An Explainable Deep Learning Approach for Multimodal Electrophysiology Classification

Miller

Calhoun

2022

Preprint

Self Cite

In recent years, many neuroimaging studies have begun to integrate gradient-based explainability methods to provide insight into key features. However, existing explainability approaches typically generate a point estimate of importance and do not provide insight into the degree of uncertainty associated with explanations. In this study, we present a novel approach for estimating explanation uncertainty for convolutional neural networks (CNN) trained on neuroimaging data. We train a CNN for classification of individuals with schizophrenia (SZs) and controls (HCs) using resting state functional magnetic resonance imaging (rs-fMRI) dynamic functional network connectivity (dFNC) data. We apply Monte Carlo batch normalization (MCBN) and generate an explanation following each iteration using layer-wise relevance propagation (LRP). We then examine whether the resulting distribution of explanations differs between SZs and HCs and examine the relationship between MCBN-based LRP and regular LRP. We find a number of significant differences in LRP relevance for SZs and HCs and find that traditional LRP values frequently diverge from the MCBN relevance distribution. This study provides a novel approach for obtaining insight into the level of uncertainty associated with gradient-based explanations in neuroimaging and represents a significant step towards increasing reliability of explainability methods for a clinical setting.

Section: Introductionmentioning

confidence: 99%

An Approach for Estimating Explanation Uncertainty in fMRI dFNC Classification

Miller

Calhoun

2022

Preprint

Self Cite

“…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%

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

Miller

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.

“…As a result, most studies have not used explainability ( Zhang et al, 2011 ; Kwon et al, 2018 ; Niroshana et al, 2019 ; Phan et al, 2019 ; Wang et al, 2020 ; Li et al, 2021 ), which is concerning because transparency is increasingly required to assist with model development and physician decision making ( Sullivan and Schweikart, 2019 ). As such, more multimodal explainability methods need to be developed ( Lin et al, 2019 ; Mellem et al, 2020 ; Ellis et al, 2021a , b , c , d ). In this study, we use automated sleep stage classification as a testbed for the development of multimodal explainability methods.…”

Section: Introductionmentioning

confidence: 99%

Novel methods for elucidating modality importance in multimodal electrophysiology classifiers

Sendi

Zhang

et al. 2023

Front. Neuroinform.

Self Cite

IntroductionMultimodal classification is increasingly common in electrophysiology studies. Many studies use deep learning classifiers with raw time-series data, which makes explainability difficult, and has resulted in relatively few studies applying explainability methods. This is concerning because explainability is vital to the development and implementation of clinical classifiers. As such, new multimodal explainability methods are needed.MethodsIn this study, we train a convolutional neural network for automated sleep stage classification with electroencephalogram (EEG), electrooculogram, and electromyogram data. We then present a global explainability approach that is uniquely adapted for electrophysiology analysis and compare it to an existing approach. We present the first two local multimodal explainability approaches. We look for subject-level differences in the local explanations that are obscured by global methods and look for relationships between the explanations and clinical and demographic variables in a novel analysis.ResultsWe find a high level of agreement between methods. We find that EEG is globally the most important modality for most sleep stages and that subject-level differences in importance arise in local explanations that are not captured in global explanations. We further show that sex, followed by medication and age, had significant effects upon the patterns learned by the classifier.DiscussionOur novel methods enhance explainability for the growing field of multimodal electrophysiology classification, provide avenues for the advancement of personalized medicine, yield unique insights into the effects of demographic and clinical variables upon classifiers, and help pave the way for the implementation of multimodal electrophysiology clinical classifiers.