Different scaling of linear models and deep learning in UKBiobank brain images versus machine-learning datasets

Deep learning based automatic detection and dipole estimation of epileptic discharges in MEG: a multi-center study

Magnetoencephalography (MEG) provides crucial information in diagnosing focal epilepsy. However, dipole estimation, a commonly used analysis method for MEG, can be time-consuming since it necessitates neurophysiologists to manually identify epileptic spikes. To reduce this burden, we developed the automatic detection of spikes using deep learning in single center. In this study, we performed a multi-center study using six MEG centers to improve the performance of the automated detection of neuromagnetically recorded epileptic spikes, which we previously developed using deep learning. Data from four centers were used for training and evaluation (internal data), and the remaining two centers were used for evaluation only (external data). We used a five-fold subject-wise cross-validation technique to train and evaluate the models. A comparison showed that the multi-center model outperformed the single-center model in terms of performance. The multi-center model achieved an average ROC-AUC of 0.9929 and 0.9426 for the internal and external data, respectively. The median distance between the neurophysiologist-analyzed and automatically analyzed dipoles was 4.36 and 7.23 mm for the multi-center model for internal and external data, respectively, indicating accurate detection of epileptic spikes. By training data from multiple centers, automated analysis can improve spike detection and reduce the analysis workload for neurophysiologists. This study suggests that the multi-center model has the potential to detect spikes within 1 cm of a neurophysiologist's analysis. This multi-center model can significantly reduce the number of hours required by neurophysiologists to detect spikes.

Advances and challenges in neuroimaging-based pain biomarkers

Identifying neural biomarkers of pain has long been a central theme in pain neuroscience. Here, we review the state-of-the-art candidates for neural biomarkers of acute and chronic pain. We classify these potential neural biomarkers into five categories based on the nature of their target variables, including neural biomarkers of (1) within-individual perception, (2) between-individual sensitivity, and (3) discriminability for acute pain, as well as (4) assessment and (5) prospective neural biomarkers for chronic pain. For each category, we provide a synthesized review of candidate biomarkers developed using neuroimaging techniques including functional magnetic resonance imaging (fMRI), structural magnetic resonance imaging (sMRI), and electroencephalography (EEG). We also discuss the conceptual and practical challenges in developing neural biomarkers of pain. Addressing these challenges, optimal biomarkers of pain can be developed to deepen our understanding of how the brain represents pain and ultimately help alleviate patients' suffering and improve their well-being.

Functional dysconnectivity of visual and somatomotor networks yields a simple and robust biomarker for psychosis

People with psychosis exhibit thalamo-cortical hyperconnectivity and cortico-cortical hypoconnectivity with sensory networks, however, it remains unclear if this applies to all sensory networks, whether it arises from other illness factors, or whether such differences could form the basis of a viable biomarker. To address the foregoing, we harnessed data from the Human Connectome Early Psychosis Project and computed resting-state functional connectivity (RSFC) matrices for 54 healthy controls and 105 psychosis patients. Primary visual, secondary visual ("visual2"), auditory, and somatomotor networks were defined via a recent brain network partition. RSFC was determined for 718 regions via regularized partial correlation. Psychosis patients-both affective and non-affective-exhibited cortico-cortical hypoconnectivity and thalamo-cortical hyperconnectivity in somatomotor and visual2 networks but not in auditory or primary visual networks. When we averaged and normalized the visual2 and somatomotor network connections, and subtracted the thalamo-cortical and cortico-cortical connectivity values, a robust psychosis biomarker emerged (p = 2e-10, Hedges' g = 1.05). This "somato-visual" biomarker was present in antipsychotic-naive patients and did not depend on confounds such as psychiatric comorbidities, substance/nicotine use, stress, anxiety, or demographics. It had moderate test-retest reliability (ICC = 0.62) and could be recovered in five-minute scans. The marker could discriminate groups in leave-one-site-out cross-validation (AUC = 0.79) and improve group classification upon being added to a well-known neurocognition task. Finally, it could differentiate later-stage psychosis patients from healthy or ADHD controls in two independent data sets. These results introduce a simple and robust RSFC biomarker that can distinguish psychosis patients from controls by the early illness stages.

Analyzing speed-difference impact on freeway joint injury severities of Leading-Following vehicles using statistical and data-driven models

Rear-end (RE) crashes are notably prevalent and pose a substantial risk on freeways. This paper explores the correlation between speed difference among the following and leading vehicles (Δν) and RE crash risk. Three joint models, comprising both uncorrelated and correlated joint random-parameters bivariate probit (RPBP) approaches (statistical methods) and a cross-stitch multilayer perceptron (CS-MLP) network (a data-driven method), were estimated and compared against three separate models: Support Vector Machines (SVM), eXtreme Gradient Boosting (XGBoost), and MLP networks (all data-driven methods). Data on 15,980 two-vehicle RE crashes were collected over a two-year period, from January 1, 2021, to December 31, 2022, considering two possible levels of injury severity: no injury and injury/fatality for both drivers of following and leading vehicles. The comparative performance analysis demonstrates the superior predictive capability of the CS-MLP network over the uncorrelated/correlated joint RPBP model, SVM, XGBoost, and MLP networks in terms of recall, F-1 Score, and AUC. Significantly, numerous shared variables influence the injury severity outcomes for the following and leading vehicles across both statistical and data-driven approaches. Among these factors, the following vehicle (a truck) and the leading vehicle (a passenger car) demonstrate contrasting effects on the injury severity outcomes for both vehicles. Furthermore, the SHapley Additive exPlanations (SHAP) values from the CS-MLP network visually show the relationship between Δν and injury severity, revealing non-linear trends unlike the average effects shown by statistical methods. They indicate that the least injury outcomes for both following and leading vehicles occurs at a Δν of 0 to 10 mph, matching observed patterns in RE crash data. Additionally, a marked variation in the trend of SHAP values for the two vehicles is noted as the speed difference increases. Therefore, the findings affirm the superior performance of joint model development and substantiate the non-linear impacts of speed difference on injury outcomes. The adoption of dynamic speed control measures is recommended to mitigate the injury outcomes involved in two-vehicle RE crashes.

Power and reproducibility in the external validation of brain-phenotype predictions

Brain-phenotype predictive models seek to identify reproducible and generalizable brain-phenotype associations. External validation, or the evaluation of a model in external datasets, is the gold standard in evaluating the generalizability of models in neuroimaging. Unlike typical studies, external validation involves two sample sizes: the training and the external sample sizes. Thus, traditional power calculations may not be appropriate. Here we ran over 900 million resampling-based simulations in functional and structural connectivity data to investigate the relationship between training sample size, external sample size, phenotype effect size, theoretical power and simulated power. Our analysis included a wide range of datasets: the Healthy Brain Network, the Adolescent Brain Cognitive Development Study, the Human Connectome Project (Development and Young Adult), the Philadelphia Neurodevelopmental Cohort, the Queensland Twin Adolescent Brain Project, and the Chinese Human Connectome Project; and phenotypes: age, body mass index, matrix reasoning, working memory, attention problems, anxiety/depression symptoms and relational processing. High effect size predictions achieved adequate power with training and external sample sizes of a few hundred individuals, whereas low and medium effect size predictions required hundreds to thousands of training and external samples. In addition, most previous external validation studies used sample sizes prone to low power, and theoretical power curves should be adjusted for the training sample size. Furthermore, model performance in internal validation often informed subsequent external validation performance (Pearson's r difference <0.2), particularly for well-harmonized datasets. These results could help decide how to power future external validation studies.

