A scan-specific unsupervised method for parallel MRI reconstruction via implicit neural representation
This work addresses the challenge of accelerating MRI data acquisition for medical imaging, but it is incremental as it applies an existing deep learning paradigm (INR) to a specific domain problem.
The paper tackles the problem of reconstructing artifact-free MRI images from highly undersampled k-space data in parallel MRI by using implicit neural representation (INR) to model the image as a continuous function, resulting in outperforming existing methods by suppressing aliasing artifacts and noise, especially at higher acceleration rates and smaller auto-calibration signal sizes.
Parallel imaging is a widely-used technique to accelerate magnetic resonance imaging (MRI). However, current methods still perform poorly in reconstructing artifact-free MRI images from highly undersampled k-space data. Recently, implicit neural representation (INR) has emerged as a new deep learning paradigm for learning the internal continuity of an object. In this study, we adopted INR to parallel MRI reconstruction. The MRI image was modeled as a continuous function of spatial coordinates. This function was parameterized by a neural network and learned directly from the measured k-space itself without additional fully sampled high-quality training data. Benefitting from the powerful continuous representations provided by INR, the proposed method outperforms existing methods by suppressing the aliasing artifacts and noise, especially at higher acceleration rates and smaller sizes of the auto-calibration signals. The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI.