Undersampled MRI Reconstruction with Side Information-Guided Normalisation
This work addresses the incremental improvement of MRI reconstruction quality for medical imaging applications by leveraging often-overlooked side information.
The paper tackled the problem of undersampled MRI reconstruction by incorporating appearance-related side information as normalization parameters in CNNs, resulting in significant improvements over baseline architectures across brain and knee images at various acceleration rates.
Magnetic resonance (MR) images exhibit various contrasts and appearances based on factors such as different acquisition protocols, views, manufacturers, scanning parameters, etc. This generally accessible appearance-related side information affects deep learning-based undersampled magnetic resonance imaging (MRI) reconstruction frameworks, but has been overlooked in the majority of current works. In this paper, we investigate the use of such side information as normalisation parameters in a convolutional neural network (CNN) to improve undersampled MRI reconstruction. Specifically, a Side Information-Guided Normalisation (SIGN) module, containing only few layers, is proposed to efficiently encode the side information and output the normalisation parameters. We examine the effectiveness of such a module on two popular reconstruction architectures, D5C5 and OUCR. The experimental results on both brain and knee images under various acceleration rates demonstrate that the proposed method improves on its corresponding baseline architectures with a significant margin.