical trials.

Quality over quantity: powering neuroimaging samples in psychiatry

Neuroimaging has been widely adopted in psychiatric research, with hopes that these non-invasive methods will provide important clues to the underpinnings and prediction of various mental health symptoms and outcomes. However, the translational impact of neuroimaging has not yet reached its promise, despite the plethora of computational methods, tools, and datasets at our disposal. Some have lamented that too many psychiatric neuroimaging studies have been underpowered with respect to sample size. In this review, we encourage this discourse to shift from a focus on sheer increases in sample size to more thoughtful choices surrounding experimental study designs. We propose considerations at multiple decision points throughout the study design, data modeling and analysis process that may help researchers working in psychiatric neuroimaging boost power for their research questions of interest without necessarily increasing sample size. We also provide suggestions for leveraging multiple datasets to inform each other and strengthen our confidence in the generalization of findings to both population-level and clinical samples. Through a greater emphasis on improving the quality of brain-based and clinical measures rather than merely quantity, meaningful and potentially translational clinical associations with neuroimaging measures can be achieved with more modest sample sizes in psychiatry.

Revolutionizing Neurology: The Role of Artificial Intelligence in Advancing Diagnosis and Treatment

Artificial intelligence (AI) has emerged as a powerful tool in the field of neurology, significantly impacting the diagnosis and treatment of neurological disorders. Recent technological breakthroughs have given us access to a plethora of information relevant to many aspects of neurology. Neuroscience and AI share a long history of collaboration. Along with great potential, we encounter obstacles relating to data quality, ethics, and inherent difficulty in applying data science in healthcare. Neurological disorders pose intricate challenges due to their complex manifestations and variability. Automating image interpretation tasks, AI algorithms accurately identify brain structures and detect abnormalities. This accelerates diagnosis and reduces the workload on medical professionals. Treatment optimization benefits from AI simulations that model different scenarios and predict outcomes. These AI systems can currently perform many of the sophisticated perceptual and cognitive capacities of biological systems, such as object identification and decision making. Furthermore, AI is rapidly being used as a tool in neuroscience research, altering our understanding of brain functioning. It has the ability to revolutionize healthcare as we know it into a system in which humans and robots collaborate to deliver better care for our patients. Image analysis activities such as recognizing particular brain regions, calculating changes in brain volume over time, and detecting abnormalities in brain scans can be automated by AI systems. This lessens the strain on radiologists and neurologists while improving diagnostic accuracy and efficiency. It is now obvious that cutting-edge artificial intelligence models combined with high-quality clinical data will lead to enhanced prognostic and diagnostic models in neurological illness, permitting expert-level clinical decision aids across healthcare settings. In conclusion, AI's integration into neurology has revolutionized diagnosis, treatment, and research. As AI technologies advance, they promise to unravel the complexities of neurological disorders further, leading to improved patient care and quality of life. The symbiosis of AI and neurology offers a glimpse into a future where innovation and compassion converge to reshape neurological healthcare. This abstract provides a concise overview of the role of AI in neurology and its transformative potential.

Sex classification from functional brain connectivity: Generalization to multiple datasets

Machine learning (ML) approaches are increasingly being applied to neuroimaging data. Studies in neuroscience typically have to rely on a limited set of training data which may impair the generalizability of ML models. However, it is still unclear which kind of training sample is best suited to optimize generalization performance. In the present study, we systematically investigated the generalization performance of sex classification models trained on the parcelwise connectivity profile of either single samples or compound samples of two different sizes. Generalization performance was quantified in terms of mean across-sample classification accuracy and spatial consistency of accurately classifying parcels. Our results indicate that the generalization performance of parcelwise classifiers (pwCs) trained on single dataset samples is dependent on the specific test samples. Certain datasets seem to "match" in the sense that classifiers trained on a sample from one dataset achieved a high accuracy when tested on the respected other one and vice versa. The pwCs trained on the compound samples demonstrated overall highest generalization performance for all test samples, including one derived from a dataset not included in building the training samples. Thus, our results indicate that both a large sample size and a heterogeneous data composition of a training sample have a central role in achieving generalizable results.

Application of machine learning techniques in the diagnostic approach of PTSD using MRI neuroimaging data: A systematic review

Background

At present, the diagnosis of post-traumatic stress disorder（PTSD） mainly relies on clinical symptoms and psychological scales, and finding objective indicators that are helpful for diagnosis has always been a challenge in clinical practice and academic research. Neuroimaging is a useful and powerful tool for discovering the biomarkers of PTSD,especially functional MRI (fMRI), structural MRI (sMRI) and Diffusion Weighted Imaging（DTI）are the most commonly used technologies, which can provide multiple perspectives on brain function, structure and its connectivity. Machine learning (ML) is an emerging and potentially powerful method, which has aroused people's interest because it is used together with neuroimaging data to define brain structural and functional abnormalities related to diseases, and identify phenotypes, such as helping physicians make early diagnosis.

Objectives

According to the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) declaration, a systematic review was conducted to assess its accuracy in distinguishing between PTSD patients, TEHC(Trauma-Exposed Healthy Controls), and HC(healthy controls).

Methods

We searched PubMed, Embase, and Web of Science using common words for ML methods and PTSD until June 2023, with no language or time limits. This review includes 13 studies, with sensitivity, specificity, and accuracy taken from each publication or acquired directly from the authors.

Results

All ML techniques have an diagnostic accuracy rate above 70%，and support vector machine（SVM） are the most commonly used techniques. This series of studies has revealed significant neurobiological differences in key brain regions among individuals with PTSD, TEHC, and HC. The connectivity patterns of regions such as the Insula and Amygdala hold particular significance in distinguishing these groups. TEHC exhibits more normal connectivity patterns compared to PTSD, providing valuable insights for the application of machine learning in PTSD diagnosis.

Conclusion

In contrast to any currently available assessment and clinical diagnosis, ML techniques can be used as an effective and non-invasive support for early identification and detection of patients as well as for early screening of high-risk populations.

