Interpretable Fusion Analytics Framework for fMRI Connectivity: Self-Attention Mechanism and Latent Space Item-Response Model

TL;DR

This paper introduces an interpretable framework combining self-attention deep learning and latent space models to classify and understand fMRI connectivity patterns in cognitive impairment diseases.

Contribution

It presents a novel analytical approach that interprets deep learning classification results in fMRI studies using a latent space item-response model.

Findings

Validates the framework on four types of cognitive impairment

Identifies significant ROI functions with distinct connectivity patterns

Enhances interpretability of deep learning in neuroimaging

Abstract

There have been several attempts to use deep learning based on brain fMRI signals to classify cognitive impairment diseases. However, deep learning is a hidden black box model that makes it difficult to interpret the process of classification. To address this issue, we propose a novel analytical framework that interprets the classification result from deep learning processes. We first derive the region of interest (ROI) functional connectivity network (FCN) by embedding functions based on their similar signal patterns. Then, using the self-attention equipped deep learning model, we classify diseases based on their FCN. Finally, in order to interpret the classification results, we employ a latent space item-response interaction network model to identify the significant functions that exhibit distinct connectivity patterns when compared to other diseases. The application of this proposed framework to the four types of cognitive impairment shows that our approach is valid for determining the significant ROI functions.