Improved Simultaneous Multi-Slice Functional MRI Using Self-supervised Deep Learning

TL;DR

This paper introduces a self-supervised deep learning method for SMS fMRI reconstruction that reduces noise and artifacts without needing fully-sampled data, improving data quality for neural activity analysis.

Contribution

It extends self-supervised deep learning to SMS fMRI, demonstrating improved reconstruction quality and preserved analysis integrity in highly-accelerated 7T data.

Findings

Reduces noise and artifacts in SMS fMRI reconstruction

Enhances temporal signal-to-noise ratio and coherence estimates

Maintains fMRI analysis accuracy after deep learning processing

Abstract

Functional MRI (fMRI) is commonly used for interpreting neural activities across the brain. Numerous accelerated fMRI techniques aim to provide improved spatiotemporal resolutions. Among these, simultaneous multi-slice (SMS) imaging has emerged as a powerful strategy, becoming a part of large-scale studies, such as the Human Connectome Project. However, when SMS imaging is combined with in-plane acceleration for higher acceleration rates, conventional SMS reconstruction methods may suffer from noise amplification and other artifacts. Recently, deep learning (DL) techniques have gained interest for improving MRI reconstruction. However, these methods are typically trained in a supervised manner that necessitates fully-sampled reference data, which is not feasible in highly-accelerated fMRI acquisitions. Self-supervised learning that does not require fully-sampled data has recently been proposed and has shown similar performance to supervised learning. However, it has only been applied for in-plane acceleration. Furthermore the effect of DL reconstruction on subsequent fMRI analysis remains unclear. In this work, we extend self-supervised DL reconstruction to SMS imaging. Our results on prospectively 10-fold accelerated 7T fMRI data show that self-supervised DL reduces reconstruction noise and suppresses residual artifacts. Subsequent fMRI analysis remains unaltered by DL processing, while the improved temporal signal-to-noise ratio produces higher coherence estimates between task runs.