Sex classification from functional brain connectivity: Generalization to multiple datasets Generalizability of sex classifiers

Machine learning (ML) approaches are increasingly being applied to neuroimaging data. Studies in neuroscience typically have to rely on a limited set of training data which may impair the generalizability of ML models. However, it is still unclear which kind of training sample is best suited to optimize generalization performance. In the present study, we systematically investigated the generalization performance of sex classification models trained on the parcelwise connectivity profile of either single samples or a compound sample containing data from four different datasets. Generalization performance was quantified in terms of mean across-sample classification accuracy and spatial consistency of accurately classifying parcels. Our results indicate that generalization performance of pwCs trained on single dataset samples is dependent on the specific test samples. Certain datasets seem to "match" in the sense that classifiers trained on a sample from one dataset achieved a high accuracy when tested on the respected other one and vice versa. The pwC trained on the compound sample demonstrated overall highest generalization performance for all test samples, including one derived from a dataset not included in building the training samples. Thus, our results indicate that a big and heterogenous training sample comprising data of multiple datasets is best suited to achieve generalizable results.

More reliable biomarkers and more accurate prediction for mental disorders using a label-noise filtering-based dimensional prediction method

The integration of neuroimaging with artificial intelligence is crucial for advancing the diagnosis of mental disorders. However, challenges arise from incomplete matching between diagnostic labels and neuroimaging. Here, we propose a label-noise filtering-based dimensional prediction (LAMP) method to identify reliable biomarkers and achieve accurate prediction for mental disorders. Our method proposes to utilize a label-noise filtering model to automatically filter out unclear cases from a neuroimaging perspective, and then the typical subjects whose diagnostic labels align with neuroimaging measures are used to construct a dimensional prediction model to score independent subjects. Using fMRI data of schizophrenia patients and healthy controls (n = 1,245), our method yields consistent scores to independent subjects, leading to more distinguishable relabeled groups with an enhanced classification accuracy of 31.89%. Additionally, it enables the exploration of stable abnormalities in schizophrenia. In summary, our LAMP method facilitates the identification of reliable biomarkers and accurate diagnosis of mental disorders using neuroimages.

Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review

INTRODUCTION

Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia.

METHODS

We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases.

RESULTS

A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort.

DISCUSSION

The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice.

HIGHLIGHTS

There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias.

Can we diagnose mental disorders in children? A large-scale assessment of machine learning on structural neuroimaging of 6916 children in the adolescent brain cognitive development study

Background

Prediction of mental disorders based on neuroimaging is an emerging area of research with promising first results in adults. However, research on the unique demographic of children is underrepresented and it is doubtful whether findings obtained on adults can be transferred to children.

Methods

Using data from 6916 children aged 9-10 in the multicenter Adolescent Brain Cognitive Development study, we extracted 136 regional volume and thickness measures from structural magnetic resonance images to rigorously evaluate the capabilities of machine learning to predict 10 different psychiatric disorders: major depressive disorder, bipolar disorder (BD), psychotic symptoms, attention deficit hyperactivity disorder (ADHD), oppositional defiant disorder, conduct disorder, post-traumatic stress disorder, obsessive-compulsive disorder, generalized anxiety disorder, and social anxiety disorder. For each disorder, we performed cross-validation and assessed whether models discovered a true pattern in the data via permutation testing.

Results

Two of 10 disorders can be detected with statistical significance when using advanced models that (i) allow for non-linear relationships between neuroanatomy and disorder, (ii) model interdependencies between disorders, and (iii) avoid confounding due to sociodemographic factors: ADHD (AUROC = 0.567, p = 0.002) and BD (AUROC = 0.551, p = 0.002). In contrast, traditional models perform consistently worse and predict only ADHD with statistical significance (AUROC = 0.529, p = 0.002).

Conclusion

While the modest absolute classification performance does not warrant application in the clinic, our results provide empirical evidence that embracing and explicitly accounting for the complexities of mental disorders via advanced machine learning models can discover patterns that would remain hidden with traditional models.

Classifying Children with ADHD Based on Prefrontal Functional Near-infrared Spectroscopy Using Machine Learning

Objective

: Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in children and adults characterized by cognitive and emotional self-control deficiencies. Previous functional near-infrared spectroscopy (fNIRS) studies found significant group differences between ADHD children and healthy controls during cognitive flexibility tasks in several brain regions. This study aims to apply a machine learning approach to identify medication-naive ADHD patients and healthy control (HC) groups using task-based fNIRS data.

Methods

: fNIRS signals from 33 ADHD children and 39 HC during the Stroop task were analyzed. In addition, regularized linear discriminant analysis (RLDA) was used to identify ADHD individuals from healthy controls, and classification performance was evaluated.

Results

: We found that participants can be correctly classified in RLDA leave-one-out cross validation, with a sensitivity of 0.67, specificity of 0.93, and accuracy of 0.82.

Conclusion

: RLDA using only fNIRS data can effectively discriminate children with ADHD from HC. This study suggests the potential utility of the fNIRS signal as a diagnostic biomarker for ADHD children.

oFVSD: a Python package of optimized forward variable selection decoder for high-dimensional neuroimaging data

The complexity and high dimensionality of neuroimaging data pose problems for decoding information with machine learning (ML) models because the number of features is often much larger than the number of observations. Feature selection is one of the crucial steps for determining meaningful target features in decoding; however, optimizing the feature selection from such high-dimensional neuroimaging data has been challenging using conventional ML models. Here, we introduce an efficient and high-performance decoding package incorporating a forward variable selection (FVS) algorithm and hyper-parameter optimization that automatically identifies the best feature pairs for both classification and regression models, where a total of 18 ML models are implemented by default. First, the FVS algorithm evaluates the goodness-of-fit across different models using the k-fold cross-validation step that identifies the best subset of features based on a predefined criterion for each model. Next, the hyperparameters of each ML model are optimized at each forward iteration. Final outputs highlight an optimized number of selected features (brain regions of interest) for each model with its accuracy. Furthermore, the toolbox can be executed in a parallel environment for efficient computation on a typical personal computer. With the optimized forward variable selection decoder (oFVSD) pipeline, we verified the effectiveness of decoding sex classification and age range regression on 1,113 structural magnetic resonance imaging (MRI) datasets. Compared to ML models without the FVS algorithm and with the Boruta algorithm as a variable selection counterpart, we demonstrate that the oFVSD significantly outperformed across all of the ML models over the counterpart models without FVS (approximately 0.20 increase in correlation coefficient, r, with regression models and 8% increase in classification models on average) and with Boruta variable selection algorithm (approximately 0.07 improvement in regression and 4% in classification models). Furthermore, we confirmed the use of parallel computation considerably reduced the computational burden for the high-dimensional MRI data. Altogether, the oFVSD toolbox efficiently and effectively improves the performance of both classification and regression ML models, providing a use case example on MRI datasets. With its flexibility, oFVSD has the potential for many other modalities in neuroimaging. This open-source and freely available Python package makes it a valuable toolbox for research communities seeking improved decoding accuracy.