MRI economics: Balancing sample size and scan duration in brain wide association studies

A pervasive dilemma in neuroimaging is whether to prioritize sample size or scan time given fixed resources. Here, we systematically investigate this trade-off in the context of brain-wide association studies (BWAS) using functional magnetic resonance imaging (fMRI). We find that total scan duration (sample size × scan time per participant) robustly explains individual-level phenotypic prediction accuracy via a logarithmic model, suggesting that sample size and scan time are broadly interchangeable up to 20-30 min of data. However, the returns of scan time diminish relative to sample size, which we explain with principled theoretical derivations. When accounting for fixed overhead costs associated with each participant (e.g., recruitment, non-imaging measures), prediction accuracy in many small-scale and some large-scale BWAS might benefit from longer scan time than typically assumed. These results generalize across phenotypic domains, scanners, acquisition protocols, racial groups, mental disorders, age groups, as well as resting-state and task-state functional connectivity. Overall, our study emphasizes the importance of scan time, which is ignored in standard power calculations. Standard power calculations maximize sample size, at the expense of scan time, which can result in sub-optimal prediction accuracies and inefficient use of resources. Our empirically informed reference is available for future study design: WEB_APPLICATION_LINK.

Functional dysconnectivity of visual and somatomotor networks yields a simple and robust biomarker for psychosis

People with psychosis exhibit thalamo-cortical hyperconnectivity and cortico-cortical hypoconnectivity with sensory networks, however, it remains unclear if this applies to all sensory networks, whether it arises from other illness factors, or whether such differences could form the basis of a viable biomarker. To address the foregoing, we harnessed data from the Human Connectome Early Psychosis Project and computed resting-state functional connectivity (RSFC) matrices for 54 healthy controls and 105 psychosis patients. Primary visual, secondary visual ("visual2"), auditory, and somatomotor networks were defined via a recent brain network partition. RSFC was determined for 718 regions via regularized partial correlation. Psychosis patients- both affective and non-affective-exhibited cortico-cortical hypoconnectivity and thalamo-cortical hyperconnectivity in somatomotor and visual2 networks but not in auditory or primary visual networks. When we averaged and normalized the visual2 and somatomotor network connections, and subtracted the thalamo-cortical and cortico-cortical connectivity values, a robust psychosis biomarker emerged (p=2e-10, Hedges' g=1.05). This "somato-visual" biomarker was present in antipsychotic-naive patients and did not depend on confounds such as psychiatric comorbidities, substance/nicotine use, stress, anxiety, or demographics. It had moderate test-retest reliability (ICC=.61) and could be recovered in five-minute scans. The marker could discriminate groups in leave-one-site-out cross-validation (AUC=.79) and improve group classification upon being added to a well-known neurocognition task. Finally, it could differentiate later-stage psychosis patients from healthy or ADHD controls in two independent data sets. These results introduce a simple and robust RSFC biomarker that can distinguish psychosis patients from controls by the early illness stages.

Normative Neuroimaging Library: Designing a Comprehensive and Demographically Diverse Dataset of Healthy Controls to Support Traumatic Brain Injury Diagnostic and Therapeutic Development

The past decade has seen impressive advances in neuroimaging, moving from qualitative to quantitative outputs. Available techniques now allow for the inference of microscopic changes occurring in white and gray matter, along with alterations in physiology and function. These existing and emerging techniques hold the potential of providing unprecedented capabilities in achieving a diagnosis and predicting outcomes for traumatic brain injury (TBI) and a variety of other neurological diseases. To see this promise move from the research lab into clinical care, an understanding is needed of what normal data look like for all age ranges, sex, and other demographic and socioeconomic categories. Clinicians can only use the results of imaging scans to support their decision-making if they know how the results for their patient compare with a normative standard. This potential for utilizing magnetic resonance imaging (MRI) in TBI diagnosis motivated the American College of Radiology and Cohen Veterans Bioscience to create a reference database of healthy individuals with neuroimaging, demographic data, and characterization of psychological functioning and neurocognitive data that will serve as a normative resource for clinicians and researchers for development of diagnostics and therapeutics for TBI and other brain disorders. The goal of this article is to introduce the large, well-curated Normative Neuroimaging Library (NNL) to the research community. NNL consists of data collected from ∼1900 healthy participants. The highlights of NNL are (1) data are collected across a diverse population, including civilians, veterans, and active-duty service members with an age range (18-64 years) not well represented in existing datasets; (2) comprehensive structural and functional neuroimaging acquisition with state-of-the-art sequences (including structural, diffusion, and functional MRI; raw scanner data are preserved, allowing higher quality data to be derived in the future; standardized imaging acquisition protocols across sites reflect sequences and parameters often recommended for use with various neurological and psychiatric conditions, including TBI, post-traumatic stress disorder, stroke, neurodegenerative disorders, and neoplastic disease); and (3) the collection of comprehensive demographic details, medical history, and a broad structured clinical assessment, including cognition and psychological scales, relevant to multiple neurological conditions with functional sequelae. Thus, NNL provides a demographically diverse population of healthy individuals who can serve as a comparison group for brain injury study and clinical samples, providing a strong foundation for precision medicine. Use cases include the creation of imaging-derived phenotypes (IDPs), derivation of reference ranges of imaging measures, and use of IDPs as training samples for artificial intelligence-based biomarker development and for normative modeling to help identify injury-induced changes as outliers for precision diagnosis and targeted therapeutic development. On its release, NNL is poised to support the use of advanced imaging in clinician decision support tools, the validation of imaging biomarkers, and the investigation of brain-behavior anomalies, moving the field toward precision medicine.

Progress and trends in neurological disorders research based on deep learning

In recent years, deep learning (DL) has emerged as a powerful tool in clinical imaging, offering unprecedented opportunities for the diagnosis and treatment of neurological disorders (NDs). This comprehensive review explores the multifaceted role of DL techniques in leveraging vast datasets to advance our understanding of NDs and improve clinical outcomes. Beginning with a systematic literature review, we delve into the utilization of DL, particularly focusing on multimodal neuroimaging data analysis-a domain that has witnessed rapid progress and garnered significant scientific interest. Our study categorizes and critically analyses numerous DL models, including Convolutional Neural Networks (CNNs), LSTM-CNN, GAN, and VGG, to understand their performance across different types of Neurology Diseases. Through particular analysis, we identify key benchmarks and datasets utilized in training and testing DL models, shedding light on the challenges and opportunities in clinical neuroimaging research. Moreover, we discuss the effectiveness of DL in real-world clinical scenarios, emphasizing its potential to revolutionize ND diagnosis and therapy. By synthesizing existing literature and describing future directions, this review not only provides insights into the current state of DL applications in ND analysis but also covers the way for the development of more efficient and accessible DL techniques. Finally, our findings underscore the transformative impact of DL in reshaping the landscape of clinical neuroimaging, offering hope for enhanced patient care and groundbreaking discoveries in the field of neurology. This review paper is beneficial for neuropathologists and new researchers in this field.

Contributions of network structure, chemoarchitecture and diagnostic categories to transitions between cognitive topographies

The mechanisms linking the brain's network structure to cognitively relevant activation patterns remain largely unknown. Here, by leveraging principles of network control, we show how the architecture of the human connectome shapes transitions between 123 experimentally defined cognitive activation maps (cognitive topographies) from the NeuroSynth meta-analytic database. Specifically, we systematically integrated large-scale multimodal neuroimaging data from functional magnetic resonance imaging, diffusion tractography, cortical morphometry and positron emission tomography to simulate how anatomically guided transitions between cognitive states can be reshaped by neurotransmitter engagement or by changes in cortical thickness. Our model incorporates neurotransmitter-receptor density maps (18 receptors and transporters) and maps of cortical thickness pertaining to a wide range of mental health, neurodegenerative, psychiatric and neurodevelopmental diagnostic categories (17,000 patients and 22,000 controls). The results provide a comprehensive look-up table charting how brain network organization and chemoarchitecture interact to manifest different cognitive topographies, and establish a principled foundation for the systematic identification of ways to promote selective transitions between cognitive topographies.

