Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
To overcome the artifacts and low signal-to-noise ratio endemic to low-field MRI, this work pairs a forward physics-guided degradation model with an adversarial super-resolution reconstruction network (MRSRGAN). The framework replaces naive bicubic downsampling with realistic simulations of $B_0$ field inhomogeneities, chemical shift artifacts, noise, and slice-profile blur to synthesize faithful paired training data. Trained with a modified spectral angle mapper loss and slice-profile deconvolution targets, the model achieves superior PSNR, SSIM, and NIQE scores while successfully generalizing to real-world clinical scans.
Low-field MRI can approach high-field diagnostic fidelity once generative super-resolution is grounded in true scanner physics—such as $B_0$ inhomogeneities and chemical shift—rather than synthetic bicubic downsampling.
Magnetic Resonance Imaging (MRI) often suffers from low signal-to-noise ratio (SNR) and limited spatial resolution, which compromise clinical precision. This study aims to address these challenges by developing a physics-guided degradation model (PGDM) and a novel deep learning framework, Magnetic Resonance Super-Resolution GAN Imaging (MRSRGAN), for improved super-resolution reconstruction of MRI images. The proposed approach consists of two stages: (1) a physics-guided degradation model that simulates low-field MRI conditions by incorporating artifacts such as blur, B0 inhomogeneity, chemical shift effects, down-sampling, and noise to generate paired low-resolution (LR) and high-resolution (HR) training datasets; and (2) an MRSRGAN-based reconstruction network utilizing a hybrid loss function, including modified spectral angle mapper (MSAM) and sharpened ground truth images based on de-convolution of slice profile-based kernels to restore high-SNR and high-resolution images. Experimental validation demonstrates that the proposed method achieves superior spatial resolution, enhanced SNR, improved peak signal-to-noise ratio (PSNR), higher structural similarity index (SSIM), reduced MSAM error, and better non-reference image quality evaluation (NIQE) metrics. Furthermore, it effectively reduces artifacts and demonstrates robustness on real MRI datasets. The MRSRGAN framework, guided by the physics-informed degradation model, provides a significant improvement in MRI image quality, enhancing spatial resolution and diagnostic accuracy. Its demonstrated robustness and effectiveness on real MRI datasets highlight its potential to resolution enhancement for precise diagnostic imaging.