An empirical evaluation of functional alignment using inter-subject decoding

Brain decoding of the Human Connectome Project tasks in a dense individual fMRI dataset

Brain decoding aims to infer cognitive states from patterns of brain activity. Substantial inter-individual variations in functional brain organization challenge accurate decoding performed at the group level. In this paper, we tested whether accurate brain decoding models can be trained entirely at the individual level. We trained several classifiers on a dense individual functional magnetic resonance imaging (fMRI) dataset for which six participants completed the entire Human Connectome Project (HCP) task battery >13 times over ten separate fMRI sessions. We evaluated nine decoding methods, from Support Vector Machines (SVM) and Multi-Layer Perceptron (MLP) to Graph Convolutional Neural Networks (GCN). All decoders were trained to classify single fMRI volumes into 21 experimental conditions simultaneously, using ∼7 h of fMRI data per participant. The best prediction accuracies were achieved with GCN and MLP models, whose performance (57-67 % accuracy) approached state-of-the-art accuracy (76 %) with models trained at the group level on >1 K hours of data from the original HCP sample. Our SVM model also performed very well (54-62 % accuracy). Feature importance maps derived from MLP -our best-performing model- revealed informative features in regions relevant to particular cognitive domains, notably in the motor cortex. We also observed that inter-subject classification achieved substantially lower accuracy than subject-specific models, indicating that our decoders learned individual-specific features. This work demonstrates that densely-sampled neuroimaging datasets can be used to train accurate brain decoding models at the individual level. We expect this work to become a useful benchmark for techniques that improve model generalization across multiple subjects and acquisition conditions.

Music-emotion EEG coupling effects based on representational similarity

BACKGROUND

Music can evoke intense emotions and music emotion is a complex cognitive process. However, we know little about the cognitive mechanisms underlying these processes, and there are significant individual differences in the emotional responses to the same musical stimuli.

NEW METHOD

We used the inter-subject representational similarity analysis (IS-RSA) method to investigate the shared music emotion responses across multiple participants. In addition, we extended IS-RSA to estimate the group cross-frequency coupling effects of music emotion. Based on the cross-frequency coupling IS-RSA, we analyzed the differences in cross-frequency coupling patterns under different music emotions using MI. Comparison of existing methods: most current IS-RSA analyses focus on within-frequency band analysis. However, the cognitive processing of music emotion involves not only activation and brain network connections differences within frequency bands but also information communication between frequency bands.

RESULTS

The results of the within-frequency band IS-RSA analysis showed that the theta and gamma frequency bands play important roles in the inter-participant consistency of music emotion. The inter-frequency band IS-RSA analysis showed that the theta-beta coupling pattern exhibited stronger inter-participant consistency compared to the theta-gamma coupling pattern, and the theta-beta coupling had significant consistent representation across various music conditions. Through the significant regions of cross-frequency coupling representation similarity analysis, we performed phase-amplitude coupling analysis on FC4-C6 and FC4-Pz connections. For the theta-beta coupling pattern, we found that the MI of these two connections exhibited different coupling patterns under different music conditions, and they showed a significant decrease compared to the baseline period.

Inter-individual deep image reconstruction via hierarchical neural code conversion

The sensory cortex is characterized by general organizational principles such as topography and hierarchy. However, measured brain activity given identical input exhibits substantially different patterns across individuals. Although anatomical and functional alignment methods have been proposed in functional magnetic resonance imaging (fMRI) studies, it remains unclear whether and how hierarchical and fine-grained representations can be converted between individuals while preserving the encoded perceptual content. In this study, we trained a method of functional alignment called neural code converter that predicts a target subject's brain activity pattern from a source subject given the same stimulus, and analyzed the converted patterns by decoding hierarchical visual features and reconstructing perceived images. The converters were trained on fMRI responses to identical sets of natural images presented to pairs of individuals, using the voxels on the visual cortex that covers from V1 through the ventral object areas without explicit labels of the visual areas. We decoded the converted brain activity patterns into the hierarchical visual features of a deep neural network using decoders pre-trained on the target subject and then reconstructed images via the decoded features. Without explicit information about the visual cortical hierarchy, the converters automatically learned the correspondence between visual areas of the same levels. Deep neural network feature decoding at each layer showed higher decoding accuracies from corresponding levels of visual areas, indicating that hierarchical representations were preserved after conversion. The visual images were reconstructed with recognizable silhouettes of objects even with relatively small numbers of data for converter training. The decoders trained on pooled data from multiple individuals through conversions led to a slight improvement over those trained on a single individual. These results demonstrate that the hierarchical and fine-grained representation can be converted by functional alignment, while preserving sufficient visual information to enable inter-individual visual image reconstruction.

