Variable Augmented Network for Invertible MR Coil Compression
This work addresses data management issues in medical imaging for MRI practitioners, but it is incremental as it builds on existing normalizing flow-based models.
The paper tackles the problem of data storage and reconstruction speed in parallel MRI by proposing a novel variable augmentation network for invertible coil compression, achieving higher compression effects compared to traditional non-deep learning approaches, with performance not susceptible to different numbers of virtual coils.
A large number of coils are able to provide enhanced signal-to-noise ratio and improve imaging performance in parallel imaging. Nevertheless, the increasing growth of coil number simultaneously aggravates the drawbacks of data storage and reconstruction speed, especially in some iterative reconstructions. Coil compression addresses these issues by generating fewer virtual coils. In this work, a novel variable augmentation network for invertible coil compression termed VAN-ICC is presented. It utilizes inherent reversibility of normalizing flow-based models for high-precision compression and invertible recovery. By employing the variable augmentation technology to image/k-space variables from multi-coils, VAN-ICC trains invertible networks by finding an invertible and bijective function, which can map the original data to the compressed counterpart and vice versa. Experiments conducted on both fully-sampled and under-sampled data verified the effectiveness and flexibility of VAN-ICC. Quantitative and qualitative comparisons with traditional non-deep learning-based approaches demonstrated that VAN-ICC can carry much higher compression effects. Additionally, its performance is not susceptible to different number of virtual coils.