Compared with 2D MRI, 3D MRI provides superior volumetric spatial resolution and signal-to-noise ratio. However, it is more challenging to reconstruct 3D MRI images. Current methods are mainly based on convolutional neural networks (CNN) with small kernels, which are difficult to scale up to have sufficient fitting power for 3D MRI reconstruction due to the large image size and GPU memory constraint. Furthermore, MRI reconstruction is a deconvolution problem, which demands long-distance information that is difficult to capture by CNNs with small convolution kernels. The multi-layer perceptron (MLP) can model such long-distance information, but it requires a fixed input size. In this paper, we proposed Recon3DMLP, a hybrid of CNN modules with small kernels for low-frequency reconstruction and adaptive MLP (dMLP) modules with large kernels to boost the high-frequency reconstruction, for 3D MRI reconstruction. We further utilized the circular shift operation based on MRI physics such that dMLP accepts arbitrary image size and can extract global information from the entire FOV. We also propose a GPU memory efficient data fidelity module that can reduce $>$50$\%$ memory. We compared Recon3DMLP with other CNN-based models on a high-resolution (HR) 3D MRI dataset. Recon3DMLP improves HR 3D reconstruction and outperforms several existing CNN-based models under similar GPU memory consumption, which demonstrates that Recon3DMLP is a practical solution for HR 3D MRI reconstruction.

翻译：与2D MRI相比，3D MRI具有优越的体积空间分辨率和信噪比。然而，重建3D MRI图像更具挑战性。当前方法主要基于小核卷积神经网络（CNN），但由于图像尺寸大和GPU内存限制，这些网络难以扩展至具有足够拟合能力的规模用于3D MRI重建。此外，MRI重建是一个反卷积问题，需要长距离信息，而小卷积核的CNN难以捕获这类信息。多层感知机（MLP）能够建模长距离信息，但其需要固定的输入尺寸。本文提出Recon3DMLP，一种混合架构——结合用于低频重建的小核CNN模块和用于提升高频重建的大核自适应MLP（dMLP）模块——用于3D MRI重建。我们进一步利用基于MRI物理的循环移位操作，使dMLP能够接受任意图像尺寸，并从整个视野中提取全局信息。我们还提出一个节省GPU内存的数据保真模块，可减少超过50%的内存占用。我们在高分辨率（HR）3D MRI数据集上比较了Recon3DMLP与其他基于CNN的模型。在相似GPU内存消耗下，Recon3DMLP提升了HR 3D重建效果，并优于多个现有基于CNN的模型，这表明Recon3DMLP是HR 3D MRI重建的实用解决方案。