Prognostic enrichment for early-stage Huntington's disease: An explainable machine learning approach for clinical trial

BACKGROUND

In Huntington's disease clinical trials, recruitment and stratification approaches primarily rely on genetic load, cognitive and motor assessment scores. They focus less on in vivo brain imaging markers, which reflect neuropathology well before clinical diagnosis. Machine learning methods offer a degree of sophistication which could significantly improve prognosis and stratification by leveraging multimodal biomarkers from large datasets. Such models specifically tailored to HD gene expansion carriers could further enhance the efficacy of the stratification process.

OBJECTIVES

To improve stratification of Huntington's disease individuals for clinical trials.

METHODS

We used data from 451 gene positive individuals with Huntington's disease (both premanifest and diagnosed) from previously published cohorts (PREDICT, TRACK, TrackON, and IMAGE). We applied whole-brain parcellation to longitudinal brain scans and measured the rate of lateral ventricular enlargement, over 3 years, which was used as the target variable for our prognostic random forest regression models. The models were trained on various combinations of features at baseline, including genetic load, cognitive and motor assessment score biomarkers, as well as brain imaging-derived features. Furthermore, a simplified stratification model was developed to classify individuals into two homogenous groups (low risk and high risk) based on their anticipated rate of ventricular enlargement.

RESULTS

The predictive accuracy of the prognostic models substantially improved by integrating brain imaging features alongside genetic load, cognitive and motor biomarkers: a 24 % reduction in the cross-validated mean absolute error, yielding an error of 530 mm3/year. The stratification model had a cross-validated accuracy of 81 % in differentiating between moderate and fast progressors (precision = 83 %, recall = 80 %).

CONCLUSIONS

This study validated the effectiveness of machine learning in differentiating between low- and high-risk individuals based on the rate of ventricular enlargement. The models were exclusively trained using features from HD individuals, which offers a more disease-specific, simplified, and accurate approach for prognostic enrichment compared to relying on features extracted from healthy control groups, as done in previous studies. The proposed method has the potential to enhance clinical utility by: i) enabling more targeted recruitment of individuals for clinical trials, ii) improving post-hoc evaluation of individuals, and iii) ultimately leading to better outcomes for individuals through personalized treatment selection.

Nonlinear latent representations of high-dimensional task-fMRI data: Unveiling cognitive and behavioral insights in heterogeneous spatial maps

Finding an interpretable and compact representation of complex neuroimaging data is extremely useful for understanding brain behavioral mapping and hence for explaining the biological underpinnings of mental disorders. However, hand-crafted representations, as well as linear transformations, may inadequately capture the considerable variability across individuals. Here, we implemented a data-driven approach using a three-dimensional autoencoder on two large-scale datasets. This approach provides a latent representation of high-dimensional task-fMRI data which can account for demographic characteristics whilst also being readily interpretable both in the latent space learned by the autoencoder and in the original voxel space. This was achieved by addressing a joint optimization problem that simultaneously reconstructs the data and predicts clinical or demographic variables. We then applied normative modeling to the latent variables to define summary statistics ('latent indices') and establish a multivariate mapping to non-imaging measures. Our model, trained with multi-task fMRI data from the Human Connectome Project (HCP) and UK biobank task-fMRI data, demonstrated high performance in age and sex predictions and successfully captured complex behavioral characteristics while preserving individual variability through a latent representation. Our model also performed competitively with respect to various baseline models including several variants of principal components analysis, independent components analysis and classical regions of interest, both in terms of reconstruction accuracy and strength of association with behavioral variables.

Exploring the potential of representation and transfer learning for anatomical neuroimaging: Application to psychiatry

The perspective of personalized medicine for brain disorders requires efficient learning models for anatomical neuroimaging-based prediction of clinical conditions. There is now a consensus on the benefit of deep learning (DL) in addressing many medical imaging tasks, such as image segmentation. However, for single-subject prediction problems, recent studies yielded contradictory results when comparing DL with Standard Machine Learning (SML) on top of classical feature extraction. Most existing comparative studies were limited in predicting phenotypes of little clinical interest, such as sex and age, and using a single dataset. Moreover, they conducted a limited analysis of the employed image pre-processing and feature selection strategies. This paper extensively compares DL and SML prediction capacity on five multi-site problems, including three increasingly complex clinical applications in psychiatry namely schizophrenia, bipolar disorder, and Autism Spectrum Disorder (ASD) diagnosis. To compensate for the relative scarcity of neuroimaging data on these clinical datasets, we also evaluate three pre-training strategies for transfer learning from brain imaging of the general healthy population: self-supervised learning, generative modeling and supervised learning with age. Overall, we find similar performance between randomly initialized DL and SML for the three clinical tasks and a similar scaling trend for sex prediction. This was replicated on an external dataset. We also show highly correlated discriminative brain regions between DL and linear ML models in all problems. Nonetheless, we demonstrate that self-supervised pre-training on large-scale healthy population imaging datasets (N≈10k), along with Deep Ensemble, allows DL to learn robust and transferable representations to smaller-scale clinical datasets (N≤1k). It largely outperforms SML on 2 out of 3 clinical tasks both in internal and external test sets. These findings suggest that the improvement of DL over SML in anatomical neuroimaging mainly comes from its capacity to learn meaningful and useful abstract representations of the brain anatomy, and it sheds light on the potential of transfer learning for personalized medicine in psychiatry.

A synergistic workspace for human consciousness revealed by Integrated Information Decomposition

How is the information-processing architecture of the human brain organised, and how does its organisation support consciousness? Here, we combine network science and a rigorous information-theoretic notion of synergy to delineate a 'synergistic global workspace', comprising gateway regions that gather synergistic information from specialised modules across the human brain. This information is then integrated within the workspace and widely distributed via broadcaster regions. Through functional MRI analysis, we show that gateway regions of the synergistic workspace correspond to the human brain's default mode network, whereas broadcasters coincide with the executive control network. We find that loss of consciousness due to general anaesthesia or disorders of consciousness corresponds to diminished ability of the synergistic workspace to integrate information, which is restored upon recovery. Thus, loss of consciousness coincides with a breakdown of information integration within the synergistic workspace of the human brain. This work contributes to conceptual and empirical reconciliation between two prominent scientific theories of consciousness, the Global Neuronal Workspace and Integrated Information Theory, while also advancing our understanding of how the human brain supports consciousness through the synergistic integration of information.

Brain-age prediction: Systematic evaluation of site effects, and sample age range and size

Structural neuroimaging data have been used to compute an estimate of the biological age of the brain (brain-age) which has been associated with other biologically and behaviorally meaningful measures of brain development and aging. The ongoing research interest in brain-age has highlighted the need for robust and publicly available brain-age models pre-trained on data from large samples of healthy individuals. To address this need we have previously released a developmental brain-age model. Here we expand this work to develop, empirically validate, and disseminate a pre-trained brain-age model to cover most of the human lifespan. To achieve this, we selected the best-performing model after systematically examining the impact of seven site harmonization strategies, age range, and sample size on brain-age prediction in a discovery sample of brain morphometric measures from 35,683 healthy individuals (age range: 5-90 years; 53.59% female). The pre-trained models were tested for cross-dataset generalizability in an independent sample comprising 2101 healthy individuals (age range: 8-80 years; 55.35% female) and for longitudinal consistency in a further sample comprising 377 healthy individuals (age range: 9-25 years; 49.87% female). This empirical examination yielded the following findings: (1) the accuracy of age prediction from morphometry data was higher when no site harmonization was applied; (2) dividing the discovery sample into two age-bins (5-40 and 40-90 years) provided a better balance between model accuracy and explained age variance than other alternatives; (3) model accuracy for brain-age prediction plateaued at a sample size exceeding 1600 participants. These findings have been incorporated into CentileBrain (https://centilebrain.org/#/brainAGE2), an open-science, web-based platform for individualized neuroimaging metrics.

