Multi-Weight Respecification of Scan-specific Learning for Parallel Imaging
This work addresses noise and acceleration issues in MRI reconstruction for medical imaging, but it is incremental as it builds upon the existing RAKI method.
The paper tackled the problem of noise amplification and poor performance at high acceleration rates in parallel MRI reconstruction by proposing a multi-weight method (MW-RAKI) and its residual version (MW-rRAKI), resulting in noticeably better reconstruction performances, particularly at high acceleration rates.
Parallel imaging is widely used in magnetic resonance imaging as an acceleration technology. Traditional linear reconstruction methods in parallel imaging often suffer from noise amplification. Recently, a non-linear robust artificial-neural-network for k-space interpolation (RAKI) exhibits superior noise resilience over other linear methods. However, RAKI performs poorly at high acceleration rates, and needs a large amount of autocalibration signals as the training samples. In order to tackle these issues, we propose a multi-weight method that implements multiple weighting matrices on the undersampled data, named as MW-RAKI. Enforcing multiple weighted matrices on the measurements can effectively reduce the influence of noise and increase the data constraints. Furthermore, we incorporate the strategy of multiple weighting matrixes into a residual version of RAKI, and form MW-rRAKI.Experimental compari-sons with the alternative methods demonstrated noticeably better reconstruction performances, particularly at high acceleration rates.