PISCO: Self-Supervised k-Space Regularization for Improved Neural Implicit k-Space Representations of Dynamic MRI
This work addresses a critical bottleneck in dynamic MRI reconstruction for medical imaging applications, offering a novel regularization technique that enhances performance without additional data, though it is incremental as it builds on existing neural implicit representations.
The paper tackles the problem of overfitting in neural implicit k-space representations for dynamic MRI when training data is limited due to reduced acquisition time, and introduces a self-supervised k-space loss function (PISCO) that improves reconstruction quality, achieving superior results at high acceleration factors (R≥54) compared to state-of-the-art methods.
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