Learning the Effect of Registration Hyperparameters with HyperMorph
Martinos Center for Biomedical Imaging, Massachusetts General Hospital（马萨诸塞州总医院马丁诺斯生物医学成像中心）；Department of Radiology, Harvard Medical School（哈佛医学院放射学系）；Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology（麻省理工学院计算机科学与人工智能实验室）
Andrew Hoopes, Malte Hoffmann, Douglas N. Greve, Bruce Fischl, John Guttag, Adrian V. Dalca
备注：
Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) at https://www.melba-journal.org
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 learning 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.
HyperMorph: Amortized Hyperparameter Learning for Image Registration
Martinos Center for Biomedical Imaging, MGH（马萨诸塞总医院马丁诺斯生物医学影像中心）；Department of Radiology, Harvard Medical School（哈佛医学院放射学系）；Computer Science and Artificial Intelligence Lab, MIT（麻省理工学院计算机科学与人工智能实验室）
Unsupervised learning of spatially varying regularization for diffeomorphic image registration
Department of Radiology and Radiological Science, Johns Hopkins School of Medicine, MD, USA（放射科与放射科学系，约翰霍普金斯医学院，马里兰州，美国）；Image Analysis and Communications Laboratory, Department of Electrical and Computer Engineering, Johns Hopkins University, MD, USA（图像分析与通信实验室，电气与计算机工程系，约翰霍普金斯大学，马里兰州，美国）；Department of Electrical and Computer Engineering, Vanderbilt University, TN, USA（电气与计算机工程系，范德比尔特大学，田纳西州，美国）；NVIDIA Corporation, Santa Clara, CA, USA（英伟达公司，圣克拉拉，加利福尼亚州，美国）
Double-Uncertainty Guided Spatial and Temporal Consistency Regularization Weighting for Learning-based Abdominal Registration
The Chinese University of Hong Kong（香港中文大学）；Brigham and Women’s Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）；Tencent Jarvis Lab（腾讯医疗健康（深圳）有限公司（腾讯医疗AI实验室/腾讯天衍实验室））；Tsinghua University（清华大学）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Unsupervised Deformable Image Registration with Structural Nonparametric Smoothing
Cornell University（康奈尔大学）；Hunan University（湖南大学）；University of Pennsylvania（宾夕法尼亚大学）；Johns Hopkins University（约翰霍普金斯大学）；Shanghai Jiao Tong University（上海交通大学）；University of Birmingham（伯明翰大学）；University of Manchester（曼彻斯特大学）
Factored Levenberg-Marquardt for Diffeomorphic Image Registration: An efficient optimizer for FireANTs
Department of Computer and Information Science（计算机与信息科学系）；University of Pennsylvania（宾夕法尼亚大学）；Department of Electrical and Systems Engineering（电气与系统工程系）；Department of Radiology & Penn Image Computing and Science Laboratory (PICSL)（放射科及宾夕法尼亚大学图像计算与科学实验室（PICSL））；Perelman School of Medicine, University of Pennsylvania（佩尔曼医学学院，宾夕法尼亚大学）
GSMorph: Gradient Surgery for cine-MRI Cardiac Deformable Registration
University of Leeds（利兹大学）；Radboud University Medical Centre（拉德堡德大学医学中心）；Netherlands Cancer Institute（荷兰癌症研究所）；Shenzhen University（深圳大学）；Shenzhen RayShape Medical Technology Co., Ltd（深圳睿心医疗科技有限公司）
Rapid patient-specific neural networks for intraoperative X-ray to volume registration
Harvard-MIT Health Sciences and Technology, Massachusetts Institute of Technology（哈佛-麻省理工健康科学与技术, 麻省理工学院）；Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology（计算机科学与人工智能实验室, 麻省理工学院）；Department of Radiology, Harvard Medical School（哈佛医学院放射科）；Saint Luke’s Marion Bloch Neuroscience Institute（圣路易斯马里恩布洛克神经科学研究所）；Department of Critical Care Medicine, Shriners Children’s Hospital（谢尔曼儿童医院重症医学科）；Department of Interventional Neuroradiology, Boston Children’s Hospital（波士顿儿童医院介入神经放射科）；Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital（阿提努拉A·马丁诺斯生物医学成像中心, 麻省总医院）
JUMP: A joint multimodal registration pipeline for neuroimaging with minimal preprocessing
Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）；Institut de Neurociències Department of Biomedicine, University of Barcelona（巴塞罗那大学生物医学系神经科学研究所）；Martinos Center for Biomedical Imaging, MGH and Harvard Medical School（马蒂诺斯生物医学成像中心，麻省总医院和哈佛医学院）；Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology（麻省理工学院计算机科学与人工智能实验室）；Centre for Medical Image Computing, University College London（伦敦大学学院医学图像计算中心）；Centro de Investigación Biomédica en Red de Bioingeniería, Biomateriales y Nanomedicina, ISCIII（生物工程、生物材料与纳米医学生物医学研究中心（ISCIII））；Nuclear Medicine Department, Hospital Clínic（临床医院核医学科）；Institut d’Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS)（奥古斯特·皮·苏涅尔生物医学研究所（IDIBAPS））
