Interpreting models interpreting brain dynamics

Explainable fuzzy clustering framework reveals divergent default mode network connectivity dynamics in schizophrenia

Introduction

Dynamic functional network connectivity (dFNC) analysis of resting state functional magnetic resonance imaging data has yielded insights into many neurological and neuropsychiatric disorders. A common dFNC analysis approach uses hard clustering methods like k-means clustering to assign samples to states that summarize network dynamics. However, hard clustering methods obscure network dynamics by assuming (1) that all samples within a cluster are equally like their assigned centroids and (2) that samples closer to one another in the data space than to their centroids are well-represented by their centroids. In addition, it can be hard to compare subjects, as in some cases an individual may not manifest a state strongly enough to enter a hard cluster. Approaches that allow a dimensional approach to connectivity patterns (e.g., fuzzy clustering) can mitigate these issues. In this study, we present an explainable fuzzy clustering framework by combining fuzzy c-means clustering with several explainability metrics and novel summary features.

Methods

We apply our framework for schizophrenia (SZ) default mode network analysis. Namely, we extract dFNC from individuals with SZ and controls, identify 5 dFNC states, and characterize the dFNC features most crucial to those states with a new perturbation-based clustering explainability approach. We then extract several features typically used in hard clustering and further present a variety of unique features specially designed for use with fuzzy clustering to quantify state dynamics. We examine differences in those features between individuals with SZ and controls and further search for relationships between those features and SZ symptom severity.

Results

Importantly, we find that individuals with SZ spend more time in states of moderate anticorrelation between the anterior and posterior cingulate cortices and strong anticorrelation between the precuneus and anterior cingulate cortex. We further find that individuals with SZ tend to transition more rapidly than controls between low-magnitude and high-magnitude dFNC states.

Conclusion

We present a novel dFNC analysis framework and use it to identify effects of SZ upon network dynamics. Given the ease of implementing our framework and its enhanced insight into network dynamics, it has great potential for use in future dFNC studies.

Discovering individual fingerprints in resting-state functional connectivity using deep neural networks

Non-negligible idiosyncrasy due to interindividual differences is an ongoing issue in resting-state functional MRI (rfMRI) analysis. We show that a deep neural network (DNN) can be employed for individual identification by learning important features from the time-varying functional connectivity (FC) of rfMRI in the Human Connectome Project. We employed the trained DNN to identify individuals from an independent dataset acquired at our institution. The results revealed that the DNN could successfully identify 300 individuals with an error rate of 2.9% using 15 s time-window and 870 individuals with an error rate of 6.7%. A trained DNN with nonlinear hidden layers led to the proposal of the "fingerprint of FC" (fpFC) as representative edges of individual FC. The fpFCs for individuals exhibited commonly important and individual-specific edges across time-window lengths (from 5 min to 15 s). Furthermore, the utility of our model for another group of subjects was validated, supporting the feasibility of our technique in the context of transfer learning. In conclusion, our study offers an insight into the discovery of the intrinsic mode of the human brain using whole-brain resting-state FC and DNNs.

BolT: Fused window transformers for fMRI time series analysis

Deep-learning models have enabled performance leaps in analysis of high-dimensional functional MRI (fMRI) data. Yet, many previous methods are suboptimally sensitive for contextual representations across diverse time scales. Here, we present BolT, a blood-oxygen-level-dependent transformer model, for analyzing multi-variate fMRI time series. BolT leverages a cascade of transformer encoders equipped with a novel fused window attention mechanism. Encoding is performed on temporally-overlapped windows within the time series to capture local representations. To integrate information temporally, cross-window attention is computed between base tokens in each window and fringe tokens from neighboring windows. To gradually transition from local to global representations, the extent of window overlap and thereby number of fringe tokens are progressively increased across the cascade. Finally, a novel cross-window regularization is employed to align high-level classification features across the time series. Comprehensive experiments on large-scale public datasets demonstrate the superior performance of BolT against state-of-the-art methods. Furthermore, explanatory analyses to identify landmark time points and regions that contribute most significantly to model decisions corroborate prominent neuroscientific findings in the literature.

Posthoc Interpretability of Neural Responses by Grouping Subject Motor Imagery Skills Using CNN-Based Connectivity

Motor Imagery (MI) refers to imagining the mental representation of motor movements without overt motor activity, enhancing physical action execution and neural plasticity with potential applications in medical and professional fields like rehabilitation and education. Currently, the most promising approach for implementing the MI paradigm is the Brain-Computer Interface (BCI), which uses Electroencephalogram (EEG) sensors to detect brain activity. However, MI-BCI control depends on a synergy between user skills and EEG signal analysis. Thus, decoding brain neural responses recorded by scalp electrodes poses still challenging due to substantial limitations, such as non-stationarity and poor spatial resolution. Also, an estimated third of people need more skills to accurately perform MI tasks, leading to underperforming MI-BCI systems. As a strategy to deal with BCI-Inefficiency, this study identifies subjects with poor motor performance at the early stages of BCI training by assessing and interpreting the neural responses elicited by MI across the evaluated subject set. Using connectivity features extracted from class activation maps, we propose a Convolutional Neural Network-based framework for learning relevant information from high-dimensional dynamical data to distinguish between MI tasks while preserving the post-hoc interpretability of neural responses. Two approaches deal with inter/intra-subject variability of MI EEG data: (a) Extracting functional connectivity from spatiotemporal class activation maps through a novel kernel-based cross-spectral distribution estimator, (b) Clustering the subjects according to their achieved classifier accuracy, aiming to find common and discriminative patterns of motor skills. According to the validation results obtained on a bi-class database, an average accuracy enhancement of 10% is achieved compared to the baseline EEGNet approach, reducing the number of "poor skill" subjects from 40% to 20%. Overall, the proposed method can be used to help explain brain neural responses even in subjects with deficient MI skills, who have neural responses with high variability and poor EEG-BCI performance.

Towards greater neuroimaging classification transparency via the integration of explainability methods and confidence estimation approaches

The field of neuroimaging has increasingly sought to develop artificial intelligence-based models for neurological and neuropsychiatric disorder automated diagnosis and clinical decision support. However, if these models are to be implemented in a clinical setting, transparency will be vital. Two aspects of transparency are (1) confidence estimation and (2) explainability. Confidence estimation approaches indicate confidence in individual predictions. Explainability methods give insight into the importance of features to model predictions. In this study, we integrate confidence estimation and explainability approaches for the first time. We demonstrate their viability for schizophrenia diagnosis using resting state functional magnetic resonance imaging (rs-fMRI) dynamic functional network connectivity (dFNC) data. We compare two confidence estimation approaches: Monte Carlo dropout (MCD) and MC batch normalization (MCBN). We combine them with two gradient-based explainability approaches, saliency and layer-wise relevance propagation (LRP), and examine their effects upon explanations. We find that MCD often adversely affects model gradients, making it ill-suited for integration with gradient-based explainability methods. In contrast, MCBN does not affect model gradients. Additionally, we find many participant-level differences between regular explanations and the distributions of explanations for combined explainability and confidence estimation approaches. This suggests that a similar confidence estimation approach used in a clinical context with explanations only output for the regular model would likely not yield adequate explanations. We hope that our findings will provide a starting point for the integration of the two fields, provide useful guidance for future studies, and accelerate the development of transparent neuroimaging clinical decision support systems.