Accurate sex prediction of cisgender and transgender individuals without brain size bias

The increasing use of machine learning approaches on neuroimaging data comes with the important concern of confounding variables which might lead to biased predictions and in turn spurious conclusions about the relationship between the features and the target. A prominent example is the brain size difference between women and men. This difference in total intracranial volume (TIV) can cause bias when employing machine learning approaches for the investigation of sex differences in brain morphology. A TIV-biased model will not capture qualitative sex differences in brain organization but rather learn to classify an individual's sex based on brain size differences, thus leading to spurious and misleading conclusions, for example when comparing brain morphology between cisgender- and transgender individuals. In this study, TIV bias in sex classification models applied to cis- and transgender individuals was systematically investigated by controlling for TIV either through featurewise confound removal or by matching the training samples for TIV. Our results provide strong evidence that models not biased by TIV can classify the sex of both cis- and transgender individuals with high accuracy, highlighting the importance of appropriate modeling to avoid bias in automated decision making.

Enhancing precision in human neuroscience

Human neuroscience has always been pushing the boundary of what is measurable. During the last decade, concerns about statistical power and replicability - in science in general, but also specifically in human neuroscience - have fueled an extensive debate. One important insight from this discourse is the need for larger samples, which naturally increases statistical power. An alternative is to increase the precision of measurements, which is the focus of this review. This option is often overlooked, even though statistical power benefits from increasing precision as much as from increasing sample size. Nonetheless, precision has always been at the heart of good scientific practice in human neuroscience, with researchers relying on lab traditions or rules of thumb to ensure sufficient precision for their studies. In this review, we encourage a more systematic approach to precision. We start by introducing measurement precision and its importance for well-powered studies in human neuroscience. Then, determinants for precision in a range of neuroscientific methods (MRI, M/EEG, EDA, Eye-Tracking, and Endocrinology) are elaborated. We end by discussing how a more systematic evaluation of precision and the application of respective insights can lead to an increase in reproducibility in human neuroscience.

A meta-analysis and systematic review of single vs. multimodal neuroimaging techniques in the classification of psychosis

BACKGROUND

Psychotic disorders are characterized by structural and functional abnormalities in brain networks. Neuroimaging techniques map and characterize such abnormalities using unique features (e.g., structural integrity, coactivation). However, it is unclear if a specific method, or a combination of modalities, is particularly effective in identifying differences in brain networks of someone with a psychotic disorder.

METHODS

A systematic meta-analysis evaluated machine learning classification of schizophrenia spectrum disorders in comparison to healthy control participants using various neuroimaging modalities (i.e., T1-weighted imaging (T1), diffusion tensor imaging (DTI), resting state functional connectivity (rs-FC), or some combination (multimodal)). Criteria for manuscript inclusion included whole-brain analyses and cross-validation to provide a complete picture regarding the predictive ability of large-scale brain systems in psychosis. For this meta-analysis, we searched Ovid MEDLINE, PubMed, PsychInfo, Google Scholar, and Web of Science published between inception and March 13th 2023. Prediction results were averaged for studies using the same dataset, but parallel analyses were run that included studies with pooled sample across many datasets. We assessed bias through funnel plot asymmetry. A bivariate regression model determined whether differences in imaging modality, demographics, and preprocessing methods moderated classification. Separate models were run for studies with internal prediction (via cross-validation) and external prediction.

RESULTS

93 studies were identified for quantitative review (30 T1, 9 DTI, 40 rs-FC, and 14 multimodal). As a whole, all modalities reliably differentiated those with schizophrenia spectrum disorders from controls (OR = 2.64 (95%CI = 2.33 to 2.95)). However, classification was relatively similar across modalities: no differences were seen across modalities in the classification of independent internal data, and a small advantage was seen for rs-FC studies relative to T1 studies in classification in external datasets. We found large amounts of heterogeneity across results resulting in significant signs of bias in funnel plots and Egger's tests. Results remained similar, however, when studies were restricted to those with less heterogeneity, with continued small advantages for rs-FC relative to structural measures. Notably, in all cases, no significant differences were seen between multimodal and unimodal approaches, with rs-FC and unimodal studies reporting largely overlapping classification performance. Differences in demographics and analysis or denoising were not associated with changes in classification scores.

CONCLUSIONS

The results of this study suggest that neuroimaging approaches have promise in the classification of psychosis. Interestingly, at present most modalities perform similarly in the classification of psychosis, with slight advantages for rs-FC relative to structural modalities in some specific cases. Notably, results differed substantially across studies, with suggestions of biased effect sizes, particularly highlighting the need for more studies using external prediction and large sample sizes. Adopting more rigorous and systematized standards will add significant value toward understanding and treating this critical population.

Reproducibility in Neuroimaging Analysis: Challenges and Solutions

Recent years have marked a renaissance in efforts to increase research reproducibility in psychology, neuroscience, and related fields. Reproducibility is the cornerstone of a solid foundation of fundamental research-one that will support new theories built on valid findings and technological innovation that works. The increased focus on reproducibility has made the barriers to it increasingly apparent, along with the development of new tools and practices to overcome these barriers. Here, we review challenges, solutions, and emerging best practices with a particular emphasis on neuroimaging studies. We distinguish 3 main types of reproducibility, discussing each in turn. Analytical reproducibility is the ability to reproduce findings using the same data and methods. Replicability is the ability to find an effect in new datasets, using the same or similar methods. Finally, robustness to analytical variability refers to the ability to identify a finding consistently across variation in methods. The incorporation of these tools and practices will result in more reproducible, replicable, and robust psychological and brain research and a stronger scientific foundation across fields of inquiry.

