Missing Data Estimation for MR Spectroscopic Imaging via Mask-Free Deep Learning Methods

TL;DR

This paper introduces a novel deep learning framework that implicitly detects and estimates missing data in MRSI metabolic maps without requiring explicit masks, significantly improving restoration accuracy over traditional methods.

Contribution

The authors develop the first mask-free deep learning approach for MRSI data restoration, utilizing 2D and 3D U-Net architectures with a progressive training strategy for robustness.

Findings

Outperforms traditional interpolation methods in MSE and SSIM metrics.

Achieves high fidelity in metabolically heterogeneous and ventricular regions.

Generalizes well to real-world datasets without retraining.

Abstract

Magnetic Resonance Spectroscopic Imaging (MRSI) is a powerful tool for non-invasive mapping of brain metabolites, providing critical insights into neurological conditions. However, its utility is often limited by missing or corrupted data due to motion artifacts, magnetic field inhomogeneities, or failed spectral fitting-especially in high resolution 3D acquisitions. To address this, we propose the first deep learning-based, mask-free framework for estimating missing data in MRSI metabolic maps. Unlike conventional restoration methods that rely on explicit masks to identify missing regions, our approach implicitly detects and estimates these areas using contextual spatial features through 2D and 3D U-Net architectures. We also introduce a progressive training strategy to enhance robustness under varying levels of data degradation. Our method is evaluated on both simulated and real patient datasets and consistently outperforms traditional interpolation techniques such as cubic and linear interpolation. The 2D model achieves an MSE of 0.002 and an SSIM of 0.97 with 20% missing voxels, while the 3D model reaches an MSE of 0.001 and an SSIM of 0.98 with 15% missing voxels. Qualitative results show improved fidelity in estimating missing data, particularly in metabolically heterogeneous regions and ventricular regions. Importantly, our model generalizes well to real-world datasets without requiring retraining or mask input. These findings demonstrate the effectiveness and broad applicability of mask-free deep learning for MRSI restoration, with strong potential for clinical and research integration.