School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China.
Radiotherapy Business Unit, Shanghai United Imaging Healthcare Co., Ltd., Shanghai, 201807, China.
J Imaging Inform Med. 2024 Aug;37(4):1969-1979. doi: 10.1007/s10278-024-01057-2. Epub 2024 Mar 8.
Magnetic resonance imaging (MRI) occupies a pivotal position within contemporary diagnostic imaging modalities, offering non-invasive and radiation-free scanning. Despite its significance, MRI's principal limitation is the protracted data acquisition time, which hampers broader practical application. Promising deep learning (DL) methods for undersampled magnetic resonance (MR) image reconstruction outperform the traditional approaches in terms of speed and image quality. However, the intricate inter-coil correlations have been insufficiently addressed, leading to an underexploitation of the rich information inherent in multi-coil acquisitions. In this article, we proposed a method called "Multi-coil Feature Fusion Variation Network" (MFFVN), which introduces an encoder to extract the feature from multi-coil MR image directly and explicitly, followed by a feature fusion operation. Coil reshaping enables the 2D network to achieve satisfactory reconstruction results, while avoiding the introduction of a significant number of parameters and preserving inter-coil information. Compared with VN, MFFVN yields an improvement in the average PSNR and SSIM of the test set, registering enhancements of 0.2622 dB and 0.0021 dB respectively. This uplift can be attributed to the integration of feature extraction and fusion stages into the network's architecture, thereby effectively leveraging and combining the multi-coil information for enhanced image reconstruction quality. The proposed method outperforms the state-of-the-art methods on fastMRI dataset of multi-coil brains under a fourfold acceleration factor without incurring substantial computation overhead.
磁共振成像（MRI）在当代诊断成像方式中占据着关键地位，提供了非侵入性和无辐射的扫描。尽管它很重要，但 MRI 的主要限制是数据采集时间长，这阻碍了更广泛的实际应用。有前途的用于欠采样磁共振（MR）图像重建的深度学习（DL）方法在速度和图像质量方面优于传统方法。然而，复杂的线圈间相关性尚未得到充分解决，导致多线圈采集所固有的丰富信息未得到充分利用。在本文中，我们提出了一种称为“多线圈特征融合变分网络”（MFFVN）的方法，该方法引入了一个编码器，直接而明确地从多线圈 MR 图像中提取特征，然后进行特征融合操作。线圈重塑使 2D 网络能够实现令人满意的重建结果，同时避免引入大量参数并保留线圈间信息。与 VN 相比，MFFVN 提高了测试集的平均 PSNR 和 SSIM，分别提高了 0.2622dB 和 0.0021dB。这种提升可以归因于将特征提取和融合阶段集成到网络架构中，从而有效地利用和组合多线圈信息，以提高图像重建质量。在四倍加速因子下，该方法在多线圈大脑 fastMRI 数据集上的表现优于最先进的方法，且不会带来大量的计算开销。