Connectome-based machine learning models are vulnerable to subtle data manipulations

Neuroimaging-based predictive models continue to improve in performance, yet a widely overlooked aspect of these models is "trustworthiness," or robustness to data manipulations. High trustworthiness is imperative for researchers to have confidence in their findings and interpretations. In this work, we used functional connectomes to explore how minor data manipulations influence machine learning predictions. These manipulations included a method to falsely enhance prediction performance and adversarial noise attacks designed to degrade performance. Although these data manipulations drastically changed model performance, the original and manipulated data were extremely similar (r = 0.99) and did not affect other downstream analysis. Essentially, connectome data could be inconspicuously modified to achieve any desired prediction performance. Overall, our enhancement attacks and evaluation of existing adversarial noise attacks in connectome-based models highlight the need for counter-measures that improve the trustworthiness to preserve the integrity of academic research and any potential translational applications.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Classifying Conduct Disorder Using a Biopsychosocial Model and Machine Learning Method

BACKGROUND

Conduct disorder (CD) is a common syndrome with far-reaching effects. Risk factors for the development of CD span social, psychological, and biological domains. Researchers note that predictive models of CD are limited if the focus is on a single risk factor or even a single domain. Machine learning methods are optimized for the extraction of trends across multidomain data but have yet to be implemented in predicting the development of CD.

METHODS

Social (e.g., family, income), psychological (e.g., psychiatric, neuropsychological), and biological (e.g., resting-state graph metrics) risk factors were measured using data from the baseline visit of the Adolescent Brain Cognitive Development Study when youth were 9 to 10 years old (N = 2368). Applying a feed-forward neural network machine learning method, risk factors were used to predict CD diagnoses 2 years later.

RESULTS

A model with factors that included social, psychological, and biological domains outperformed models representing factors within any single domain, predicting the presence of a CD diagnosis with 91.18% accuracy. Within each domain, certain factors stood out in terms of their relationship to CD (social: lower parental monitoring, more aggression in the household, lower income; psychological: greater attention-deficit/hyperactivity disorder and oppositional defiant disorder symptoms, worse crystallized cognition and card sorting performance; biological: disruptions in the topology of subcortical and frontoparietal networks).

CONCLUSIONS

The development of an accurate, sensitive, and specific predictive model of CD has the potential to aid in prevention and intervention efforts. Key risk factors for CD appear best characterized as reflecting unpredictable, impulsive, deprived, and emotional external and internal contexts.

Artificial intelligence for diffusion MRI-based tissue microstructure estimation in the human brain: an overview

Artificial intelligence (AI) has made significant advances in the field of diffusion magnetic resonance imaging (dMRI) and other neuroimaging modalities. These techniques have been applied to various areas such as image reconstruction, denoising, detecting and removing artifacts, segmentation, tissue microstructure modeling, brain connectivity analysis, and diagnosis support. State-of-the-art AI algorithms have the potential to leverage optimization techniques in dMRI to advance sensitivity and inference through biophysical models. While the use of AI in brain microstructures has the potential to revolutionize the way we study the brain and understand brain disorders, we need to be aware of the pitfalls and emerging best practices that can further advance this field. Additionally, since dMRI scans rely on sampling of the q-space geometry, it leaves room for creativity in data engineering in such a way that it maximizes the prior inference. Utilization of the inherent geometry has been shown to improve general inference quality and might be more reliable in identifying pathological differences. We acknowledge and classify AI-based approaches for dMRI using these unifying characteristics. This article also highlighted and reviewed general practices and pitfalls involving tissue microstructure estimation through data-driven techniques and provided directions for building on them.

Artificial intelligence ecosystem for computational psychiatry: Ideas to practice

Computational psychiatry is an emerging field that not only explores the biological basis of mental illness but also considers the diagnoses and identifies the underlying mechanisms. One of the key strengths of computational psychiatry is that it may identify patterns in large datasets that are not easily identifiable. This may help researchers develop more effective treatments and interventions for mental health problems. This paper is a narrative review that reviews the literature and produces an artificial intelligence ecosystem for computational psychiatry. The artificial intelligence ecosystem for computational psychiatry includes data acquisition, preparation, modeling, application, and evaluation. This approach allows researchers to integrate data from a variety of sources, such as brain imaging, genetics, and behavioral experiments, to obtain a more complete understanding of mental health conditions. Through the process of data preprocessing, training, and testing, the data that are required for model building can be prepared. By using machine learning, neural networks, artificial intelligence, and other methods, researchers have been able to develop diagnostic tools that can accurately identify mental health conditions based on a patient’s symptoms and other factors. Despite the continuous development and breakthrough of computational psychiatry, it has not yet influenced routine clinical practice and still faces many challenges, such as data availability and quality, biological risks, equity, and data protection. As we move progress in this field, it is vital to ensure that computational psychiatry remains accessible and inclusive so that all researchers may contribute to this significant and exciting field.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Restoring the missing person to personalized medicine and precision psychiatry

Precision psychiatry has emerged as part of the shift to personalized medicine and builds on frameworks such as the U.S. National Institute of Mental Health Research Domain Criteria (RDoC), multilevel biological "omics" data and, most recently, computational psychiatry. The shift is prompted by the realization that a one-size-fits all approach is inadequate to guide clinical care because people differ in ways that are not captured by broad diagnostic categories. One of the first steps in developing this personalized approach to treatment was the use of genetic markers to guide pharmacotherapeutics based on predictions of pharmacological response or non-response, and the potential risk of adverse drug reactions. Advances in technology have made a greater degree of specificity or precision potentially more attainable. To date, however, the search for precision has largely focused on biological parameters. Psychiatric disorders involve multi-level dynamics that require measures of phenomenological, psychological, behavioral, social structural, and cultural dimensions. This points to the need to develop more fine-grained analyses of experience, self-construal, illness narratives, interpersonal interactional dynamics, and social contexts and determinants of health. In this paper, we review the limitations of precision psychiatry arguing that it cannot reach its goal if it does not include core elements of the processes that give rise to psychopathological states, which include the agency and experience of the person. Drawing from contemporary systems biology, social epidemiology, developmental psychology, and cognitive science, we propose a cultural-ecosocial approach to integrating precision psychiatry with person-centered care.