Individual characteristics outperform resting-state fMRI for the prediction of behavioral phenotypes

In this study, we aimed to compare imaging-based features of brain function, measured by resting-state fMRI (rsfMRI), with individual characteristics such as age, gender, and total intracranial volume to predict behavioral measures. We developed a machine learning framework based on rsfMRI features in a dataset of 20,000 healthy individuals from the UK Biobank, focusing on temporal complexity and functional connectivity measures. Our analysis across four behavioral phenotypes revealed that both temporal complexity and functional connectivity measures provide comparable predictive performance. However, individual characteristics consistently outperformed rsfMRI features in predictive accuracy, particularly in analyses involving smaller sample sizes. Integrating rsfMRI features with demographic data sometimes enhanced predictive outcomes. The efficacy of different predictive modeling techniques and the choice of brain parcellation atlas were also examined, showing no significant influence on the results. To summarize, while individual characteristics are superior to rsfMRI in predicting behavioral phenotypes, rsfMRI still conveys additional predictive value in the context of machine learning, such as investigating the role of specific brain regions in behavioral phenotypes.

Distinct brain morphometry patterns revealed by deep learning improve prediction of post-stroke aphasia severity

BACKGROUND

Emerging evidence suggests that post-stroke aphasia severity depends on the integrity of the brain beyond the lesion. While measures of lesion anatomy and brain integrity combine synergistically to explain aphasic symptoms, substantial interindividual variability remains unaccounted. One explanatory factor may be the spatial distribution of morphometry beyond the lesion (e.g., atrophy), including not just specific brain areas, but distinct three-dimensional patterns.

METHODS

Here, we test whether deep learning with Convolutional Neural Networks (CNNs) on whole brain morphometry (i.e., segmented tissue volumes) and lesion anatomy better predicts chronic stroke individuals with severe aphasia (N = 231) than classical machine learning (Support Vector Machines; SVMs), evaluating whether encoding spatial dependencies identifies uniquely predictive patterns.

RESULTS

CNNs achieve higher balanced accuracy and F1 scores, even when SVMs are nonlinear or integrate linear or nonlinear dimensionality reduction. Parity only occurs when SVMs access features learned by CNNs. Saliency maps demonstrate that CNNs leverage distributed morphometry patterns, whereas SVMs focus on the area around the lesion. Ensemble clustering of CNN saliencies reveals distinct morphometry patterns unrelated to lesion size, consistent across individuals, and which implicate unique networks associated with different cognitive processes as measured by the wider neuroimaging literature. Individualized predictions depend on both ipsilateral and contralateral features outside the lesion.

CONCLUSIONS

Three-dimensional network distributions of morphometry are directly associated with aphasia severity, underscoring the potential for CNNs to improve outcome prognostication from neuroimaging data, and highlighting the prospective benefits of interrogating spatial dependence at different scales in multivariate feature space.

Systematic evaluation of fMRI data-processing pipelines for consistent functional connectomics

Functional interactions between brain regions can be viewed as a network, enabling neuroscientists to investigate brain function through network science. Here, we systematically evaluate 768 data-processing pipelines for network reconstruction from resting-state functional MRI, evaluating the effect of brain parcellation, connectivity definition, and global signal regression. Our criteria seek pipelines that minimise motion confounds and spurious test-retest discrepancies of network topology, while being sensitive to both inter-subject differences and experimental effects of interest. We reveal vast and systematic variability across pipelines' suitability for functional connectomics. Inappropriate choice of data-processing pipeline can produce results that are not only misleading, but systematically so, with the majority of pipelines failing at least one criterion. However, a set of optimal pipelines consistently satisfy all criteria across different datasets, spanning minutes, weeks, and months. We provide a full breakdown of each pipeline's performance across criteria and datasets, to inform future best practices in functional connectomics.

Machine to brain: facial expression recognition using brain machine generative adversarial networks

The human brain can effectively perform Facial Expression Recognition (FER) with a few samples by utilizing its cognitive ability. However, unlike the human brain, even the well-trained deep neural network is data-dependent and lacks cognitive ability. To tackle this challenge, this paper proposes a novel framework, Brain Machine Generative Adversarial Networks (BM-GAN), which utilizes the concept of brain's cognitive ability to guide a Convolutional Neural Network to generate LIKE-electroencephalograph (EEG) features. More specifically, we firstly obtain EEG signals triggered from facial emotion images, then we adopt BM-GAN to carry out the mutual generation of image visual features and EEG cognitive features. BM-GAN intends to use the cognitive knowledge learnt from EEG signals to instruct the model to perceive LIKE-EEG features. Thereby, BM-GAN has a superior performance for FER like the human brain. The proposed model consists of VisualNet, EEGNet, and BM-GAN. More specifically, VisualNet can obtain image visual features from facial emotion images and EEGNet can obtain EEG cognitive features from EEG signals. Subsequently, the BM-GAN completes the mutual generation of image visual features and EEG cognitive features. Finally, the predicted LIKE-EEG features of test images are used for FER. After learning, without the participation of the EEG signals, an average classification accuracy of 96.6 % is obtained on Chinese Facial Affective Picture System dataset using LIKE-EEG features for FER. Experiments demonstrate that the proposed method can produce an excellent performance for FER.

Deep Learning and Multimodal Artificial Intelligence in Orthopaedic Surgery

This review article focuses on the applications of deep learning with neural networks and multimodal neural networks in the orthopaedic domain. By providing practical examples of how artificial intelligence (AI) is being applied successfully in orthopaedic surgery, particularly in the realm of imaging data sets and the integration of clinical data, this study aims to provide orthopaedic surgeons with the necessary tools to not only evaluate existing literature but also to consider AI's potential in their own clinical or research pursuits. We first review standard deep neural networks which can analyze numerical clinical variables, then describe convolutional neural networks which can analyze image data, and then introduce multimodal AI models which analyze various types of different data. Then, we contrast these deep learning techniques with related but more limited techniques such as radiomics, describe how to interpret deep learning studies, and how to initiate such studies at your institution. Ultimately, by empowering orthopaedic surgeons with the knowledge and know-how of deep learning, this review aspires to facilitate the translation of research into clinical practice, thereby enhancing the efficacy and precision of real-world orthopaedic care for patients.

Single-cell genomics and regulatory networks for 388 human brains

Single-cell genomics is a powerful tool for studying heterogeneous tissues such as the brain. Yet little is understood about how genetic variants influence cell-level gene expression. Addressing this, we uniformly processed single-nuclei, multiomics datasets into a resource comprising >2.8 million nuclei from the prefrontal cortex across 388 individuals. For 28 cell types, we assessed population-level variation in expression and chromatin across gene families and drug targets. We identified >550,000 cell type-specific regulatory elements and >1.4 million single-cell expression quantitative trait loci, which we used to build cell-type regulatory and cell-to-cell communication networks. These networks manifest cellular changes in aging and neuropsychiatric disorders. We further constructed an integrative model accurately imputing single-cell expression and simulating perturbations; the model prioritized ~250 disease-risk genes and drug targets with associated cell types.

Computational limits to the legibility of the imaged human brain

Our knowledge of the organisation of the human brain at the population-level is yet to translate into power to predict functional differences at the individual-level, limiting clinical applications and casting doubt on the generalisability of inferred mechanisms. It remains unknown whether the difficulty arises from the absence of individuating biological patterns within the brain, or from limited power to access them with the models and compute at our disposal. Here we comprehensively investigate the resolvability of such patterns with data and compute at unprecedented scale. Across 23 810 unique participants from UK Biobank, we systematically evaluate the predictability of 25 individual biological characteristics, from all available combinations of structural and functional neuroimaging data. Over 4526 GPU*hours of computation, we train, optimize, and evaluate out-of-sample 700 individual predictive models, including fully-connected feed-forward neural networks of demographic, psychological, serological, chronic disease, and functional connectivity characteristics, and both uni- and multi-modal 3D convolutional neural network models of macro- and micro-structural brain imaging. We find a marked discrepancy between the high predictability of sex (balanced accuracy 99.7%), age (mean absolute error 2.048 years, R2 0.859), and weight (mean absolute error 2.609Kg, R2 0.625), for which we set new state-of-the-art performance, and the surprisingly low predictability of other characteristics. Neither structural nor functional imaging predicted an individual's psychology better than the coincidence of common chronic disease (p < 0.05). Serology predicted chronic disease (p < 0.05) and was best predicted by it (p < 0.001), followed by structural neuroimaging (p < 0.05). Our findings suggest either more informative imaging or more powerful models will be needed to decipher individual level characteristics from the human brain. We make our models and code openly available.