Enhanced hyperalignment via spatial prior information

Functional alignment between subjects is an important assumption of functional magnetic resonance imaging (fMRI) group-level analysis. However, it is often violated in practice, even after alignment to a standard anatomical template. Hyperalignment, based on sequential Procrustes orthogonal transformations, has been proposed as a method of aligning shared functional information into a common high-dimensional space and thereby improving inter-subject analysis. Though successful, current hyperalignment algorithms have a number of shortcomings, including difficulties interpreting the transformations, a lack of uniqueness of the procedure, and difficulties performing whole-brain analysis. To resolve these issues, we propose the ProMises (Procrustes von Mises-Fisher) model. We reformulate functional alignment as a statistical model and impose a prior distribution on the orthogonal parameters (the von Mises-Fisher distribution). This allows for the embedding of anatomical information into the estimation procedure by penalizing the contribution of spatially distant voxels when creating the shared functional high-dimensional space. Importantly, the transformations, aligned images, and related results are all unique. In addition, the proposed method allows for efficient whole-brain functional alignment. In simulations and application to data from four fMRI studies we find that ProMises improves inter-subject classification in terms of between-subject accuracy and interpretability compared to standard hyperalignment algorithms.

Interpreting mental state decoding with deep learning models

In mental state decoding, researchers aim to identify the set of mental states (e.g., experiencing happiness or fear) that can be reliably identified from the activity patterns of a brain region (or network). Deep learning (DL) models are highly promising for mental state decoding because of their unmatched ability to learn versatile representations of complex data. However, their widespread application in mental state decoding is hindered by their lack of interpretability, difficulties in applying them to small datasets, and in ensuring their reproducibility and robustness. We recommend approaching these challenges by leveraging recent advances in explainable artificial intelligence (XAI) and transfer learning, and also provide recommendations on how to improve the reproducibility and robustness of DL models in mental state decoding.

Real-Time Functional MRI in the Treatment of Mental Health Disorders

Multiple mental disorders have been associated with dysregulation of precise brain processes. However, few therapeutic approaches can correct such specific patterns of brain activity. Since the late 1960s and early 1970s, many researchers have hoped that this feat could be achieved by closed-loop brain imaging approaches, such as neurofeedback, that aim to modulate brain activity directly. However, neurofeedback never gained mainstream acceptance in mental health, in part due to methodological considerations. In this review, we argue that, when contemporary methodological guidelines are followed, neurofeedback is one of the few intervention methods in psychology that can be assessed in double-blind placebo-controlled trials. Furthermore, using new advances in machine learning and statistics, it is now possible to target very precise patterns of brain activity for therapeutic purposes. We review the recent literature in functional magnetic resonance imaging neurofeedback and discuss current and future applications to mental health.

Expected final online publication date for the Annual Review of Clinical Psychology, Volume 18 is May 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Machine learning in neuroimaging: from research to clinical practice

Neuroimaging is critical in clinical care and research, enabling us to investigate the brain in health and disease. There is a complex link between the brain's morphological structure, physiological architecture, and the corresponding imaging characteristics. The shape, function, and relationships between various brain areas change during development and throughout life, disease, and recovery. Like few other areas, neuroimaging benefits from advanced analysis techniques to fully exploit imaging data for studying the brain and its function. Recently, machine learning has started to contribute (a) to anatomical measurements, detection, segmentation, and quantification of lesions and disease patterns, (b) to the rapid identification of acute conditions such as stroke, or (c) to the tracking of imaging changes over time. As our ability to image and analyze the brain advances, so does our understanding of its intricate relationships and their role in therapeutic decision-making. Here, we review the current state of the art in using machine learning techniques to exploit neuroimaging data for clinical care and research, providing an overview of clinical applications and their contribution to fundamental computational neuroscience.