Channel Attention Networks for Robust MR Fingerprinting Matching
This work provides a more accurate and potentially faster method for generating tissue parameter maps for medical imaging, which could benefit clinicians and researchers using MRF.
This paper addresses the challenges of erroneous and slow parametric map generation in Magnetic Resonance Fingerprinting (MRF) by proposing a novel neural network architecture. The method reduces reconstruction error for tissue parameters by 8.88% for T1 and 75.44% for T2 compared to state-of-the-art methods.
Magnetic Resonance Fingerprinting (MRF) enables simultaneous mapping of multiple tissue parameters such as T1 and T2 relaxation times. The working principle of MRF relies on varying acquisition parameters pseudo-randomly, so that each tissue generates its unique signal evolution during scanning. Even though MRF provides faster scanning, it has disadvantages such as erroneous and slow generation of the corresponding parametric maps, which needs to be improved. Moreover, there is a need for explainable architectures for understanding the guiding signals to generate accurate parametric maps. In this paper, we addressed both of these shortcomings by proposing a novel neural network architecture consisting of a channel-wise attention module and a fully convolutional network. The proposed approach, evaluated over 3 simulated MRF signals, reduces error in the reconstruction of tissue parameters by 8.88% for T1 and 75.44% for T2 with respect to state-of-the-art methods. Another contribution of this study is a new channel selection method: attention-based channel selection. Furthermore, the effect of patch size and temporal frames of MRF signal on channel reduction are analyzed by employing a channel-wise attention.