Threats to external validity in the neuroprediction of substance use treatment outcomes

Background: Tools predicting individual relapse risk would invaluably inform clinical decision-making (e.g. level-of-care) in substance use treatment. Studies of neuroprediction - use of neuromarkers to predict individual outcomes - have the dual potential to create such tools and inform etiological models leading to new treatments. However, financial limitations, statistical power demands, and related factors encourage restrictive selection criteria, yielding samples that do not fully represent the target population. This problem may be further compounded by a lack of statistical optimism correction in neuroprediction research, resulting in predictive models that are overfit to already-restricted samples.Objectives: This systematic review aims to identify potential threats to external validity related to restrictive selection criteria and underutilization of optimism correction in the existing neuroprediction literature targeting substance use treatment outcomes.Methods: Sixty-seven studies of neuroprediction in substance use treatment were identified and details of sample selection criteria and statistical optimism correction were extracted.Results: Most publications were found to report restrictive selection criteria (e.g. excluding psychiatric (94% of publications) and substance use comorbidities (69% of publications)) that would rule-out a considerable portion of the treatment population. Furthermore, only 21% of publications reported optimism correction.Conclusion: Restrictive selection criteria and underutilization of optimism correction are common in the existing literature and may limit the generalizability of identified neural predictors to the target population whose treatment they would ultimately inform. Greater attention to the inclusivity and generalizability of addiction neuroprediction research, as well as new opportunities provided through open science initiatives, have the potential to address this issue.

Abnormal structural and functional network topological properties associated with left prefrontal, parietal, and occipital cortices significantly predict childhood TBI-related attention deficits: A semi-supervised deep learning study

Introduction

Traumatic brain injury (TBI) is a major public health concern in children. Children with TBI have elevated risk in developing attention deficits. Existing studies have found that structural and functional alterations in multiple brain regions were linked to TBI-related attention deficits in children. Most of these existing studies have utilized conventional parametric models for group comparisons, which have limited capacity in dealing with large-scale and high dimensional neuroimaging measures that have unknown nonlinear relationships. Nevertheless, none of these existing findings have been successfully implemented to clinical practice for guiding diagnoses and interventions of TBI-related attention problems. Machine learning techniques, especially deep learning techniques, are able to handle the multi-dimensional and nonlinear information to generate more robust predictions. Therefore, the current research proposed to construct a deep learning model, semi-supervised autoencoder, to investigate the topological alterations in both structural and functional brain networks in children with TBI and their predictive power for post-TBI attention deficits.

Methods

Functional magnetic resonance imaging data during sustained attention processing task and diffusion tensor imaging data from 110 subjects (55 children with TBI and 55 group-matched controls) were used to construct the functional and structural brain networks, respectively. A total of 60 topological properties were selected as brain features for building the model.

Results

The model was able to differentiate children with TBI and controls with an average accuracy of 82.86%. Functional and structural nodal topological properties associated with left frontal, inferior temporal, postcentral, and medial occipitotemporal regions served as the most important brain features for accurate classification of the two subject groups. Post hoc regression-based machine learning analyses in the whole study sample showed that among these most important neuroimaging features, those associated with left postcentral area, superior frontal region, and medial occipitotemporal regions had significant value for predicting the elevated inattentive and hyperactive/impulsive symptoms.

Discussion

Findings of this study suggested that deep learning techniques may have the potential to help identifying robust neurobiological markers for post-TBI attention deficits; and the left superior frontal, postcentral, and medial occipitotemporal regions may serve as reliable targets for diagnosis and interventions of TBI-related attention problems in children.

Tai Chi increases functional connectivity and decreases chronic fatigue syndrome: A pilot intervention study with machine learning and fMRI analysis

BACKGROUND

The latest guidance on chronic fatigue syndrome (CFS) recommends exercise therapy. Tai Chi, an exercise method in traditional Chinese medicine, is reportedly helpful for CFS. However, the mechanism remains unclear. The present longitudinal study aimed to detect the influence of Tai Chi on functional brain connectivity in CFS.

METHODS

The study recruited 20 CFS patients and 20 healthy controls to receive eight sessions of Tai Chi exercise over a period of one month. Before the Tai Chi exercise, an abnormal functional brain connectivity for recognizing CFS was generated by a linear support vector model. The prediction ability of the structure was validated with a random forest classification under a permutation test. Then, the functional connections (FCs) of the structure were analyzed in the large-scale brain network after Tai Chi exercise while taking the changes in the Fatigue Scale-14, Pittsburgh Sleep Quality Index (PSQI), and the 36-item short-form health survey (SF-36) as clinical effectiveness evaluation. The registration number is ChiCTR2000032577 in the Chinese Clinical Trial Registry.

RESULTS

1) The score of the Fatigue Scale-14 decreased significantly in the CFS patients, and the scores of the PSQI and SF-36 changed significantly both in CFS patients and healthy controls. 2) Sixty FCs were considered significant to discriminate CFS (P = 0.000, best accuracy 90%), with 80.5% ± 9% average accuracy. 3) The FCs that were majorly related to the left frontoparietal network (FPN) and default mode network (DMN) significantly increased (P = 0.0032 and P = 0.001) in CFS patients after Tai Chi exercise. 4) The change of FCs in the left FPN and DMN were positively correlated (r = 0.40, P = 0.012).

CONCLUSION

These results demonstrated that the 60 FCs we found using machine learning could be neural biomarkers to discriminate between CFS patients and healthy controls. Tai Chi exercise may improve CFS patients' fatigue syndrome, sleep quality, and body health statement by strengthening the functional connectivity of the left FPN and DMN under these FCs. The findings promote our understanding of Tai Chi exercise's value in treating CFS.

Distinct Neural Profiles of Frontoparietal Networks in Boys with ADHD and Boys with Persistent Depressive Disorder

Working memory deficits are common in attention-deficit/hyperactivity disorder (ADHD) and depression-two common neurodevelopmental disorders with overlapping cognitive profiles but distinct clinical presentation. Multivariate techniques have previously been utilized to understand working memory processes in functional brain networks in healthy adults but have not yet been applied to investigate how working memory processes within the same networks differ within typical and atypical developing populations. We used multivariate pattern analysis (MVPA) to identify whether brain networks discriminated between spatial versus verbal working memory processes in ADHD and Persistent Depressive Disorder (PDD). Thirty-six male clinical participants and 19 typically developing (TD) boys participated in a fMRI scan while completing a verbal and a spatial working memory task. Within a priori functional brain networks (frontoparietal, default mode, salience), the TD group demonstrated differential response patterns to verbal and spatial working memory. The PDD group showed weaker differentiation than TD, with lower classification accuracies observed in primarily the left frontoparietal network. The neural profiles of the ADHD and PDD differed specifically in the SN where the ADHD group's neural profile suggests significantly less specificity in neural representations of spatial and verbal working memory. We highlight within-group classification as an innovative tool for understanding the neural mechanisms of how cognitive processes may deviate in clinical disorders, an important intermediary step towards improving translational psychiatry.

