PISCO: Self-Supervised k-Space Regularization for Improved Neural Implicit k-Space Representations of Dynamic MRI

TL;DR

This paper introduces PISCO, a self-supervised k-space regularization method that enhances neural implicit k-space representations for dynamic MRI, especially at high acceleration factors, improving reconstruction quality without extra data.

Contribution

The paper proposes a novel self-supervised k-space loss function, PISCO, which improves neural implicit k-space reconstructions for dynamic MRI by enforcing global k-space consistency without additional data.

Findings

PISCO significantly improves reconstruction quality at high acceleration factors (R≥54).

NIK with PISCO outperforms state-of-the-art methods in spatio-temporal MRI reconstruction.

PISCO demonstrates versatility and stability as a self-supervised k-space loss function.

Abstract

Neural implicit k-space representations (NIK) have shown promising results for dynamic magnetic resonance imaging (MRI) at high temporal resolutions. Yet, reducing acquisition time, and thereby available training data, results in severe performance drops due to overfitting. To address this, we introduce a novel self-supervised k-space loss function $\mathcal{L}_\mathrm{PISCO}$, applicable for regularization of NIK-based reconstructions. The proposed loss function is based on the concept of parallel imaging-inspired self-consistency (PISCO), enforcing a consistent global k-space neighborhood relationship without requiring additional data. Quantitative and qualitative evaluations on static and dynamic MR reconstructions show that integrating PISCO significantly improves NIK representations. Particularly for high acceleration factors (R$\geq$54), NIK with PISCO achieves superior spatio-temporal reconstruction quality compared to state-of-the-art methods. Furthermore, an extensive analysis of the loss assumptions and stability shows PISCO's potential as versatile self-supervised k-space loss function for further applications and architectures. Code is available at: https://github.com/compai-lab/2025-pisco-spieker