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

TractGeoNet: A geometric deep learning framework for pointwise analysis of tract microstructure to predict language assessment performance

We propose a geometric deep-learning-based framework, TractGeoNet, for performing regression using diffusion magnetic resonance imaging (dMRI) tractography and associated pointwise tissue microstructure measurements. By employing a point cloud representation, TractGeoNet can directly utilize tissue microstructure and positional information from all points within a fiber tract without the need to average or bin data along the streamline as traditionally required by dMRI tractometry methods. To improve regression performance, we propose a novel loss function, the Paired-Siamese Regression loss, which encourages the model to focus on accurately predicting the relative differences between regression label scores rather than just their absolute values. In addition, to gain insight into the brain regions that contribute most strongly to the prediction results, we propose a Critical Region Localization algorithm. This algorithm identifies highly predictive anatomical regions within the white matter fiber tracts for the regression task. We evaluate the effectiveness of the proposed method by predicting individual performance on two neuropsychological assessments of language using a dataset of 20 association white matter fiber tracts from 806 subjects from the Human Connectome Project Young Adult dataset. The results demonstrate superior prediction performance of TractGeoNet compared to several popular regression models that have been applied to predict individual cognitive performance based on neuroimaging features. Of the twenty tracts studied, we find that the left arcuate fasciculus tract is the most highly predictive of the two studied language performance assessments. Within each tract, we localize critical regions whose microstructure and point information are highly and consistently predictive of language performance across different subjects and across multiple independently trained models. These critical regions are widespread and distributed across both hemispheres and all cerebral lobes, including areas of the brain considered important for language function such as superior and anterior temporal regions, pars opercularis, and precentral gyrus. Overall, TractGeoNet demonstrates the potential of geometric deep learning to enhance the study of the brain's white matter fiber tracts and to relate their structure to human traits such as language performance.

Cross-cohort replicable resting-state functional connectivity in predicting symptoms and cognition of schizophrenia

Schizophrenia (SZ) is a debilitating mental illness characterized by adolescence or early adulthood onset of psychosis, positive and negative symptoms, as well as cognitive impairments. Despite a plethora of studies leveraging functional connectivity (FC) from functional magnetic resonance imaging (fMRI) to predict symptoms and cognitive impairments of SZ, the findings have exhibited great heterogeneity. We aimed to identify congruous and replicable connectivity patterns capable of predicting positive and negative symptoms as well as cognitive impairments in SZ. Predictable functional connections (FCs) were identified by employing an individualized prediction model, whose replicability was further evaluated across three independent cohorts (BSNIP, SZ = 174; COBRE, SZ = 100; FBIRN, SZ = 161). Across cohorts, we observed that altered FCs in frontal-temporal-cingulate-thalamic network were replicable in prediction of positive symptoms, while sensorimotor network was predictive of negative symptoms. Temporal-parahippocampal network was consistently identified to be associated with reduced cognitive function. These replicable 23 FCs effectively distinguished SZ from healthy controls (HC) across three cohorts (82.7%, 90.2%, and 86.1%). Furthermore, models built using these replicable FCs showed comparable accuracies to those built using the whole-brain features in predicting symptoms/cognition of SZ across the three cohorts (r = .17-.33, p < .05). Overall, our findings provide new insights into the neural underpinnings of SZ symptoms/cognition and offer potential targets for further research and possible clinical interventions.

Triple Interactions Between the Environment, Brain, and Behavior in Children: An ABCD Study

BACKGROUND

Environmental exposures play a crucial role in shaping children's behavioral development. However, the mechanisms by which these exposures interact with brain functional connectivity and influence behavior remain unexplored.

METHODS

We investigated the comprehensive environment-brain-behavior triple interactions through rigorous association, prediction, and mediation analyses, while adjusting for multiple confounders. Particularly, we examined the predictive power of brain functional network connectivity (FNC) and 41 environmental exposures for 23 behaviors related to cognitive ability and mental health in 7655 children selected from the Adolescent Brain Cognitive Development (ABCD) Study at both baseline and follow-up.

RESULTS

FNC demonstrated more predictability for cognitive abilities than for mental health, with cross-validation from the UK Biobank study (N = 20,852), highlighting the importance of thalamus and hippocampus in longitudinal prediction, while FNC+environment demonstrated more predictive power than FNC in both cross-sectional and longitudinal prediction of all behaviors, especially for mental health (r = 0.32-0.63). We found that family and neighborhood exposures were common critical environmental influencers on cognitive ability and mental health, which can be mediated by FNC significantly. Healthy perinatal development was a unique protective factor for higher cognitive ability, whereas sleep problems, family conflicts, and adverse school environments specifically increased risk of poor mental health.

CONCLUSIONS

This work revealed comprehensive environment-brain-behavior triple interactions based on the ABCD Study, identified cognitive control and default mode networks as the most predictive functional networks for a wide repertoire of behaviors, and underscored the long-lasting impact of critical environmental exposures on childhood development, in which sleep problems were the most prominent factors affecting mental health.