Exploring neurometabolic alterations in bipolar disorder with suicidal ideation based on proton magnetic resonance spectroscopy and machine learning technology

Bipolar disorder (BD) is associated with a high risk of suicide. We used proton magnetic resonance spectroscopy (1H-MRS) to detect biochemical metabolite ratios in the bilateral prefrontal white matter (PWM) and hippocampus in 32 BD patients with suicidal ideation (SI) and 18 BD patients without SI, identified potential brain biochemical differences and used abnormal metabolite ratios to predict the severity of suicide risk based on the support vector machine (SVM) algorithm. Furthermore, we analyzed the correlations between biochemical metabolites and clinical variables in BD patients with SI. There were three main findings: (1) the highest classification accuracy of 88% and an area under the curve of 0.9 were achieved in distinguishing BD patients with and without SI, with N-acetyl aspartate (NAA)/creatine (Cr), myo-inositol (mI)/Cr values in the bilateral PWM, NAA/Cr and choline (Cho)/Cr values in the left hippocampus, and Cho/Cr values in the right hippocampus being the features contributing the most; (2) the above seven features could be used to predict Self-rating Idea of Suicide Scale scores (r = 0.4261, p = 0.0302); and (3) the level of neuronal function in the left hippocampus may be related to the duration of illness, the level of membrane phospholipid catabolism in the left hippocampus may be related to the severity of depression, and the level of inositol metabolism in the left PWM may be related to the age of onset in BD patients with SI. Our results showed that the combination of multiple brain biochemical metabolites could better predict the risk and severity of suicide in patients with BD and that there was a significant correlation between biochemical metabolic values and clinical variables in BD patients with SI.

Predicting the future of neuroimaging predictive models in mental health

Predictive modeling using neuroimaging data has the potential to improve our understanding of the neurobiology underlying psychiatric disorders and putatively information interventions. Accordingly, there is a plethora of literature reviewing published studies, the mathematics underlying machine learning, and the best practices for using these approaches. As our knowledge of mental health and machine learning continue to evolve, we instead aim to look forward and "predict" topics that we believe will be important in current and future studies. Some of the most discussed topics in machine learning, such as bias and fairness, the handling of dirty data, and interpretable models, may be less familiar to the broader community using neuroimaging-based predictive modeling in psychiatry. In a similar vein, transdiagnostic research and targeting brain-based features for psychiatric intervention are modern topics in psychiatry that predictive models are well-suited to tackle. In this work, we target an audience who is a researcher familiar with the fundamental procedures of machine learning and who wishes to increase their knowledge of ongoing topics in the field. We aim to accelerate the utility and applications of neuroimaging-based predictive models for psychiatric research by highlighting and considering these topics. Furthermore, though not a focus, these ideas generalize to neuroimaging-based predictive modeling in other clinical neurosciences and predictive modeling with different data types (e.g., digital health data).

The physical home environment and sleep: What matters most for sleep in early childhood

The physical home environment is thought to play a crucial role in facilitating healthy sleep in young children. However, relatively little is known about how various features of the physical home environment are associated with sleep in early childhood, and some of the recommendations clinicians make for improving child sleep environments are based on limited research evidence. The present study examined how observer and parent descriptions of the child's physical home environment were associated with child sleep, measured using actigraphy and parent's reports, across a year in early childhood. The study used a machine learning approach (elastic net regression) to specify which aspects of the physical home environment were most important for predicting five aspects of child sleep, sleep duration, sleep variability, sleep timing, sleep activity, and latency to fall asleep. The study included 546 toddlers (265 females) recruited at 30 months of age and reassessed at 36 and 42 months of age. Poorer quality physical home environments were associated with later sleep schedules, more variable sleep schedules, shorter sleep durations, and more parent-reported sleep problems in young children. The most important environmental predictors of sleep were room sharing with an adult, bed sharing, and quality of both the child's sleep space and the wider home environment. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Interpreting Brain Biomarkers: Challenges and solutions in interpreting machine learning-based predictive neuroimaging

Predictive modeling of neuroimaging data (predictive neuroimaging) for evaluating individual differences in various behavioral phenotypes and clinical outcomes is of growing interest. However, the field is experiencing challenges regarding the interpretability of the results. Approaches to defining the specific contribution of functional connections, regions, or networks in prediction models are urgently needed, which may help explore the underlying mechanisms. In this article, we systematically review the methods and applications for interpreting brain signatures derived from predictive neuroimaging based on a survey of 326 research articles. Strengths, limitations, and the suitable conditions for major interpretation strategies are also deliberated. In-depth discussion of common issues in existing literature and the corresponding recommendations to address these pitfalls are provided. We highly recommend exhaustive validation on the reliability and interpretability of the biomarkers across multiple datasets and contexts, which thereby could translate technical advances in neuroimaging into concrete improvements in precision medicine.

Implementing Critical Machine Learning (ML) Approaches for Generating Robust Discriminative Neuroimaging Representations Using Structural Equation Model (SEM)

Critical ML or CML is a critical approach development of the standard ML (SML) procedure. Conventional ML (ML) is being used in radiology departments where complex neuroimages are discriminated using ML technology. Radiologists and researchers found that sole decision by the ML algorithms is not accurate enough to implement the treatment procedure. Thus, an intelligent decision is required further by the radiologists after evaluating the ML outcomes. The current research is based on the critical ML, where radiologists' critical thinking ability, IQ (intelligence quotient), and experience in radiology have been examined to understand how these factors affect the accuracy of neuroimaging discrimination. A primary quantitative survey has been carried out, and the data were analysed in IBM SPSS. The results showed that experience in works has a positive impact on neuroimaging discrimination accuracy. IQ and trained ML are also responsible for improving the accuracy as well. Thus, radiologists with more experience in that field are able to improve the discriminative and diagnostic capability of CML.