Reliability and predictability of phenotype information from functional connectivity in large imaging datasets

One of the central objectives of contemporary neuroimaging research is to create predictive models that can disentangle the connection between patterns of functional connectivity across the entire brain and various behavioral traits. Previous studies have shown that models trained to predict behavioral features from the individual's functional connectivity have modest to poor performance. In this study, we trained models that predict observable individual traits (phenotypes) and their corresponding singular value decomposition (SVD) representations - herein referred to as latent phenotypes from resting state functional connectivity. For this task, we predicted phenotypes in two large neuroimaging datasets: the Human Connectome Project (HCP) and the Philadelphia Neurodevelopmental Cohort (PNC). We illustrate the importance of regressing out confounds, which could significantly influence phenotype prediction. Our findings reveal that both phenotypes and their corresponding latent phenotypes yield similar predictive performance. Interestingly, only the first five latent phenotypes were reliably identified, and using just these reliable phenotypes for predicting phenotypes yielded a similar performance to using all latent phenotypes. This suggests that the predictable information is present in the first latent phenotypes, allowing the remainder to be filtered out without any harm in performance. This study sheds light on the intricate relationship between functional connectivity and the predictability and reliability of phenotypic information, with potential implications for enhancing predictive modeling in the realm of neuroimaging research.

A Review of Machine Learning Algorithms for Biomedical Applications

As the amount and complexity of biomedical data continue to increase, machine learning methods are becoming a popular tool in creating prediction models for the underlying biomedical processes. Although all machine learning methods aim to fit models to data, the methodologies used can vary greatly and may seem daunting at first. A comprehensive review of various machine learning algorithms per biomedical applications is presented. The key concepts of machine learning are supervised and unsupervised learning, feature selection, and evaluation metrics. Technical insights on the major machine learning methods such as decision trees, random forests, support vector machines, and k-nearest neighbors are analyzed. Next, the dimensionality reduction methods like principal component analysis and t-distributed stochastic neighbor embedding methods, and their applications in biomedical data analysis were reviewed. Moreover, in biomedical applications predominantly feedforward neural networks, convolutional neural networks, and recurrent neural networks are utilized. In addition, the identification of emerging directions in machine learning methodology will serve as a useful reference for individuals involved in biomedical research, clinical practice, and related professions who are interested in understanding and applying machine learning algorithms in their research or practice.

Fusion of biomedical imaging studies for increased sample size and diversity: a case study of brain MRI

Data collection, curation, and cleaning constitute a crucial phase in Machine Learning (ML) projects. In biomedical ML, it is often desirable to leverage multiple datasets to increase sample size and diversity, but this poses unique challenges, which arise from heterogeneity in study design, data descriptors, file system organization, and metadata. In this study, we present an approach to the integration of multiple brain MRI datasets with a focus on homogenization of their organization and preprocessing for ML. We use our own fusion example (approximately 84,000 images from 54,000 subjects, 12 studies, and 88 individual scanners) to illustrate and discuss the issues faced by study fusion efforts, and we examine key decisions necessary during dataset homogenization, presenting in detail a database structure flexible enough to accommodate multiple observational MRI datasets. We believe our approach can provide a basis for future similarly-minded biomedical ML projects.

The 'middle-aging' brain

Middle age has historically been an understudied period of life compared to older age, when cognitive and brain health decline are most pronounced, but the scope for intervention may be limited. However, recent research suggests that middle age could mark a shift in brain aging. We review emerging evidence on multiple levels of analysis indicating that midlife is a period defined by unique central and peripheral processes that shape future cognitive trajectories and brain health. Informed by recent developments in aging research and lifespan studies in humans and animal models, we highlight the utility of modeling non-linear changes in study samples with wide subject age ranges to distinguish life stage-specific processes from those acting linearly throughout the lifespan.

SADXAI: Predicting social anxiety disorder using multiple interpretable artificial intelligence techniques

Social anxiety disorder (SAD), also known as social phobia, is a psychological condition in which a person has a persistent and overwhelming fear of being negatively judged or observed by other individuals. This fear can affect them at work, in relationships and other social activities. The intricate combination of several environmental and biological factors is the reason for the onset of this mental condition. SAD is diagnosed using a test called the "Diagnostic and Statistical Manual of Mental Health Disorders (DSM-5), which is based on several physical, emotional and demographic symptoms. Artificial Intelligence has been a boon for medicine and is regularly used to diagnose various health conditions and diseases. Hence, this study used demographic, emotional, and physical symptoms and multiple machine learning (ML) techniques to diagnose SAD. A thorough descriptive and statistical analysis has been conducted before using the classifiers. Among all the models, the AdaBoost and logistic regression obtained the highest accuracy of 88 % each. Four eXplainable artificial techniques (XAI) techniques are utilized to make the predictions interpretable, transparent and understandable. According to XAI, the "Liebowitz Social Anxiety Scale questionnaire" and "The fear of speaking in public" are the most critical attributes in the diagnosis of SAD. This clinical decision support system framework could be utilized in various suitable locations such as schools, hospitals and workplaces to identify SAD in people.

Single-cell genomics and regulatory networks for 388 human brains

Single-cell genomics is a powerful tool for studying heterogeneous tissues such as the brain. Yet, little is understood about how genetic variants influence cell-level gene expression. Addressing this, we uniformly processed single-nuclei, multi-omics datasets into a resource comprising >2.8M nuclei from the prefrontal cortex across 388 individuals. For 28 cell types, we assessed population-level variation in expression and chromatin across gene families and drug targets. We identified >550K cell-type-specific regulatory elements and >1.4M single-cell expression-quantitative-trait loci, which we used to build cell-type regulatory and cell-to-cell communication networks. These networks manifest cellular changes in aging and neuropsychiatric disorders. We further constructed an integrative model accurately imputing single-cell expression and simulating perturbations; the model prioritized ~250 disease-risk genes and drug targets with associated cell types.

Advancing glioma diagnosis: Integrating custom U-Net and VGG-16 for improved grading in MR imaging

In the realm of medical imaging, the precise segmentation and classification of gliomas represent fundamental challenges with profound clinical implications. Leveraging the BraTS 2018 dataset as a standard benchmark, this study delves into the potential of advanced deep learning models for addressing these challenges. We propose a novel approach that integrates a customized U-Net for segmentation and VGG-16 for classification. The U-Net, with its tailored encoder-decoder pathways, accurately identifies glioma regions, thus improving tumor localization. The fine-tuned VGG-16, featuring a customized output layer, precisely differentiates between low-grade and high-grade gliomas. To ensure consistency in data pre-processing, a standardized methodology involving gamma correction, data augmentation, and normalization is introduced. This novel integration surpasses existing methods, offering significantly improved glioma diagnosis, validated by high segmentation dice scores (WT: 0.96, TC: 0.92, ET: 0.89), and a remarkable overall classification accuracy of 97.89%. The experimental findings underscore the potential of integrating deep learning-based methodologies for tumor segmentation and classification in enhancing glioma diagnosis and formulating subsequent treatment strategies.

