Conditional WGANs with Adaptive Gradient Balancing for Sparse MRI Reconstruction
This work addresses the challenge of preserving fine details and natural appearance in MRI scans for medical imaging applications, representing an incremental improvement over existing methods.
The paper tackles the problem of reconstructing sharp, artifact-free MRI images from highly undersampled k-space data by using a Conditional Wasserstein GAN with Adaptive Gradient Balancing, resulting in improved image quality compared to other techniques.
Recent sparse MRI reconstruction models have used Deep Neural Networks (DNNs) to reconstruct relatively high-quality images from highly undersampled k-space data, enabling much faster MRI scanning. However, these techniques sometimes struggle to reconstruct sharp images that preserve fine detail while maintaining a natural appearance. In this work, we enhance the image quality by using a Conditional Wasserstein Generative Adversarial Network combined with a novel Adaptive Gradient Balancing technique that stabilizes the training and minimizes the degree of artifacts, while maintaining a high-quality reconstruction that produces sharper images than other techniques.