Can Autism Be Diagnosed with Artificial Intelligence? A Narrative Review

Radiomics with deep learning models have become popular in computer-aided diagnosis and have outperformed human experts on many clinical tasks. Specifically, radiomic models based on artificial intelligence (AI) are using medical data (i.e., images, molecular data, clinical variables, etc.) for predicting clinical tasks such as autism spectrum disorder (ASD). In this review, we summarized and discussed the radiomic techniques used for ASD analysis. Currently, the limited radiomic work of ASD is related to the variation of morphological features of brain thickness that is different from texture analysis. These techniques are based on imaging shape features that can be used with predictive models for predicting ASD. This review explores the progress of ASD-based radiomics with a brief description of ASD and the current non-invasive technique used to classify between ASD and healthy control (HC) subjects. With AI, new radiomic models using the deep learning techniques will be also described. To consider the texture analysis with deep CNNs, more investigations are suggested to be integrated with additional validation steps on various MRI sites.

Prediction of tuberous sclerosis-associated neurocognitive disorders and seizures via machine learning of structural magnetic resonance imaging

PURPOSE

Tuberous sclerosis complex (TSC) is a genetic disorder characterized by multiorgan hamartomas, including cerebral lesions, with seizures as a common presentation. Most TSC patients will also experience neurocognitive comorbidities. Our objective was to use machine learning techniques incorporating clinical and imaging data to predict the occurrence of major neurocognitive disorders and seizures in TSC patients.

METHODS

A cohort of TSC patients were enrolled in this retrospective study. Clinical data included genetic, demographic, and seizure characteristics. Imaging parameters included the number, characteristics, and location of cortical tubers and the presence of subependymal nodules, SEGAs, and cerebellar tubers. A random forest machine learning scheme was used to predict seizures and neurodevelopmental delay or intellectual developmental disability. Prediction ability was assessed by the area-under-the-curve of receiver-operating-characteristics (AUC-ROC) of ten-fold cross-validation training set and an independent validation set.

RESULTS

The study population included 77 patients, 55% male (17.1 ± 11.7 years old). The model achieved AUC-ROC of 0.72 ± 0.1 and 0.68 in the training and internal validation datasets, respectively, for predicting neurocognitive comorbidity. Performance was limited in predicting seizures (AUC-ROC of 0.54 ± 0.19 and 0.71 in the training and internal validation datasets, respectively). The integration of seizure characteristics into the model improved the prediction of neurocognitive comorbidity with AUC-ROC of 0.84 ± 0.07 and 0.75 in the training and internal validation datasets, respectively.

CONCLUSIONS

This proof of concept study shows that it is possible to achieve a reasonable prediction of major neurocognitive morbidity in TSC patients using structural brain imaging and machine learning techniques. These tools can help clinicians identify subgroups of TSC patients with an increased risk of developing neurocognitive comorbidities.

Distributed functional connectivity predicts neuropsychological test performance among older adults

Neuropsychological test is an essential tool in assessing cognitive and functional changes associated with late-life neurocognitive disorders. Despite the utility of the neuropsychological test, the brain-wide neural basis of the test performance remains unclear. Using the predictive modeling approach, we aimed to identify the optimal combination of functional connectivities that predicts neuropsychological test scores of novel individuals. Resting-state functional connectivity and neuropsychological tests included in the OASIS-3 dataset (n = 428) were used to train the predictive models, and the identified models were iteratively applied to the holdout internal test set (n = 216) and external test set (KSHAP, n = 151). We found that the connectivity-based predicted score tracked the actual behavioral test scores (r = 0.08-0.44). The predictive models utilizing most of the connectivity features showed better accuracy than those composed of focal connectivity features, suggesting that its neural basis is largely distributed across multiple brain systems. The discriminant and clinical validity of the predictive models were further assessed. Our results suggest that late-life neuropsychological test performance can be formally characterized with distributed connectome-based predictive models, and further translational evidence is needed when developing theoretically valid and clinically incremental predictive models.

A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises

Since its renaissance, deep learning has been widely used in various medical imaging tasks and has achieved remarkable success in many medical imaging applications, thereby propelling us into the so-called artificial intelligence (AI) era. It is known that the success of AI is mostly attributed to the availability of big data with annotations for a single task and the advances in high performance computing. However, medical imaging presents unique challenges that confront deep learning approaches. In this survey paper, we first present traits of medical imaging, highlight both clinical needs and technical challenges in medical imaging, and describe how emerging trends in deep learning are addressing these issues. We cover the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, etc. Then, we present several case studies that are commonly found in clinical practice, including digital pathology and chest, brain, cardiovascular, and abdominal imaging. Rather than presenting an exhaustive literature survey, we instead describe some prominent research highlights related to these case study applications. We conclude with a discussion and presentation of promising future directions.

Predicting visual working memory with multimodal magnetic resonance imaging

The indispensability of visual working memory (VWM) in human daily life suggests its importance in higher cognitive functions and neurological diseases. However, despite the extensive research efforts, most findings on the neural basis of VWM are limited to a unimodal context (either structure or function) and have low generalization. To address the above issues, this study proposed the usage of multimodal neuroimaging in combination with machine learning to reveal the neural mechanism of VWM across a large cohort (N = 547). Specifically, multimodal magnetic resonance imaging features extracted from voxel-wise amplitude of low-frequency fluctuations, gray matter volume, and fractional anisotropy were used to build an individual VWM capacity prediction model through a machine learning pipeline, including the steps of feature selection, relevance vector regression, cross-validation, and model fusion. The resulting model exhibited promising predictive performance on VWM (r = .402, p < .001), and identified features within the subcortical-cerebellum network, default mode network, motor network, corpus callosum, anterior corona radiata, and external capsule as significant predictors. The main results were then compared with those obtained on emotional regulation and fluid intelligence using the same pipeline, confirming the specificity of our findings. Moreover, the main results maintained well under different cross-validation regimes and preprocess strategies. These findings, while providing richer evidence for the importance of multimodality in understanding cognitive functions, offer a solid and general foundation for comprehensively understanding the VWM process from the top down.

