Self-Supervised Implicit CEST Reconstruction via Physics-Informed Lorentz Encoding

2026-07-07

AI Summary

This work addresses the ill-posed inverse problem in Z-spectrum reconstruction for multi-pool chemical exchange saturation transfer (CEST) MRI caused by highly sparse sampling. The authors propose a Lorentzian encoding (LE) framework that formulates reconstruction as a self-supervised implicit continuous coordinate learning task. By incorporating learnable Lorentzian line-shape basis functions as physical constraints, LE embeds CEST-specific priors into an implicit neural representation. This approach not only substantially improves reconstruction fidelity but also induces geometrically ordered trajectories in the latent space, enabling accurate metabolite quantification. With only 39 sparsely sampled points, the method achieves a peak signal-to-noise ratio (PSNR) of 57.58 dB and a structural similarity index (SSIM) of 0.9994, significantly outperforming existing techniques, and facilitates high-fidelity amide proton transfer (APT), nuclear Overhauser effect (NOE), and magnetization transfer (MT) imaging.

Abstract

Multi-Pool Chemical Exchange Saturation Transfer (CEST) MRI provides valuable metabolic information but is clinically limited by long acquisition times. Although sparse sampling reduces scanning time, reconstructing high-resolution Z-spectra from limited data remains an ill-posed inverse problem. Conventional interpolation and generic Implicit Neural Rep-resentations (INRs) often lack physical constraints, leading to spectral artifacts and physically invalid signals. To address this, we propose Lorentz Encoding (LE), a physics-informed framework that formulates CEST reconstruction as a self-supervised reconstruction task via implicit continuous coordinate learning. Unlike generic positional encodings, LE regularizes the continuous spectral mapping by projecting sparse coordinates into a physically constrained space governed by a combination of parametric Lorentzian profiles with learnable basis functions. This mechanism effectively reduces noise and enforces consistency with physical models. Experiments on in vivo human brain data demonstrate that LE significantly outperforms state-of-the-art methods. Specifically, under a 39-point sampling strategy, LE achieves a PSNR of 57.58 dB and an SSIM of 0.9994. Furthermore, the learned physics-informed encodings form a continuous, geometrically ordered trajectory in the latent space, ensuring accurate quantitative metabo-lite mapping (APT, NOE, MT).

Problem

• CEST MRI
• Z-spectrum reconstruction
• sparse sampling
• ill-posed inverse problem
• spectral artifacts

Innovation

• Lorentz Encoding
• Physics-Informed Neural Representation
• Self-Supervised Reconstruction
• CEST MRI
• Implicit Neural Representation