Individualized spatial network predictions using Siamese convolutional neural networks: A resting-state fMRI study of over 11,000 unaffected individuals

Contrastive learning for neural fingerprinting from limited neuroimaging data

Introduction

Neural fingerprinting is a technique used to identify individuals based on their unique brain activity patterns. While deep learning techniques have been demonstrated to outperform traditional correlation-based methods, they often require retraining to accommodate new subjects. Furthermore, the limited availability of samples in neuroscience research can impede the quick adoption of deep learning methods, presenting a challenge for their broader application in neural fingerprinting.

Methods

This study addresses these challenges by using contrastive learning to eliminate the need for retraining with new subjects and developing a data augmentation methodology to enhance model robustness in limited sample size conditions. We utilized the LEMON dataset, comprising 3 Tesla MRI and resting-state fMRI scans from 138 subjects, to compute functional connectivity as a baseline for fingerprinting performance based on correlation metrics. We adapted a recent deep learning model by incorporating data augmentation with short random temporal segments for training and reformulated the fingerprinting task as a contrastive problem, comparing the efficacy of contrastive triplet loss against conventional cross-entropy loss.

Results

The results of this study confirm that deep learning methods can significantly improve fingerprinting performance over correlation-based methods, achieving an accuracy of about 98% in identifying a single subject out of 138 subjects utilizing 39 different functional connectivity profiles.

Discussion

The contrastive method showed added value in the "leave subject out" scenario, demonstrating flexibility comparable to correlation-based methods and robustness across different data sizes. These findings suggest that contrastive learning and data augmentation offer a scalable solution for neural fingerprinting, even with limited sample sizes.

Graph-matching distance between individuals' functional connectomes varies with relatedness, age, and cognitive score

Functional connectomes (FCs), represented by networks or graphs that summarize coactivation patterns between pairs of brain regions, have been related at a population level to age, sex, cognitive/behavioral scores, life experience, genetics, and disease/disorders. However, quantifying FC differences between individuals also provides a rich source of information with which to map to differences in those individuals' biology, experience, genetics or behavior. In this study, graph matching is used to create a novel inter-individual FC metric, called swap distance, that quantifies the distance between pairs of individuals' partial FCs, with a smaller swap distance indicating the individuals have more similar FC. We apply graph matching to align FCs between individuals from the the Human Connectome ProjectN = 997 and find that swap distance (i) increases with increasing familial distance, (ii) increases with subjects' ages, (iii) is smaller for pairs of females compared to pairs of males, and (iv) is larger for females with lower cognitive scores compared to females with larger cognitive scores. Regions that contributed most to individuals' swap distances were in higher-order networks, that is, default-mode and fronto-parietal, that underlie executive function and memory. These higher-order networks' regions also had swap frequencies that varied monotonically with familial relatedness of the individuals in question. We posit that the proposed graph matching technique provides a novel way to study inter-subject differences in FC and enables quantification of how FC may vary with age, relatedness, sex, and behavior.

Fine temporal brain network structure modularizes and localizes differently in men and women: insights from a novel explainability framework

Deep learning has become an effective tool for classifying biological sex based on functional magnetic resonance imaging (fMRI). However, research on what features within the brain are most relevant to this classification is still lacking. Model interpretability has become a powerful way to understand "black box" deep-learning models, and select features within the input data that are most relevant to the correct classification. However, very little work has been done employing these methods to understand the relationship between the temporal dimension of functional imaging signals and the classification of biological sex. Consequently, less attention has been paid to rectifying problems and limitations associated with feature explanation models, e.g. underspecification and instability. In this work, we first provide a methodology to limit the impact of underspecification on the stability of the measured feature importance. Then, using intrinsic connectivity networks from fMRI data, we provide a deep exploration of sex differences among functional brain networks. We report numerous conclusions, including activity differences in the visual and cognitive domains and major connectivity differences.