Neuropsychiatric Disorder Subtyping Via Clustered Deep Learning Classifier Explanations

Calhoun

2023

Preprint

Self Cite

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. We apply our framework for schizophrenia (SZ) default mode network analysis, identifying 5 states and characterizing those states with a new explainability approach. While also showing that features typically used in hard clustering can be extracted in our framework, we present a variety of unique features to quantify state dynamics and identify effects of SZ upon network dynamics. We further uncover relationships between symptom severity and interactions of the precuneus with the anterior and posterior cingulate cortex. Given the ease of implementing our framework and its enhanced insight into network dynamics, it has great potential for use in future dFNC studies.

Section: Introductionmentioning

confidence: 99%

Explainable Fuzzy Clustering Framework Reveals Divergent Default Mode Network Connectivity Dynamics in Schizophrenia

Calhoun

2023

Preprint

Self Cite

“…We used rs-fMRI recordings from 160 HCs and 151 SZs that are part of the Functional Imaging Biomedical Informatics Research Network (FBIRN) dataset (62). The dataset has been used in many studies (8,9,11,18,22,54,60,63) and also contains negative and positive symptom scores from the Positive and Negative Syndrome Scale (PANSS) (64). Negative SZ symptoms include apathy, alogia, asociality, and affective flattening, while positive SZ symptoms include delusions, hallucinations, and bizarre behavior (41).…”

Section: Methodsmentioning

confidence: 99%

“…For explainability, we used the αβ-rule (70) of layer-wise relevance propagation (LRP) (71,72). LRP is a popular approach that have been used in many studies for insight into neurological time-series and neuroimaging data (8,9,59,60,(73)(74)(75)(76)(77)(78)(79)(80). LRP involves several steps.…”

Section: Description Of Explainability Approachmentioning

confidence: 99%

“…Figure 2 shows our 1D-CNN model architecture, which we originally used in (60). Before training, we feature-wise z-scored the dFNC data for each participant separately.…”

Section: Description Of Model Developmentmentioning

confidence: 99%

“…The combination of an explainable classifier followed by a clustering approach presents an opportunity that could (1) improve upon clustering approaches by providing highly discriminatory insight into disorders and (2) improve upon classification approaches by providing more granular insights into the effects of disorders upon brain activity. Moreover, while we have applied a combination of a classifier with a clustering algorithm in one previous study to identify subtypes of SZs (60), the potential of this approach still remains largely understudied.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Pairing Explainable Deep Learning Classification with Clustering to Uncover Effects of Schizophrenia Upon Whole Brain Functional Network Connectivity Dynamics

Calhoun

2023

Preprint

Self Cite

Many studies have analyzed resting state functional magnetic resonance imaging (rs-fMRI) dynamic functional network connectivity (dFNC) data to elucidate the effects of neurological and neuropsychiatric disorders upon the interactions of brain regions over time. Existing studies often use either machine learning classification or clustering algorithms. Additionally, several studies have used clustering algorithms to extract features related to brain states trajectories that can be used to train interpretable classifiers. However, the combination of explainable dFNC classifiers followed by clustering algorithms is highly underutilized. In this study, we show how such an approach can be used to study the effects of schizophrenia (SZ) upon brain activity. Specifically, we train an explainable deep learning model to classify between individuals with SZ and healthy controls. We then cluster the resulting explanations, identifying discriminatory states of dFNC. We lastly apply several novel measures to quantify aspects of the classifier explanations and obtain additional insights into the effects of SZ upon brain network dynamics. Specifically, we uncover effects of schizophrenia upon subcortical, sensory, and cerebellar network interactions. We also find that individuals with SZ likely have reduced variability in overall brain activity and that the effects of SZ may be temporally localized. In addition to uncovering effects of SZ upon brain network dynamics, our approach could provide novel insights into a variety of neurological and neuropsychiatric disorders in future dFNC studies.

A Framework for Systematically Evaluating the Representations Learned by A Deep Learning Classifier from Raw Multi-Channel Electroencephalogram Data

Sattiraju

et al. 2023

Preprint

Self Cite

The application of deep learning methods to raw electroencephalogram (EEG) data is growing increasingly common. While these methods offer the possibility of improved performance relative to other approaches applied to manually engineered features, they also present the problem of reduced explainability. As such, a number of studies have sought to provide explainability methods uniquely adapted to the domain of deep learning-based raw EEG classification. In this study, we present a taxonomy of those methods, identifying existing approaches that provide insight into spatial, spectral, and temporal features. We then present a novel framework consisting of a series of explainability approaches for insight into classifiers trained on raw EEG data. Our framework provides spatial, spectral, and temporal explanations similar to existing approaches. However, it also, to the best of our knowledge, proposes the first explainability approaches for insight into spatial and spatio-spectral interactions in EEG. This is particularly important given the frequent use and well-characterized importance of EEG connectivity measures for neurological and neuropsychiatric disorder analysis. We demonstrate our proposed framework within the context of automated major depressive disorder (MDD) diagnosis, training a high performing one-dimensional convolutional neural network with a robust cross-validation approach on a publicly available dataset. We identify interactions between central electrodes and other electrodes and identify differences in frontal theta, beta, and gamma low between healthy controls and individuals with MDD. Our study represents a significant step forward for the field of deep learning-based raw EEG classification, providing new capabilities in interaction explainability and providing direction for future innovations through our proposed taxonomy.