Are Registration Uncertainty and Error Monotonically Associated
Brigham and Women’s Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）；Graduate School of Frontier Sciences, The University of Tokyo（东京大学前沿科学研究生院）；Department of Automation, Tsinghua University（清华大学自动化系）；Center for Advanced Intelligence Project, RIKEN（理化学研究所先进智能项目中心）
Jie Luo, Sarah Frisken, Duo Wang, Alexandra Golby, Masashi Sugiyama, William M. Wells
In image-guided neurosurgery, current commercial systems usually provide only rigid registration, partly because it is harder to predict, validate and understand non-rigid registration error. For instance, when surgeons see a discrepancy in aligned image features, they may not be able to distinguish between registration error and actual tissue deformation caused by tumor resection. In this case, the spatial distribution of registration error could help them make more informed decisions, e.g., ignoring the registration where the estimated error is high. However, error estimates are difficult to acquire. Probabilistic image registration (PIR) methods provide measures of registration uncertainty, which could be a surrogate for assessing the registration error. It is intuitive and believed by many clinicians that high uncertainty indicates a large error. However, the monotonic association between uncertainty and error has not been examined in image registration literature. In this pilot study, we attempt to address this fundamental problem by looking at one PIR method, the Gaussian process (GP) registration. We systematically investigate the relation between GP uncertainty and error based on clinical data and show empirically that there is a weak-to-moderate positive monotonic correlation between point-wise GP registration uncertainty and non-rigid registration error.
Brigham and Women’s Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）；Graduate School of Frontier Sciences, The University of Tokyo（东京大学前沿科学研究生院）；School of Computing, Queen‘s University（女王大学计算学院）；School of Engineering Science, Simon Fraser University（西蒙弗雷泽大学工程科学学院）；Computing Science Department, University of Alberta（阿尔伯塔大学计算科学系）；Ecole de Technologie Superieure（高等技术学院）；Center for Advanced Intelligence Project, RIKEN（理化学研究所高级智能项目中心）
Estimating the uncertainty in (probabilistic) image registration enables, e.g., surgeons to assess the operative risk based on the trustworthiness of the registered image data. If surgeons receive inaccurately calculated registration uncertainty and misplace unwarranted confidence in the alignment solutions, severe consequences may result. For probabilistic image registration (PIR), the predominant way to quantify the registration uncertainty is using summary statistics of the distribution of transformation parameters. The majority of existing research focuses on trying out different summary s…
Imperial College London（帝国理工学院）；Technische Universität München（慕尼黑工业大学）；Sharif University of Technology（谢里夫理工大学）；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡大学）
We develop a new Bayesian model for non-rigid registration of three-dimensional medical images, with a focus on uncertainty quantification. Probabilistic registration of large images with calibrated uncertainty estimates is difficult for both computational and modelling reasons. To address the computational issues, we explore connections between the Markov chain Monte Carlo by backpropagation and the variational inference by backpropagation frameworks, in order to efficiently draw samples from the posterior distribution of transformation parameters. To address the modelling issues, we formulat…
This paper presents a novel probabilistic voxel selection strategy for medical image registration in time-sensitive contexts, where the goal is aggressive voxel sampling (e.g. using less than 1% of the total number) while maintaining registration accuracy and low failure rate. We develop a Bayesian framework whereby, first, a voxel sampling probability field (VSPF) is built based on the uncertainty on the transformation parameters. We then describe a practical, multi-scale registration algorithm, where, at each optimization iteration, different voxel subsets are sampled based on the VSPF. The …
Harvard Medical School（哈佛医学院）；INRIA Sophia Antipolis-Méditerranée（法国国家信息与自动化研究所索菲亚-安提波利斯-地中海中心）；University of North Carolina（北卡罗来纳大学）；Massachusetts Institute of Technology（麻省理工学院）