Brain-phenotype predictions can survive across diverse real-world data

Recent work suggests that machine learning models predicting psychiatric treatment outcomes based on clinical data may fail when applied to unharmonized samples. Neuroimaging predictive models offer the opportunity to incorporate neurobiological information, which may be more robust to dataset shifts. Yet, among the minority of neuroimaging studies that undertake any form of external validation, there is a notable lack of attention to generalization across dataset-specific idiosyncrasies. Research settings, by design, remove the between-site variations that real-world and, eventually, clinical applications demand. Here, we rigorously test the ability of a range of predictive models to generalize across three diverse, unharmonized samples: the Philadelphia Neurodevelopmental Cohort (n=1291), the Healthy Brain Network (n=1110), and the Human Connectome Project in Development (n=428). These datasets have high inter-dataset heterogeneity, encompassing substantial variations in age distribution, sex, racial and ethnic minority representation, recruitment geography, clinical symptom burdens, fMRI tasks, sequences, and behavioral measures. We demonstrate that reproducible and generalizable brain-behavior associations can be realized across diverse dataset features with sample sizes in the hundreds. Results indicate the potential of functional connectivity-based predictive models to be robust despite substantial inter-dataset variability. Notably, for the HCPD and HBN datasets, the best predictions were not from training and testing in the same dataset (i.e., cross-validation) but across datasets. This result suggests that training on diverse data may improve prediction in specific cases. Overall, this work provides a critical foundation for future work evaluating the generalizability of neuroimaging predictive models in real-world scenarios and clinical settings.

Brain Status Transferring Generative Adversarial Network for Decoding Individualized Atrophy in Alzheimer's Disease

Deep learning has been widely investigated in brain image computational analysis for diagnosing brain diseases such as Alzheimer's disease (AD). Most of the existing methods built end-to-end models to learn discriminative features by group-wise analysis. However, these methods cannot detect pathological changes in each subject, which is essential for the individualized interpretation of disease variances and precision medicine. In this article, we propose a brain status transferring generative adversarial network (BrainStatTrans-GAN) to generate corresponding healthy images of patients, which are further used to decode individualized brain atrophy. The BrainStatTrans-GAN consists of generator, discriminator, and status discriminator. First, a normative GAN is built to generate healthy brain images from normal controls. However, it cannot generate healthy images from diseased ones due to the lack of paired healthy and diseased images. To address this problem, a status discriminator with adversarial learning is designed in the training process to produce healthy brain images for patients. Then, the residual between the generated and input images can be computed to quantify pathological brain changes. Finally, a residual-based multi-level fusion network (RMFN) is built for more accurate disease diagnosis. Compared to the existing methods, our method can model individualized brain atrophy for facilitating disease diagnosis and interpretation. Experimental results on T1-weighted magnetic resonance imaging (MRI) data of 1,739 subjects from three datasets demonstrate the effectiveness of our method.

The challenges and prospects of brain-based prediction of behaviour

Relating individual brain patterns to behaviour is fundamental in system neuroscience. Recently, the predictive modelling approach has become increasingly popular, largely due to the recent availability of large open datasets and access to computational resources. This means that we can use machine learning models and interindividual differences at the brain level represented by neuroimaging features to predict interindividual differences in behavioural measures. By doing so, we could identify biomarkers and neural correlates in a data-driven fashion. Nevertheless, this budding field of neuroimaging-based predictive modelling is facing issues that may limit its potential applications. Here we review these existing challenges, as well as those that we anticipate as the field develops. We focus on the impacts of these challenges on brain-based predictions. We suggest potential solutions to address the resolvable challenges, while keeping in mind that some general and conceptual limitations may also underlie the predictive modelling approach.

Differential responses in the mirror neuron system during imitation of individual emotional facial expressions and association with autistic traits

The mirror neuron system (MNS), including the inferior frontal gyrus (IFG), inferior parietal lobule (IPL) and superior temporal sulcus (STS) plays an important role in action representation and imitation and may be dysfunctional in autism spectrum disorder (ASD). However, it's not clear how these three regions respond and interact during the imitation of different basic facial expressions and whether the pattern of responses is influenced by autistic traits. Thus, we conducted a natural facial expression (happiness, angry, sadness and fear) imitation task in 100 healthy male subjects where expression intensity was measured using facial emotion recognition software (FaceReader) and MNS responses were recorded using functional near-infrared spectroscopy (fNIRS). Autistic traits were measured using the Autism Spectrum Quotient questionnaire. Results showed that imitation of happy expressions produced the highest expression intensity but a small deactivation in MNS responses, suggesting a lower processing requirement compared to other expressions. A cosine similarity analysis indicated a distinct pattern of MNS responses during imitation of each facial expression with functional intra-hemispheric connectivity between the left IPL and left STS being significantly higher during happy compared to other expressions, while inter-hemispheric connectivity between the left and right IPL differed between imitation of fearful and sad expressions. Furthermore, functional connectivity changes during imitation of each different expression could reliably predict autistic trait scores. Overall, the results provide evidence for distinct patterns of functional connectivity changes between MNS regions during imitation of different emotions which are also associated with autistic traits.

Machine Learning and Prediction in Fetal, Infant, and Toddler Neuroimaging: A Review and Primer

Predictive models in neuroimaging are increasingly designed with the intent to improve risk stratification and support interventional efforts in psychiatry. Many of these models have been developed in samples of children school-aged or older. Nevertheless, despite growing evidence that altered brain maturation during the fetal, infant, and toddler (FIT) period modulates risk for poor mental health outcomes in childhood, these models are rarely implemented in FIT samples. Applications of predictive modeling in children of these ages provide an opportunity to develop powerful tools for improved characterization of the neural mechanisms underlying development. To facilitate the broader use of predictive models in FIT neuroimaging, we present a brief primer and systematic review on the methods used in current predictive modeling FIT studies. Reflecting on current practices in more than 100 studies conducted over the past decade, we provide an overview of topics, modalities, and methods commonly used in the field and under-researched areas. We then outline ethical and future considerations for neuroimaging researchers interested in predicting health outcomes in early life, including researchers who may be relatively new to either advanced machine learning methods or using FIT data. Altogether, the last decade of FIT research in machine learning has provided a foundation for accelerating the prediction of early-life trajectories across the full spectrum of illness and health.