Artificial intelligence applied to neuroimaging data in Parkinsonian syndromes: Actuality and expectations

Idiopathic Parkinson's Disease (iPD) is a common motor neurodegenerative disorder. It affects more frequently the elderly population, causing a significant emotional burden both for the patient and caregivers, due to the disease-related onset of motor and cognitive disabilities. iPD's clinical hallmark is the onset of cardinal motor symptoms such as bradykinesia, rest tremor, rigidity, and postural instability. However, these symptoms appear when the neurodegenerative process is already in an advanced stage. Furthermore, the greatest challenge is to distinguish iPD from other similar neurodegenerative disorders, "atypical parkinsonisms", such as Multisystem Atrophy, Progressive Supranuclear Palsy and Cortical Basal Degeneration, since they share many phenotypic manifestations, especially in the early stages. The diagnosis of these neurodegenerative motor disorders is essentially clinical. Consequently, the diagnostic accuracy mainly depends on the professional knowledge and experience of the physician. Recent advances in artificial intelligence have made it possible to analyze the large amount of clinical and instrumental information in the medical field. The application machine learning algorithms to the analysis of neuroimaging data appear to be a promising tool for identifying microstructural alterations related to the pathological process in order to explain the onset of symptoms and the spread of the neurodegenerative process. In this context, the search for quantitative biomarkers capable of identifying parkinsonian patients in the prodromal phases of the disease, of correctly distinguishing them from atypical parkinsonisms and of predicting clinical evolution and response to therapy represent the main goal of most current clinical research studies. Our aim was to review the recent literature and describe the current knowledge about the contribution given by machine learning applications to research and clinical management of parkinsonian syndromes.

Evaluating Cognitive Relationships with Resting-State and Task-driven Blood Oxygen Level-Dependent Variability

Recent functional magnetic resonance imaging studies have reported that moment-to-moment variability in the blood oxygen level-dependent (BOLD) signal is positively associated with task performance and, thus, may reflect a behaviorally sensitive signal. However, it is not clear whether estimates of resting-state and task-driven BOLD variability are differentially related to cognition, as they may be driven by distinct sources of variance in the BOLD signal. Moreover, other studies have suggested that age differences in resting-state BOLD variability may be particularly sensitive to individual differences in cardiovascular, rather than neural, factors. In this study, we tested relationships between measures of behavioral task performance and BOLD variability during both resting-state and task-driven runs of a Stroop and an animacy judgment task in a large, well-characterized sample of cognitively normal middle-aged to older adults. Resting-state BOLD variability was related to composite measures of global cognition and attentional control, but these relationships were eliminated after correction for age or cardiovascular estimates. In contrast, task-driven BOLD variability was related to attentional control measured both inside and outside the scanner, and importantly, these relationships persisted after correction for age and cardiovascular measures. Overall, these results suggest that BOLD variability is a behaviorally sensitive signal. However, resting-state and task-driven estimates of BOLD variability may differ in the degree to which they are sensitive to age-related, cardiovascular, and neural mechanisms.

Evaluating resting-state BOLD variability in relation to biomarkers of preclinical Alzheimer's disease

Recent functional magnetic resonance imaging studies have demonstrated that moment-to-moment variability in the blood oxygen level-dependent (BOLD) signal is related to age differences, cognition, and symptomatic Alzheimer's disease (AD). However, no studies have examined BOLD variability in the context of preclinical AD. We tested relationships between resting-state BOLD variability and biomarkers of amyloidosis, tauopathy, and neurodegeneration in a large (N = 321), well-characterized sample of cognitively normal adults (age = 39-93), using multivariate machine learning techniques. Furthermore, we controlled for cardiovascular health factors, which may contaminate resting-state BOLD variability estimates. BOLD variability, particularly in the default mode network, was related to cerebrospinal fluid (CSF) amyloid-β42 but was not related to CSF phosphorylated tau-181. Furthermore, BOLD variability estimates were also related to markers of neurodegeneration, including CSF neurofilament light protein, hippocampal volume, and a cortical thickness composite. Notably, relationships with hippocampal volume and cortical thickness survived correction for cardiovascular health and also contributed to age-related differences in BOLD variability. Thus, BOLD variability may be sensitive to preclinical pathology, including amyloidosis and neurodegeneration in AD-sensitive areas.

Evaluating the Sensitivity of Resting-State BOLD Variability to Age and Cognition after Controlling for Motion and Cardiovascular Influences: A Network-Based Approach

Recent functional magnetic resonance imaging (fMRI) studies report that moment-to-moment variability in the BOLD signal is related to differences in age and cognition and, thus, may be sensitive to age-dependent decline. However, head motion and/or cardiovascular health (CVH) may contaminate these relationships. We evaluated relationships between resting-state BOLD variability, age, and cognition, after characterizing and controlling for motion-related and cardiovascular influences, including pulse, blood pressure, BMI, and white matter hyperintensities (WMH), in a large (N = 422) resting-state fMRI sample of cognitively normal individuals (age 43-89). We found that resting-state BOLD variability was negatively related to age and positively related to cognition after maximally controlling for head motion. Age relationships also survived correction for CVH, but were greatly reduced when correcting for WMH alone. Our results suggest that network-based machine learning analyses of resting-state BOLD variability might yield reliable, sensitive measures to characterize age-related decline across a broad range of networks. Age-related differences in resting-state BOLD variability may be largely sensitive to processes related to WMH burden.

The New Tics study: A Novel Approach to Pathophysiology and Cause of Tic Disorders

We report on the ongoing project "The New Tics Study: A Novel Approach to Pathophysiology and Cause of Tic Disorders," describing the work completed to date, ongoing studies and long-term goals. The overall goals of this research are to study the pathophysiology of Provisional Tic Disorder, and to study tic remission (or improvement) in a prospective fashion. Preliminary data collection for the project began almost 10 years ago. The current study is nearing completion of its third year, and has already reported several novel and important results. First, surprisingly, at least 90% of children who had experienced tics for only a mean of 3 months still had tics at the 12-month anniversary of their first tic, though in some cases tics were seen only with remote video observation of the child sitting alone. Thus almost all of them now had a DSM-5 diagnosis of Tourette's Disorder or Persistent (Chronic) Tic Disorder. Baseline clinical features that predicted 12-month outcome included tic severity, subsyndromal autism spectrum symptoms, an anxiety disorder, and a history of 3 or more phonic tics. Second, we found that poorer tic suppression ability when immediately rewarded for suppression predicted greater tic severity at follow-up. Third, striatal volumes did not predict outcome as hypothesized, but a larger hippocampus at baseline predicted worse severity at follow-up. Enrollment and data collection continue, including functional connectivity MRI (fcMRI) imaging, and additional analyses are planned once the full sample is enrolled.