Explaining Deep Learning-Based Representations of Resting State Functional Connectivity Data: Focusing on Interpreting Nonlinear Patterns in Autism Spectrum Disorder.

Background: Resting state Functional Magnetic Resonance Imaging fMRI (rs-fMRI) has been used to study brain function in psychiatric disorders, yielding insight into brain organization. However, the high dimensionality of the rs-fMRI data presents challenges, and requires dimensionality reduction before applying machine learning techniques. Neural networks, specifically variational autoencoders (VAEs), have been instrumental in extracting low-dimensional latent representations of resting state functional connectivity patterns, addressing the complex nonlinear structure of rs-fMRI. However, interpreting those latent representations remains a challenge. This paper aims to address this gap by creating explainable VAE models and testing their utility using rs-fMRI data in autism spectrum disorder (ASD). Methods: One-thousand one hundred and fifty participants (601 HC and 549 patients with ASD) were included in the analysis. We extracted functional connectivity correlation matrices from the preprocessed rs-fMRI data using Power atlas with 264 ROIs. Then VAEs were trained in an unsupervised fashion. Lastly, we introduce our latent contribution scores to explain the relationship between estimated representations and the original rs-fMRI brain measures. Results: We quantified the latent contribution scores for the ASD and control groups at the network level. We found that both ASD and control groups share the top network connectivity that contribute to all estimated latent components. For example, latent 0 was driven by resting state functional connectivity patterns (rsFC) within ventral attention network in both the ASD and control. However, significant differences in the latent contribution scores between the ASD and control groups were discovered within the ventral attention network in latent 0 and the sensory/somatomotor network in latent 2. Conclusion: This study introduced latent contribution scores to interpret nonlinear patterns identified by VAEs. These scores effectively capture changes in each observed rsFC features as estimated latent representation changes, enabling an explainable deep learning model to better understand the underlying neural mechanism of ASD.