This paper presents a novel mathematical framework for representing uncertainty in large deformation diffeomorphic image registration. The Bayesian posterior distribution over the deformations aligning a moving and a fixed image is approximated via a variational formulation. A stochastic differential equation (SDE) modeling the deformations as the evolution of a time-varying velocity field leads to a prior density over deformations in the form of a Gaussian process. This permits estimating the full posterior distribution in order to represent uncertainty, in contrast to methods in which the po…
University College London（伦敦大学学院）；Massachusetts General Hospital（马萨诸塞总医院）；Harvard Medical School（哈佛医学院）；Massachusetts Institute of Technology（麻省理工学院）
Landmark correspondences are a widely used type of gold standard in image registration. However, the manual placement of corresponding points is subject to high inter-user variability in the chosen annotated locations and in the interpretation of visual ambiguities. In this paper, we introduce a principled strategy for the construction of a gold standard in deformable registration. Our framework: (i) iteratively suggests the most informative location to annotate next, taking into account its redundancy with previous annotations; (ii) extends traditional pointwise annotations by accounting for …
The University of Tokyo（东京大学）；Simon Fraser University（西蒙弗雷泽大学）；University of Alberta（阿尔伯塔大学）
Probabilistic image registration methods estimate the posterior distribution of transformation. The conventional way of interpreting the transformation posterior is to use the mode as the most likely transformation and assign its corresponding intensity to the registered voxel. Meanwhile, summary statistics of the posterior are employed to evaluate the registration uncertainty, that is the trustworthiness of the registered image. Despite the wide acceptance, this convention has never been justified. In this paper, based on illustrative examples, we question the correctness and usefulness of co…
UNC Chapel Hill（北卡罗来纳大学教堂山分校）；University of Salzburg（萨尔茨堡大学）
We present a method to predict image deformations based on patch-wise image appearance. Specifically, we design a patch-based deep encoder-decoder network which learns the pixel/voxel-wise mapping between image appearance and registration parameters. Our approach can predict general deformation parameterizations, however, we focus on the large deformation diffeomorphic metric mapping (LDDMM) registration model. By predicting the LDDMM momentum-parameterization we retain the desirable theoretical properties of LDDMM, while reducing computation time by orders of magnitude: combined with patch pr…
Cluster of Excellence – ML for Science（卓越集群——科学机器学习）；University of Tübingen（蒂宾根大学）；Faculty of Health Sciences and Medicine, University of Lucerne（卢塞恩大学健康科学与医学院）；University of Lübeck（吕贝克大学）
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）
In order to tackle the difficulty associated with the ill-posed nature of the image registration problem, regularization is often used to constrain the solution space. For most learning-based registration approaches, the regularization usually has a fixed weight and only constrains the spatial transformation. Such convention has two limitations: (i) Besides the laborious grid search for the optimal fixed weight, the regularization strength of a specific image pair should be associated with the content of the images, thus the "one value fits all" training scheme is not ideal; (ii) Only spatiall…
UNC Chapel Hill（北卡罗来纳大学教堂山分校）；University of Salzburg（萨尔茨堡大学）
We introduce a deep encoder-decoder architecture for image deformation prediction from multimodal images. Specifically, we design an image-patch-based deep network that jointly (i) learns an image similarity measure and (ii) the relationship between image patches and deformation parameters. While our method can be applied to general image registration formulations, we focus on the Large Deformation Diffeomorphic Metric Mapping (LDDMM) registration model. By predicting the initial momentum of the shooting formulation of LDDMM, we preserve its mathematical properties and drastically reduce the c…
Robust deformable image registration using cycle-consistent implicit representations
Amsterdam UMC location University of Amsterdam（阿姆斯特丹大学医学中心（阿姆斯特丹大学））；Informatics Institute, University of Amsterdam（阿姆斯特丹大学信息学研究所）；Amsterdam Gastroenterology Endocrinology Metabolism（阿姆斯特丹胃肠病学与内分泌代谢研究所）；Cancer Center Amsterdam（阿姆斯特丹癌症中心）
Technion – Israel Institute of Technology（以色列理工学院）