On the stability of canonical correlation analysis and partial least squares with application to brain-behavior associations

Associations between datasets can be discovered through multivariate methods like Canonical Correlation Analysis (CCA) or Partial Least Squares (PLS). A requisite property for interpretability and generalizability of CCA/PLS associations is stability of their feature patterns. However, stability of CCA/PLS in high-dimensional datasets is questionable, as found in empirical characterizations. To study these issues systematically, we developed a generative modeling framework to simulate synthetic datasets. We found that when sample size is relatively small, but comparable to typical studies, CCA/PLS associations are highly unstable and inaccurate; both in their magnitude and importantly in the feature pattern underlying the association. We confirmed these trends across two neuroimaging modalities and in independent datasets with n ≈ 1000 and n = 20,000, and found that only the latter comprised sufficient observations for stable mappings between imaging-derived and behavioral features. We further developed a power calculator to provide sample sizes required for stability and reliability of multivariate analyses. Collectively, we characterize how to limit detrimental effects of overfitting on CCA/PLS stability, and provide recommendations for future studies.

Amplifying pathological detection in EEG signaling pathways through cross-dataset transfer learning

Pathology diagnosis based on EEG signals and decoding brain activity holds immense importance in understanding neurological disorders. With the advancement of artificial intelligence methods and machine learning techniques, the potential for accurate data-driven diagnoses and effective treatments has grown significantly. However, applying machine learning algorithms to real-world datasets presents diverse challenges at multiple levels. The scarcity of labeled data, especially in low regime scenarios with limited availability of real patient cohorts due to high costs of recruitment, underscores the vital deployment of scaling and transfer learning techniques. In this study, we explore a real-world pathology classification task to highlight the effectiveness of data and model scaling and cross-dataset knowledge transfer. As such, we observe varying performance improvements through data scaling, indicating the need for careful evaluation and labeling. Additionally, we identify the challenges of possible negative transfer and emphasize the significance of some key components to overcome distribution shifts and potential spurious correlations and achieve positive transfer. We see improvement in the performance of the target model on the target (NMT) datasets by using the knowledge from the source dataset (TUAB) when a low amount of labeled data was available. Our findings demonstrated that a small and generic model (e.g. ShallowNet) performs well on a single dataset, however, a larger model (e.g. TCN) performs better in transfer learning when leveraging a larger and more diverse dataset.

Performance reserves in brain-imaging-based phenotype prediction

This study examines the impact of sample size on predicting cognitive and mental health phenotypes from brain imaging via machine learning. Our analysis shows a 3- to 9-fold improvement in prediction performance when sample size increases from 1,000 to 1 M participants. However, despite this increase, the data suggest that prediction accuracy remains worryingly low and far from fully exploiting the predictive potential of brain imaging data. Additionally, we find that integrating multiple imaging modalities boosts prediction accuracy, often equivalent to doubling the sample size. Interestingly, the most informative imaging modality often varied with increasing sample size, emphasizing the need to consider multiple modalities. Despite significant performance reserves for phenotype prediction, achieving substantial improvements may necessitate prohibitively large sample sizes, thus casting doubt on the practical or clinical utility of machine learning in some areas of neuroimaging.

Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures

Machine learning (ML) techniques have gained popularity in the neuroimaging field due to their potential for classifying neuropsychiatric disorders. However, the diagnostic predictive power of the existing algorithms has been limited by small sample sizes, lack of representativeness, data leakage, and/or overfitting. Here, we overcome these limitations with the largest multi-site sample size to date (N = 5365) to provide a generalizable ML classification benchmark of major depressive disorder (MDD) using shallow linear and non-linear models. Leveraging brain measures from standardized ENIGMA analysis pipelines in FreeSurfer, we were able to classify MDD versus healthy controls (HC) with a balanced accuracy of around 62%. But after harmonizing the data, e.g., using ComBat, the balanced accuracy dropped to approximately 52%. Accuracy results close to random chance levels were also observed in stratified groups according to age of onset, antidepressant use, number of episodes and sex. Future studies incorporating higher dimensional brain imaging/phenotype features, and/or using more advanced machine and deep learning methods may yield more encouraging prospects.

Scaling behaviours of deep learning and linear algorithms for the prediction of stroke severity

Deep learning has allowed for remarkable progress in many medical scenarios. Deep learning prediction models often require 105-107 examples. It is currently unknown whether deep learning can also enhance predictions of symptoms post-stroke in real-world samples of stroke patients that are often several magnitudes smaller. Such stroke outcome predictions however could be particularly instrumental in guiding acute clinical and rehabilitation care decisions. We here compared the capacities of classically used linear and novel deep learning algorithms in their prediction of stroke severity. Our analyses relied on a total of 1430 patients assembled from the MRI-Genetics Interface Exploration collaboration and a Massachusetts General Hospital-based study. The outcome of interest was National Institutes of Health Stroke Scale-based stroke severity in the acute phase after ischaemic stroke onset, which we predict by means of MRI-derived lesion location. We automatically derived lesion segmentations from diffusion-weighted clinical MRI scans, performed spatial normalization and included a principal component analysis step, retaining 95% of the variance of the original data. We then repeatedly separated a train, validation and test set to investigate the effects of sample size; we subsampled the train set to 100, 300 and 900 and trained the algorithms to predict the stroke severity score for each sample size with regularized linear regression and an eight-layered neural network. We selected hyperparameters on the validation set. We evaluated model performance based on the explained variance (R2) in the test set. While linear regression performed significantly better for a sample size of 100 patients, deep learning started to significantly outperform linear regression when trained on 900 patients. Average prediction performance improved by ∼20% when increasing the sample size 9× [maximum for 100 patients: 0.279 ± 0.005 (R2, 95% confidence interval), 900 patients: 0.337 ± 0.006]. In summary, for sample sizes of 900 patients, deep learning showed a higher prediction performance than typically employed linear methods. These findings suggest the existence of non-linear relationships between lesion location and stroke severity that can be utilized for an improved prediction performance for larger sample sizes.

Improving Prediction of Complications Post-Proton Therapy in Lung Cancer Using Large Language Models and Meta-Analysis

PURPOSE

This study enhances the efficiency of predicting complications in lung cancer patients receiving proton therapy by utilizing large language models (LLMs) and meta-analytical techniques for literature quality assessment.

MATERIALS AND METHODS

We integrated systematic reviews with LLM evaluations, sourcing studies from Web of Science, PubMed, and Scopus, managed via EndNote X20. Inclusion and exclusion criteria ensured literature relevance. Techniques included meta-analysis, heterogeneity assessment using Cochran's Q test and I2 statistics, and subgroup analyses for different complications. Quality and bias risk were assessed using the PROBAST tool and further analyzed with models such as ChatGPT-4, Llama2-13b, and Llama3-8b. Evaluation metrics included AUC, accuracy, precision, recall, F1 score, and time efficiency (WPM).

RESULTS

The meta-analysis revealed an overall effect size of 0.78 for model predictions, with high heterogeneity observed (I2 = 72.88%, P < 0.001). Subgroup analysis for radiation-induced esophagitis and pneumonitis revealed predictive effect sizes of 0.79 and 0.77, respectively, with a heterogeneity index (I2) of 0%, indicating that there were no significant differences among the models in predicting these specific complications. A literature assessment using LLMs demonstrated that ChatGPT-4 achieved the highest accuracy at 90%, significantly outperforming the Llama3 and Llama2 models, which had accuracies ranging from 44% to 62%. Additionally, LLM evaluations were conducted 3229 times faster than manual assessments were, markedly enhancing both efficiency and accuracy. The risk assessment results identified nine studies as high risk, three as low risk, and one as unknown, confirming the robustness of the ChatGPT-4 across various evaluation metrics.

CONCLUSION

This study demonstrated that the integration of large language models with meta-analysis techniques can significantly increase the efficiency of literature evaluations and reduce the time required for assessments, confirming that there are no significant differences among models in predicting post proton therapy complications in lung cancer patients.

Review of artificial intelligence clinical applications in Nuclear Medicine

This paper provides an in-depth analysis of the clinical applications of artificial intelligence (AI) in Nuclear Medicine, focusing on three key areas: neurology, cardiology, and oncology. Beginning with neurology, specifically Alzheimer's disease and Parkinson's disease, the paper examines reviews on diagnosis and treatment planning. The same pattern is followed in cardiology studies. In the final section on oncology, the paper explores the various AI applications in multiple cancer types, including lung, head and neck, lymphoma, and pancreatic cancer.

