DiffNMR: Advancing Inpainting of Randomly Sampled Nuclear Magnetic Resonance Signals

TL;DR

This paper introduces DiffNMR, a deep learning approach using diffusion models to improve the reconstruction of non-uniform sampled NMR spectra, reducing artifacts and enhancing spectral quality.

Contribution

It applies diffusion models to NMR spectrum reconstruction, demonstrating improved results over traditional methods and highlighting the benefits of using time-frequency domain data.

Findings

DiffNMR achieves high-quality spectral reconstructions from sparse data.

Diffusion models outperform existing reconstruction techniques.

Time-frequency domain data yields better results than time-time domain data.

Abstract

Nuclear Magnetic Resonance (NMR) spectroscopy leverages nuclear magnetization to probe molecules' chemical environment, structure, and dynamics, with applications spanning from pharmaceuticals to the petroleum industry. Despite its utility, the high cost of NMR instrumentation, operation and the lengthy duration of experiments necessitate the development of computational techniques to optimize acquisition times. Non-Uniform sampling (NUS) is widely employed as a sub-sampling method to address these challenges, but it often introduces artifacts and degrades spectral quality, offsetting the benefits of reduced acquisition times. In this work, we propose the use of deep learning techniques to enhance the reconstruction quality of NUS spectra. Specifically, we explore the application of diffusion models, a relatively untapped approach in this domain. Our methodology involves applying diffusion models to both time-time and time-frequency NUS data, yielding satisfactory reconstructions of challenging spectra from the benchmark Artina dataset. This approach demonstrates the potential of diffusion models to improve the efficiency and accuracy of NMR spectroscopy as well as the superiority of using a time-frequency domain data over the time-time one, opening new landscapes for future studies.