Unsupervised deep-learning (DL) models were recently proposed for deformable image registration tasks. In such models, a neural-network is trained to predict the best deformation field by minimizing some dissimilarity function between the moving and the target images. After training on a dataset without reference deformation fields available, such a model can be used to rapidly predict the deformation field between newly seen moving and target images. Currently, the training process effectively provides a point-estimate of the network weights rather than characterizing their entire posterior d…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
In this report we present an unsupervised image registration framework, using a pre-trained deep neural network as a feature extractor. We refer this to zero-shot learning, due to nonoverlap between training and testing dataset (none of the network modules in the processing pipeline were trained specifically for the task of medical image registration). Highlights of our technique are: (a) No requirement of a training dataset (b) Keypoints i.e.locations of important features are automatically estimated (c) The number of key points in this model is fixed and can possibly be tuned as a hyperparam…
FAU Erlangen-Nürnberg（埃尔朗根-纽伦堡大学）；Brigham and Women’s Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）；KRH Klinikum Nordstadt（KRH北城医院）；Universität Klinikum Erlangen（埃尔朗根大学医院）
For a wide range of clinical applications, such as adaptive treatment planning or intraoperative image update, feature-based deformable registration (FDR) approaches are widely employed because of their simplicity and low computational complexity. FDR algorithms estimate a dense displacement field by interpolating a sparse field, which is given by the established correspondence between selected features. In this paper, we consider the deformation field as a Gaussian Process (GP), whereas the selected features are regarded as prior information on the valid deformations. Using GP, we are able to…
Brigham and Women’s Hospital, Harvard Medical School（哈佛医学院布莱根妇女医院）；The University of Tokyo（东京大学）；Simon Fraser University（西蒙弗雷泽大学）；University of Alberta（阿尔伯塔大学）；Massachusetts Institute of Technology（麻省理工学院）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
Being a task of establishing spatial correspondences, medical image registration is often formalized as finding the optimal transformation that best aligns two images. Since the transformation is such an essential component of registration, most existing researches conventionally quantify the registration uncertainty, which is the confidence in the estimated spatial correspondences, by the transformation uncertainty. In this paper, we give concrete examples and reveal that using the transformation uncertainty to quantify the registration uncertainty is inappropriate and sometimes misleading. B…
Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；The Hawkes Institute, University College London（霍克斯研究所，伦敦大学学院）；AI Laboratory, Massachusetts Institute of Technology（人工智能实验室，麻省理工学院）
Technion – Israel Institute of Technology（以色列理工学院）
Quantification of uncertainty in deep-neural-networks (DNN) based image registration algorithms plays a critical role in the deployment of image registration algorithms for clinical applications such as surgical planning, intraoperative guidance, and longitudinal monitoring of disease progression or treatment efficacy as well as in research-oriented processing pipelines. Currently available approaches for uncertainty estimation in DNN-based image registration algorithms may result in sub-optimal clinical decision making due to potentially inaccurate estimation of the uncertainty of the registr…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Nanjing University（南京大学）；Hong Kong Polytechnic University（香港理工大学）
High-confidence overlap prediction and accurate correspondences are critical for cutting-edge models to align paired point clouds in a partial-to-partial manner. However, there inherently exists uncertainty between the overlapping and non-overlapping regions, which has always been neglected and significantly affects the registration performance. Beyond the current wisdom, we propose a novel uncertainty-aware overlap prediction network, dubbed UTOPIC, to tackle the ambiguous overlap prediction problem; to our knowledge, this is the first to explicitly introduce overlap uncertainty to point clou…
