3D Wasserstein generative adversarial network with dense U-Net based discriminator for preclinical fMRI denoising

TL;DR

This paper introduces a novel 3D Wasserstein GAN with a dense U-Net discriminator for denoising preclinical fMRI data, effectively improving image quality and signal-to-noise ratio while preserving brain structure.

Contribution

The paper presents a new 3D Wasserstein GAN with a dense U-Net discriminator specifically designed for preclinical fMRI denoising, addressing challenges of noise and structural preservation.

Findings

Significant improvement in image quality and SNR in preclinical fMRI data.

Outperforms existing state-of-the-art denoising methods on simulated and real data.

Effectively preserves brain structure while reducing noise.

Abstract

Functional magnetic resonance imaging (fMRI) is extensively used in clinical and preclinical settings to study brain function, however, fMRI data is inherently noisy due to physiological processes, hardware, and external noise. Denoising is one of the main preprocessing steps in any fMRI analysis pipeline. This process is challenging in preclinical data in comparison to clinical data due to variations in brain geometry, image resolution, and low signal-to-noise ratios. In this paper, we propose a structure-preserved algorithm based on a 3D Wasserstein generative adversarial network with a 3D dense U-net based discriminator called, 3D U-WGAN. We apply a 4D data configuration to effectively denoise temporal and spatial information in analyzing preclinical fMRI data. GAN-based denoising methods often utilize a discriminator to identify significant differences between denoised and noise-free images, focusing on global or local features. To refine the fMRI denoising model, our method employs a 3D dense U-Net discriminator to learn both global and local distinctions. To tackle potential over-smoothing, we introduce an adversarial loss and enhance perceptual similarity by measuring feature space distances. Experiments illustrate that 3D U-WGAN significantly improves image quality in resting-state and task preclinical fMRI data, enhancing signal-to-noise ratio without introducing excessive structural changes in existing methods. The proposed method outperforms state-of-the-art methods when applied to simulated and real data in a fMRI analysis pipeline.