Iterative Temporal-Spatial Transformer-based Cardiac T1 Mapping MRI Reconstruction

Abstract

The precise reconstruction of accelerated magnetic resonance imaging (MRI) brings about notable clinical advantages, such as enhanced diagnostic precision and decreased examination costs. In contrast, traditional cardiac MRI necessitates repetitive acquisitions across multiple heartbeats, resulting in prolonged acquisition times. Significant strides have been made in accelerating MRI through deep learning-based reconstruction methods. However, these existing methods encounter certain limitations: (1) The intricate nature of heart reconstruction involving multiple complex time-series data and image information poses a challenge in exploring nonlinear dependencies between temporal contexts. (2) Existing research often overlooks weight sharing in iterative frameworks, impeding the effective capture of long-range or non-local information in the data and, consequently, limiting improvements in model performance. In order to improve cardiac MRI reconstruction, we propose a novel temporal-spatial transformer with a strategy in this study. We perform multi-level spatiotemporal information feature aggregation across multiple adjacent views, establishing nonlinear dependencies between features and efficiently learning important information between adjacent cardiac temporal frames, based on the multi-level encoder and decoder architecture of the transformer. Additionally, in order to improve contextual awareness between neighboring views, we add cross-view attention for temporal information interaction and fusion. Furthermore, we introduce an iterative strategy for training weights during the reconstruction process, which improves feature fusion in critical locations and reduces the number of computations required to calculate global feature dependencies. Extensive experiments have demonstrated the substantial superiority of this procedure over the most advanced techniques, suggesting that it has broad potential for clinical use.