Dual-Domain Inter-Frame Feature Enhancement Network for cardiac MR image reconstruction

作     者：Ding, Wenzhe Liu, Xiaohan Liu, Yiming Pang, Yanwei 

作者机构：Tianjin Univ Sch Elect & Informat Engn TJK BIIT Lab Tianjin 300072 Peoples R China 

出 版 物：《BIOMEDICAL SIGNAL PROCESSING AND CONTROL》 (Biomed. Signal Process. Control)

年 卷 期：2025年第104卷

核心收录：

学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 10[医学] 

基　　金：National Key Research and Development Program of China [2023YFC2411100] National Natural Science Foundation of China Chinese Institutes for Medical Research [CX23YZ16] 

主　　题：Deep learning Cardiac MRI Cardiac cine reconstruction Spatio-temporal information 

摘      要：The accelerated MR image reconstruction algorithm based on deep learning has demonstrated tremendous potential in improving efficiency and performance. Compared with static reconstruction, the utilization of temporal correlation is the key to cardiac cine MR image reconstruction, and modeling the information of temporal dimension during the reconstruction process can effectively reduce artifacts. However, current methods typically depend on 3D convolutional neural networks or recurrent neural networks, which may not be able to effectively capture both local feature details and long-range feature dependencies at the same time. In this paper, we propose a Dual-Domain Inter-Frame Feature Enhancement Network (DIFENet) for cardiac MR image reconstruction to extract beneficial information from the neighboring frames. First, an inter- frame feature fusion strategy is designed to learn the non-local spatio-temporal correlations of cardiac motion with attention mechanisms from the features of multi-frame data. Moreover, the fused inter-frame features are used to provide proper guidance for the subsequent refinement of reconstructed details by modulating the multi-scale features. Beyond that, a dual-domain parallel structure is incorporated into the framework, considering the complementarity of inter-frame features in the frequency and image domains. Comprehensive experiments demonstrate that the proposed method consistently outperforms other state-of-the-art static and dynamic reconstruction methods at multiple acceleration rates.