Macroscopic resting-state brain dynamics are best described by linear models

It is typically assumed that large networks of neurons exhibit a large repertoire of nonlinear behaviours. Here we challenge this assumption by leveraging mathematical models derived from measurements of local field potentials via intracranial electroencephalography and of whole-brain blood-oxygen-level-dependent brain activity via functional magnetic resonance imaging. We used state-of-the-art linear and nonlinear families of models to describe spontaneous resting-state activity of 700 participants in the Human Connectome Project and 122 participants in the Restoring Active Memory project. We found that linear autoregressive models provide the best fit across both data types and three performance metrics: predictive power, computational complexity and the extent of the residual dynamics unexplained by the model. To explain this observation, we show that microscopic nonlinear dynamics can be counteracted or masked by four factors associated with macroscopic dynamics: averaging over space and over time, which are inherent to aggregated macroscopic brain activity, and observation noise and limited data samples, which stem from technological limitations. We therefore argue that easier-to-interpret linear models can faithfully describe macroscopic brain dynamics during resting-state conditions.

Multilayer meta-matching: translating phenotypic prediction models from multiple datasets to small data

Resting-state functional connectivity (RSFC) is widely used to predict phenotypic traits in individuals. Large sample sizes can significantly improve prediction accuracies. However, for studies of certain clinical populations or focused neuroscience inquiries, small-scale datasets often remain a necessity. We have previously proposed a "meta-matching" approach to translate prediction models from large datasets to predict new phenotypes in small datasets. We demonstrated large improvement of meta-matching over classical kernel ridge regression (KRR) when translating models from a single source dataset (UK Biobank) to the Human Connectome Project Young Adults (HCP-YA) dataset. In the current study, we propose two meta-matching variants ("meta-matching with dataset stacking" and "multilayer meta-matching") to translate models from multiple source datasets across disparate sample sizes to predict new phenotypes in small target datasets. We evaluate both approaches by translating models trained from five source datasets (with sample sizes ranging from 862 participants to 36,834 participants) to predict phenotypes in the HCP-YA and HCP-Aging datasets. We find that multilayer meta-matching modestly outperforms meta-matching with dataset stacking. Both meta-matching variants perform better than the original "meta-matching with stacking" approach trained only on the UK Biobank. All meta-matching variants outperform classical KRR and transfer learning by a large margin. In fact, KRR is better than classical transfer learning when less than 50 participants are available for finetuning, suggesting the difficulty of classical transfer learning in the very small sample regime. The multilayer meta-matching model is publicly available at GITHUB_LINK.

Brain cancer classification based on multistage ensemble generative adversarial network and convolutional neural network

An advanced approach that capitalizes on the synergies between multimodal feature fusion and the dual-path network is presented in this manuscript. Our proposed methodology harnesses a combination of potent techniques, merging the benefits of nonlinear mapping and expansive perception. The foundation of our methodology lies in leveraging well-established pretrained models, namely EfficientNet-B7, ResNet-152, and a meticulously crafted custom convolutional neural network (CNN), to effectively extract salient features from the data. These models are combined in a two-stage ensemble approach. We employ maximum variance unfolding (MVU) to select the most relevant attributes from the extracted features. In this study, we propose a hybrid approach that integrates a generative adversarial network and Neural Autoregressive Distribution Estimation (NADE-K) with a CNN. The resulting two-stage ensemble hybrid CNN model achieves an accuracy of 99.63%. The implementation of the two-stage ensemble hybrid CNN with MVU demonstrates significant improvements in brain tumor classification.

Human-to-monkey transfer learning identifies the frontal white matter as a key determinant for predicting monkey brain age

The application of artificial intelligence (AI) to summarize a whole-brain magnetic resonance image (MRI) into an effective "brain age" metric can provide a holistic, individualized, and objective view of how the brain interacts with various factors (e.g., genetics and lifestyle) during aging. Brain age predictions using deep learning (DL) have been widely used to quantify the developmental status of human brains, but their wider application to serve biomedical purposes is under criticism for requiring large samples and complicated interpretability. Animal models, i.e., rhesus monkeys, have offered a unique lens to understand the human brain - being a species in which aging patterns are similar, for which environmental and lifestyle factors are more readily controlled. However, applying DL methods in animal models suffers from data insufficiency as the availability of animal brain MRIs is limited compared to many thousands of human MRIs. We showed that transfer learning can mitigate the sample size problem, where transferring the pre-trained AI models from 8,859 human brain MRIs improved monkey brain age estimation accuracy and stability. The highest accuracy and stability occurred when transferring the 3D ResNet [mean absolute error (MAE) = 1.83 years] and the 2D global-local transformer (MAE = 1.92 years) models. Our models identified the frontal white matter as the most important feature for monkey brain age predictions, which is consistent with previous histological findings. This first DL-based, anatomically interpretable, and adaptive brain age estimator could broaden the application of AI techniques to various animal or disease samples and widen opportunities for research in non-human primate brains across the lifespan.

A Siamese Network With Node Convolution for Individualized Predictions Based on Connectivity Maps Extracted From Resting-State fMRI Data

Deep learning has demonstrated great potential for objective diagnosis of neuropsychiatric disorders based on neuroimaging data, which includes the promising resting-state functional magnetic resonance imaging (RS-fMRI). However, the insufficient sample size has long been a bottleneck for deep model training for the purpose. In this study, we proposed a Siamese network with node convolution (SNNC) for individualized predictions based on RS-fMRI data. With the involvement of Siamese network, which uses sample pair (rather than a single sample) as input, the problem of insufficient sample size can largely be alleviated. To adapt to connectivity maps extracted from RS-fMRI data, we applied node convolution to each of the two branches of the Siamese network. For regression purposes, we replaced the contrastive loss in classic Siamese network with the mean square error loss and thus enabled Siamese network to quantitatively predict label differences. The label of a test sample can be predicted based on any of the training samples, by adding the label of the training sample to the predicted label difference between them. The final prediction for a test sample in this study was made by averaging the predictions based on each of the training samples. The performance of the proposed SNNC was evaluated with age and IQ predictions based on a public dataset (Cam-CAN). The results indicated that SNNC can make effective predictions even with a sample size of as small as 40, and SNNC achieved state-of-the-art accuracy among a variety of deep models and standard machine learning approaches.

Brain-Machine Coupled Learning Method for Facial Emotion Recognition

Neural network models of machine learning have shown promising prospects for visual tasks, such as facial emotion recognition (FER). However, the generalization of the model trained from a dataset with a few samples is limited. Unlike the machine, the human brain can effectively realize the required information from a few samples to complete the visual tasks. To learn the generalization ability of the brain, in this article, we propose a novel brain-machine coupled learning method for facial emotion recognition to let the neural network learn the visual knowledge of the machine and cognitive knowledge of the brain simultaneously. The proposed method utilizes visual images and electroencephalogram (EEG) signals to couple training the models in the visual and cognitive domains. Each domain model consists of two types of interactive channels, common and private. Since the EEG signals can reflect brain activity, the cognitive process of the brain is decoded by a model following reverse engineering. Decoding the EEG signals induced by the facial emotion images, the common channel in the visual domain can approach the cognitive process in the cognitive domain. Moreover, the knowledge specific to each domain is found in each private channel using an adversarial strategy. After learning, without the participation of the EEG signals, only the concatenation of both channels in the visual domain is used to classify facial emotion images based on the visual knowledge of the machine and the cognitive knowledge learned from the brain. Experiments demonstrate that the proposed method can produce excellent performance on several public datasets. Further experiments show that the proposed method trained from the EEG signals has good generalization ability on new datasets and can be applied to other network models, illustrating the potential for practical applications.

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.

