Hoopes Andrew, Hoffmann Malte, Greve Douglas N, Fischl Bruce, Guttag John, Dalca Adrian V
Martinos Center for Biomedical Imaging, Massachusetts General Hospital.
Department of Radiology, Harvard Medical School.
J Mach Learn Biomed Imaging. 2022 Mar;1. Epub 2022 Apr 7.
We introduce HyperMorph, a framework that facilitates efficient hyperparameter tuning in learning-based deformable image registration. Classical registration algorithms perform an iterative pair-wise optimization to compute a deformation field that aligns two images. Recent learning-based approaches leverage large image datasets to learn a function that rapidly estimates a deformation for a given image pair. In both strategies, the accuracy of the resulting spatial correspondences is strongly influenced by the choice of certain hyperparameter values. However, an effective hyperparameter search consumes substantial time and human effort as it often involves training multiple models for different fixed hyperparameter values and may lead to suboptimal registration. We propose an amortized hyperparameter learning strategy to alleviate this burden by the impact of hyperparameters on deformation fields. We design a meta network, or hypernetwork, that predicts the parameters of a registration network for input hyperparameters, thereby comprising a single model that generates the optimal deformation field corresponding to given hyperparameter values. This strategy enables fast, high-resolution hyperparameter search at test-time, reducing the inefficiency of traditional approaches while increasing flexibility. We also demonstrate additional benefits of HyperMorph, including enhanced robustness to model initialization and the ability to rapidly identify optimal hyperparameter values specific to a dataset, image contrast, task, or even anatomical region, all without the need to retrain models. We make our code publicly available at http://hypermorph.voxelmorph.net.
我们介绍了HyperMorph，这是一个有助于在基于学习的可变形图像配准中进行高效超参数调整的框架。经典的配准算法通过迭代成对优化来计算使两幅图像对齐的变形场。最近基于学习的方法利用大型图像数据集来学习一个函数，该函数能快速估计给定图像对的变形。在这两种策略中，所得空间对应关系的准确性都受到某些超参数值选择的强烈影响。然而，有效的超参数搜索会消耗大量时间和人力，因为它通常涉及为不同的固定超参数值训练多个模型，并且可能导致次优配准。我们提出一种摊销超参数学习策略，以减轻超参数对变形场的影响带来的负担。我们设计了一个元网络，即超网络，它为输入的超参数预测配准网络的参数，从而形成一个单一模型，该模型生成与给定超参数值对应的最优变形场。这种策略能够在测试时进行快速、高分辨率的超参数搜索，减少传统方法的低效率，同时增加灵活性。我们还展示了HyperMorph的其他优点，包括增强对模型初始化的鲁棒性以及能够快速识别特定于数据集、图像对比度、任务甚至解剖区域的最优超参数值，而无需重新训练模型。我们将代码公开在http://hypermorph.voxelmorph.net。
