Parallel imaging, a fast MRI technique, involves dynamic adjustments based on the configuration i.e. number, positioning, and sensitivity of the coils with respect to the anatomy under study. Conventional deep learning-based image reconstruction models have to be trained or fine-tuned for each configuration, posing a barrier to clinical translation, given the lack of computational resources and machine learning expertise for clinicians to train models at deployment. Joint training on diverse datasets learns a single weight set that might underfit to deviated configurations. We propose, HyperCoil-Recon, a hypernetwork-based coil configuration task-switching network for multi-coil MRI reconstruction that encodes varying configurations of the numbers of coils in a multi-tasking perspective, posing each configuration as a task. The hypernetworks infer and embed task-specific weights into the reconstruction network, 1) effectively utilizing the contextual knowledge of common and varying image features among the various fields-of-view of the coils, and 2) enabling generality to unseen configurations at test time. Experiments reveal that our approach 1) adapts on the fly to various unseen configurations up to 32 coils when trained on lower numbers (i.e. 7 to 11) of randomly varying coils, and to 120 deviated unseen configurations when trained on 18 configurations in a single model, 2) matches the performance of coil configuration-specific models, and 3) outperforms configuration-invariant models with improvement margins of around 1 dB / 0.03 and 0.3 dB / 0.02 in PSNR / SSIM for knee and brain data. Our code is available at https://github.com/sriprabhar/HyperCoil-Recon

翻译：并行成像作为一种快速MRI技术，需根据采集过程中线圈的配置（即数量、位置及相对于被研究解剖结构的灵敏度）进行动态调整。传统的基于深度学习的图像重建模型必须针对每种配置进行训练或微调，这给临床转化带来了障碍，因为临床医生在部署时缺乏计算资源和机器学习专业知识。在多样化数据集上的联合训练会学习单一的权重集，可能无法充分适应偏离的配置。我们提出HyperCoil-Recon，一种基于超网络的线圈配置任务切换网络，用于多线圈MRI重建。该方法从多任务视角对不同线圈数量配置进行编码，将每种配置视为一个任务。超网络推断并嵌入任务特定的权重到重建网络，从而：1）有效利用各线圈视野中常见与变化的图像特征的上下文知识；2）在测试时能够泛化到未见过的配置。实验表明，我们的方法：1）在仅训练少量随机变化线圈（如7至11个）时，即可动态适应多达32个线圈的各种未见配置；当在18种配置上训练单一模型时，可适应120种未见配置的偏移；2）其性能与针对特定线圈配置的模型相当；3）优于配置不变模型，在膝盖和脑部数据上PSNR/SSIM分别提升约1dB/0.03和0.3dB/0.02。我们的代码发布于https://github.com/sriprabhar/HyperCoil-Recon。