TV-based Deep 3D Self Super-Resolution for fMRI

TL;DR

This paper presents a self-supervised deep learning method with TV regularization to enhance fMRI resolution, avoiding the need for ground truth high-resolution images while maintaining functional map integrity.

Contribution

It introduces a novel self-supervised super-resolution model combining deep learning, analytical methods, and TV regularization for fMRI imaging.

Findings

Achieves competitive resolution enhancement without ground truth data

Preserves functional maps effectively

Outperforms some supervised methods in quality

Abstract

While functional Magnetic Resonance Imaging (fMRI) offers valuable insights into cognitive processes, its inherent spatial limitations pose challenges for detailed analysis of the fine-grained functional architecture of the brain. More specifically, MRI scanner and sequence specifications impose a trade-off between temporal resolution, spatial resolution, signal-to-noise ratio, and scan time. Deep Learning (DL) Super-Resolution (SR) methods have emerged as a promising solution to enhance fMRI resolution, generating high-resolution (HR) images from low-resolution (LR) images typically acquired with lower scanning times. However, most existing SR approaches depend on supervised DL techniques, which require training ground truth (GT) HR data, which is often difficult to acquire and simultaneously sets a bound for how far SR can go. In this paper, we introduce a novel self-supervised DL SR model that combines a DL network with an analytical approach and Total Variation (TV) regularization. Our method eliminates the need for external GT images, achieving competitive performance compared to supervised DL techniques and preserving the functional maps.