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 extensively to study brain function in psychiatric disorders, yielding insights into brain organization. However, the high dimensionality of the rs-fMRI data presents significant challenges for data analysis. Variational autoencoders (VAEs), a type of neural network, have been instrumental in extracting low-dimensional latent representations of resting state functional connectivity (rsFC) patterns, thereby addressing the complex nonlinear structure of rs-fMRI data. Despite these advances, interpreting these latent representations remains a challenge. This paper aims to address this gap by developing 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 healthy controls [HC] and 549 patients with ASD) were included in the analysis. RsFC correlation matrices were extracted from the preprocessed rs-fMRI data using the Power atlas, which includes 264 regions of interest (ROIs). Then VAEs were trained in an unsupervised manner. 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 both the ASD and HC groups at the network level. We found that both ASD and HC groups share the top network connectivitives contributing to all estimated latent components. For example, latent 0 was driven by rsFC within ventral attention network (VAN) in both the ASD and HC. However, we found significant differences in the latent contribution scores between the ASD and HC groups within the VAN for latent 0 and the sensory/somatomotor network for 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 feature as the estimated latent representation changes, enabling an explainable deep learning model that better understands the underlying neural mechanisms of ASD.

Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium.

BACKGROUND: Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group. METHODS: We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality. RESULTS: We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for d-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance. CONCLUSION: These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable.

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.