Neurobiological Clusters Are Associated With Trajectories of Overall Psychopathology in Youth

BACKGROUND

Integrating multiple neuroimaging modalities to identify clusters of individuals and then associating these clusters with psychopathology is a promising approach for understanding neurobiological mechanisms that underlie psychopathology and the extent to which these features are associated with clinical symptoms.

METHODS

We leveraged neuroimaging data from T1-weighted, diffusion-weighted, and resting-state functional magnetic resonance images from the Adolescent Brain Cognitive Development (ABCD) Study (N = 8035) and used similarity network fusion and spectral clustering to identify subgroups of participants. We examined neuroimaging measures as a function of clustering profiles using 1, 2, or 3 imaging modalities (i.e., data combinations), calculated the stability of the clustering assignment in each respective data combination, and compared the consistency of clusters across different data combinations. We then compared the extent to which clusters were associated with overall psychopathology at the baseline assessment and at 2 yearly follow-up visits.

RESULTS

Each data combination resulted in optimal clusters ranging from 2 to 4 subgroups for each data combination. Clusters were stable across subsampling of the ABCD Study cohort. Widespread structural measures (surface area, fractional anisotropy, and mean diffusivity) were important features contributing to clustering across different data combinations. Five of the seven data combinations were associated with overall psychopathology, both at baseline and over time (d = 0.08-0.41). Generally, lower global cortical volume and surface area, widespread reduced fractional anisotropy, and increased radial diffusivity were associated with increased overall psychopathology.

CONCLUSIONS

Profiles constructed from neuroimaging data combinations are associated with concurrent and future psychopathology trajectories.

Automatic brain MRI motion artifact detection based on end-to-end deep learning is similarly effective as traditional machine learning trained on image quality metrics

Head motion artifacts in magnetic resonance imaging (MRI) are an important confounding factor concerning brain research as well as clinical practice. For this reason, several machine learning-based methods have been developed for the automatic quality control of structural MRI scans. Deep learning offers a promising solution to this problem, however, given its data-hungry nature and the scarcity of expert-annotated datasets, its advantage over traditional machine learning methods in identifying motion-corrupted brain scans is yet to be determined. In the present study, we investigated the relative advantage of the two methods in structural MRI quality control. To this end, we collected publicly available T1-weighted images and scanned subjects in our own lab under conventional and active head motion conditions. The quality of the images was rated by a team of radiologists from the point of view of clinical diagnostic use. We present a relatively simple, lightweight 3D convolutional neural network trained in an end-to-end manner that achieved a test set (N = 411) balanced accuracy of 94.41% in classifying brain scans into clinically usable or unusable categories. A support vector machine trained on image quality metrics achieved a balanced accuracy of 88.44% on the same test set. Statistical comparison of the two models yielded no significant difference in terms of confusion matrices, error rates, or receiver operating characteristic curves. Our results suggest that these machine learning methods are similarly effective in identifying severe motion artifacts in brain MRI scans, and underline the efficacy of end-to-end deep learning-based systems in brain MRI quality control, allowing the rapid evaluation of diagnostic utility without the need for elaborate image pre-processing.

Multivariate analytical approaches for investigating brain-behavior relationships

Background

Many studies of brain-behavior relationships rely on univariate approaches where each variable of interest is tested independently, which does not allow for the simultaneous investigation of multiple correlated variables. Alternatively, multivariate approaches allow for examining relationships between psychopathology and neural substrates simultaneously. There are multiple multivariate methods to choose from that each have assumptions which can affect the results; however, many studies employ one method without a clear justification for its selection. Additionally, there are few studies illustrating how differences between methods manifest in examining brain-behavior relationships. The purpose of this study was to exemplify how the choice of multivariate approach can change brain-behavior interpretations.

Method

We used data from 9,027 9- to 10-year-old children from the Adolescent Brain Cognitive DevelopmentSM Study (ABCD Study®) to examine brain-behavior relationships with three commonly used multivariate approaches: canonical correlation analysis (CCA), partial least squares correlation (PLSC), and partial least squares regression (PLSR). We examined the associations between psychopathology dimensions including general psychopathology, attention-deficit/hyperactivity symptoms, conduct problems, and internalizing symptoms with regional brain volumes.

Results

The results of CCA, PLSC, and PLSR showed both consistencies and differences in the relationship between psychopathology symptoms and brain structure. The leading significant component yielded by each method demonstrated similar patterns of associations between regional brain volumes and psychopathology symptoms. However, the additional significant components yielded by each method demonstrated differential brain-behavior patterns that were not consistent across methods.

Conclusion

Here we show that CCA, PLSC, and PLSR yield slightly different interpretations regarding the relationship between child psychopathology and brain volume. In demonstrating the divergence between these approaches, we exemplify the importance of carefully considering the method's underlying assumptions when choosing a multivariate approach to delineate brain-behavior relationships.

A multicentre study on grey matter morphometric biomarkers for classifying early schizophrenia and parkinson's disease psychosis

Psychotic symptoms occur in a majority of schizophrenia patients and in ~50% of all Parkinson's disease (PD) patients. Altered grey matter (GM) structure within several brain areas and networks may contribute to their pathogenesis. Little is known, however, about transdiagnostic similarities when psychotic symptoms occur in different disorders, such as in schizophrenia and PD. The present study investigated a large, multicenter sample containing 722 participants: 146 patients with first episode psychosis, FEP; 106 individuals in at-risk mental state for developing psychosis, ARMS; 145 healthy controls matching FEP and ARMS, Con-Psy; 92 PD patients with psychotic symptoms, PDP; 145 PD patients without psychotic symptoms, PDN; 88 healthy controls matching PDN and PDP, Con-PD. We applied source-based morphometry in association with receiver operating curves (ROC) analyses to identify common GM structural covariance networks (SCN) and investigated their accuracy in identifying the different patient groups. We assessed group-specific homogeneity and variability across the different networks and potential associations with clinical symptoms. SCN-extracted GM values differed significantly between FEP and Con-Psy, PDP and Con-PD, PDN and Con-PD, as well as PDN and PDP, indicating significant overall grey matter reductions in PD and early schizophrenia. ROC analyses showed that SCN-based classification algorithms allow good classification (AUC ~0.80) of FEP and Con-Psy, and fair performance (AUC ~0.72) when differentiating PDP from Con-PD. Importantly, the best performance was found in partly the same networks, including the thalamus. Alterations within selected SCNs may be related to the presence of psychotic symptoms in both early schizophrenia and PD psychosis, indicating some commonality of underlying mechanisms. Furthermore, results provide evidence that GM volume within specific SCNs may serve as a biomarker for identifying FEP and PDP.

AutoPrognosis 2.0: Democratizing diagnostic and prognostic modeling in healthcare with automated machine learning

Diagnostic and prognostic models are increasingly important in medicine and inform many clinical decisions. Recently, machine learning approaches have shown improvement over conventional modeling techniques by better capturing complex interactions between patient covariates in a data-driven manner. However, the use of machine learning introduces technical and practical challenges that have thus far restricted widespread adoption of such techniques in clinical settings. To address these challenges and empower healthcare professionals, we present an open-source machine learning framework, AutoPrognosis 2.0, to facilitate the development of diagnostic and prognostic models. AutoPrognosis leverages state-of-the-art advances in automated machine learning to develop optimized machine learning pipelines, incorporates model explainability tools, and enables deployment of clinical demonstrators, without requiring significant technical expertise. To demonstrate AutoPrognosis 2.0, we provide an illustrative application where we construct a prognostic risk score for diabetes using the UK Biobank, a prospective study of 502,467 individuals. The models produced by our automated framework achieve greater discrimination for diabetes than expert clinical risk scores. We have implemented our risk score as a web-based decision support tool, which can be publicly accessed by patients and clinicians. By open-sourcing our framework as a tool for the community, we aim to provide clinicians and other medical practitioners with an accessible resource to develop new risk scores, personalized diagnostics, and prognostics using machine learning techniques. Software: https://github.com/vanderschaarlab/AutoPrognosis.