用于压缩感知磁共振图像重建的神经架构搜索
Neural Architecture Search for Compressed Sensing Magnetic Resonance Image Reconstruction
AI总结：
本文提出用可微 NAS 在模型驱动 MR 重建流程中自动搜索 cell 结构，以更少算力取得更高 PSNR/SSIM，并验证其超参数敏感性与跨器官泛化性。
摘要：
近期研究表明，基于深度学习（DL）的压缩感知（CS）实现能够通过从欠采样的 k 空间数据重建 MR 图像，从而加速磁共振（MR）成像。然而，以往方法采用的网络架构均由人工设计。神经架构搜索（NAS）算法能够自动构建神经网络架构，并且已在多个视觉任务中表现优于人工设计的架构。受此启发，本文通过 NAS 而非人工尝试，针对 MR 图像重建问题提出了一种新颖且高效的网络。具体而言，本文将一个特定的 cell 结构集成到模型驱动的 MR 重建流程中，并以可微方式从灵活的预定义操作搜索空间中自动搜索该结构。实验结果表明，与以往最先进方法相比，所搜索到的网络在 PSNR 和 SSIM 方面能够取得更好的重建结果，同时计算资源消耗减少 4 至 6 倍。本文还开展了大量实验，以分析超参数如何影响重建性能和搜索到的结构，并在不同器官的 MR 数据集上评估了所搜索架构的泛化能力。所提出的方法能够在 MR 重建问题的计算成本与重建性能之间实现更好的权衡，具有良好的泛化性，并为其他医学图像应用的神经网络设计提供启示。评估代码将发布于 https://github.com/yjump/NAS-for-CSMRI。
英文摘要：
Recent works have demonstrated that deep learning (DL) based compressed sensing (CS) implementation can accelerate Magnetic Resonance (MR) Imaging by reconstructing MR images from sub-sampled k-space data. However, network architectures adopted in previous methods are all designed by handcraft. Neural Architecture Search (NAS) algorithms can automatically build neural network architectures which have outperformed human designed ones in several vision tasks. Inspired by this, here we proposed a novel and efficient network for the MR image reconstruction problem via NAS instead of manual attempts. Particularly, a specific cell structure, which was integrated into the model-driven MR reconstruction pipeline, was automatically searched from a flexible pre-defined operation search space in a differentiable manner. Experimental results show that our searched network can produce better reconstruction results compared to previous state-of-the-art methods in terms of PSNR and SSIM with 4-6 times fewer computation resources. Extensive experiments were conducted to analyze how hyper-parameters affect reconstruction performance and the searched structures. The generalizability of the searched architecture was also evaluated on different organ MR datasets. Our proposed method can reach a better trade-off between computation cost and reconstruction performance for MR reconstruction problem with good generalizability and offer insights to design neural networks for other medical image applications. The evaluation code will be available at https://github.com/yjump/NAS-for-CSMRI.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
