Physics-Informed DeepMRI: k-Space Interpolation Meets Heat Diffusion | IEEE Journals & Magazine | IEEE Xplore

Physics-Informed DeepMRI: k-Space Interpolation Meets Heat Diffusion


Abstract:

Recently, diffusion models have shown considerable promise for MRI reconstruction. However, extensive experimentation has revealed that these models are prone to generati...Show More

Abstract:

Recently, diffusion models have shown considerable promise for MRI reconstruction. However, extensive experimentation has revealed that these models are prone to generating artifacts due to the inherent randomness involved in generating images from pure noise. To achieve more controlled image reconstruction, we reexamine the concept of interpolatable physical priors in k-space data, focusing specifically on the interpolation of high-frequency (HF) k-space data from low-frequency (LF) k-space data. Broadly, this insight drives a shift in the generation paradigm from random noise to a more deterministic approach grounded in the existing LF k-space data. Building on this, we first establish a relationship between the interpolation of HF k-space data from LF k-space data and the reverse heat diffusion process, providing a fundamental framework for designing diffusion models that generate missing HF data. To further improve reconstruction accuracy, we integrate a traditional physics-informed k-space interpolation model into our diffusion framework as a data fidelity term. Experimental validation using publicly available datasets demonstrates that our approach significantly surpasses traditional k-space interpolation methods, deep learning-based k-space interpolation techniques, and conventional diffusion models, particularly in HF regions. Finally, we assess the generalization performance of our model across various out-of-distribution datasets. Our code are available at https://github.com/ZhuoxuCui/Heat-Diffusion.
Published in: IEEE Transactions on Medical Imaging ( Volume: 43, Issue: 10, October 2024)
Page(s): 3503 - 3520
Date of Publication: 18 September 2024

ISSN Information:

PubMed ID: 39292579

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.