Continuous sPatial-Temporal Deformable Image Registration (CPT-DIR) for motion modelling in radiotherapy: beyond classic voxel-based methods
Center for Proton Therapy, Paul Scherrer Institut（保罗·施特格研究所质子治疗中心）；Department of Computer Science, ETH Zürich（苏黎世联邦理工学院计算机科学系）；Department of Physics, ETH Zürich（苏黎世联邦理工学院物理系）；Department of Automation, Tsinghua Univeristy（清华大学自动化系）；S-Lab, Nanyang Technological University（南洋理工大学S实验室）
Robust Flower Cluster Matching Using The Unscented Transform
Department of Mechanical, Materials, and Aerospace Engineering, West Virginia University（机械、材料与航空航天工程系，西弗吉尼亚大学）；Lane Department of Computer Science and Electrical Engineering, West Virginia University（计算机科学与电气工程系，西弗吉尼亚大学）
Data-driven registration and modeling of brain deformation for image-guided neurosurgery
LASIGE, Faculty of Sciences, University of Lisbon（里斯本大学科学学院LASIGE）；Department of Neurosurgery and Department of Radiology, Brigham and Women's Hospital, Harvard Medical School（哈佛医学院布里洛妇女医院神经外科与放射科）；Gina Cody School of Engineering and Computer Science, Concordia University（康科迪亚大学工程与计算机科学学院）；Cancer Research UK Cambridge Centre, University of Cambridge（剑桥大学癌症研究英国中心）；Department of Oncology, University of Cambridge（剑桥大学肿瘤科）；Department of Clinical Neurosciences, University of Cambridge（剑桥大学临床神经科学系）；Computational Health Informatics Program (CHIP) and Department of Radiology, Boston Children's Hospital, Harvard Medical School（哈佛医学院波士顿儿童医院计算健康信息学计划与放射科）；Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM（索邦大学巴黎脑研究所-ICM）
Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment
University of Science and Technology of China（中国科学技术大学）；School of Information Science and Technology（信息科学技术学院）；Deep Space Exploration Laboratory（深空探测实验室）
L2M-Reg: Building-level Uncertainty-aware Registration of Outdoor LiDAR Point Clouds and Semantic 3D City Models
Chair of Engineering Geodesy, TUM School of Engineering and Design, Technical University of Munich（工程测量学教授会，技术大学慕尼黑工程与设计学院）；Chair of Geoinformatics, TUM School of Engineering and Design, Technical University of Munich（地理信息学教授会，技术大学慕尼黑工程与设计学院）
Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Aalto University（阿尔托大学）；Copenhagen University Hospital（哥本哈根大学医院）；University College London（伦敦大学学院）；Massachusetts Institute of Technology（麻省理工学院）
In this paper, we unify popular non-rigid registration methods for point sets and surfaces under our general framework, GiNGR. GiNGR builds upon Gaussian Process Morphable Models (GPMM) and hence separates modeling the deformation prior from model adaptation for registration. In addition, it provides explainable hyperparameters, multi-resolution registration, trivial inclusion of expert annotation, and the ability to use and combine analytical and statistical deformation priors. But more importantly, the reformulation allows for a direct comparison of registration methods. Instead of using a g…
University of Sydney（悉尼大学）；Brigham and Women’s Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）
White matter (WM) tract segmentation based on diffusion magnetic resonance imaging (dMRI) plays an important role in the analysis of human health and brain diseases. However, the annotation of WM tracts is time-consuming and needs experienced neuroanatomists. In this study, to explore tract segmentation in the challenging setting of minimal annotations, we propose a novel framework utilizing only one annotated subject (subject-level one-shot) for tract segmentation. Our method is constructed by proposed registration-based peak augmentation (RPA) and uncertainty-based refining (URe) modules. RP…
Uncertainty-Aware Cortical Surface Reconstruction and Spherical Registration for Heterogeneous Brain MRI
Danish Research Centre for Magnetic Resonance, Department of Radiology and Nuclear Medicine, Copenhagen University Hospital – Amager and Hvidovre（丹麦磁共振研究中心，放射科与核医学科，哥本哈根大学医院-阿马格和维多弗）；Department of Health Technology, Technical University of Denmark（技术丹麦大学健康技术系）；Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital（阿蒂努拉·A·马丁诺斯生物医学成像中心，麻省总医院）；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）；Department of Radiology, Harvard Medical School（哈佛医学院放射学系）；Hawkes Institute, University College London（霍克斯研究所，伦敦大学学院）
RWTH Aachen University（亚琛工业大学）；University of South Carolina（南卡罗来纳大学）
The extraordinary improvements of modern imaging devices offer access to data with unprecedented information content. However, widely used image processing methodologies fall far short of exploiting the full breadth of information offered by numerous types of scanning probe, optical, and electron microscopies. In many applications, it is necessary to keep measurement intensities below a desired threshold. We propose a methodology for extracting an increased level of information by processing a series of data sets suffering, in particular, from high degree of spatial uncertainty caused by compl…
University College London（伦敦大学学院）；Harvard Medical School（哈佛医学院）；Massachusetts General Hospital（麻省总医院）；Allen Institute for Brain Science（艾伦脑科学研究所）；Massachusetts Institute of Technology（麻省理工学院）
Nonlinear registration of 2D histological sections with corresponding slices of MRI data is a critical step of 3D histology reconstruction. This task is difficult due to the large differences in image contrast and resolution, as well as the complex nonrigid distortions produced when sectioning the sample and mounting it on the glass slide. It has been shown in brain MRI registration that better spatial alignment across modalities can be obtained by synthesizing one modality from the other and then using intra-modality registration metrics, rather than by using mutual information (MI) as metric…
The random walker (RW) algorithm is used for both image segmentation and registration, and possesses several useful properties that make it popular in medical imaging, such as being globally optimizable, allowing user interaction, and providing uncertainty information. The RW algorithm defines a weighted graph over an image and uses the graph's Laplacian matrix to regularize its solutions. This regularization reduces to solving a large system of equations, which may be excessively time consuming in some applications, such as when interacting with a human user. Techniques have been developed th…
Classical deformable registration techniques achieve impressive results and offer a rigorous theoretical treatment, but are computationally intensive since they solve an optimization problem for each image pair. Recently, learning-based methods have facilitated fast registration by learning spatial deformation functions. However, these approaches use restricted deformation models, require supervised labels, or do not guarantee a diffeomorphic (topology-preserving) registration. Furthermore, learning-based registration tools have not been derived from a probabilistic framework that can offer un…
German Cancer Research Center（德国癌症研究中心）；Heidelberg University（海德堡大学）
Image registration is the basis for many applications in the fields of medical image computing and computer assisted interventions. One example is the registration of 2D X-ray images with preoperative three-dimensional computed tomography (CT) images in intraoperative surgical guidance systems. Due to the high safety requirements in medical applications, estimating registration uncertainty is of a crucial importance in such a scenario. However, previously proposed methods, including classical iterative registration methods and deep learning-based methods have one characteristic in common: They…
Johns Hopkins Medical Institutes（约翰·霍普金斯医学院）；Johns Hopkins University（约翰·霍普金斯大学）；NVIDIA Corporation（英伟达公司）；Duke University Medical Center（杜克大学医学中心）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
In the last decade, convolutional neural networks (ConvNets) have been a major focus of research in medical image analysis. However, the performances of ConvNets may be limited by a lack of explicit consideration of the long-range spatial relationships in an image. Recently Vision Transformer architectures have been proposed to address the shortcomings of ConvNets and have produced state-of-the-art performances in many medical imaging applications. Transformers may be a strong candidate for image registration because their substantially larger receptive field enables a more precise comprehensi…
Registration is a fundamental task in medical image analysis which can be applied to several tasks including image segmentation, intra-operative tracking, multi-modal image alignment, and motion analysis. Popular registration tools such as ANTs and NiftyReg optimize an objective function for each pair of images from scratch which is time-consuming for large images with complicated deformation. Facilitated by the rapid progress of deep learning, learning-based approaches such as VoxelMorph have been emerging for image registration. These approaches can achieve competitive performance in a fract…
The University of Tokyo（东京大学）；Computer Science and Artificial Intelligence Laboratory, MIT（麻省理工学院计算机科学与人工智能实验室）；Brigham and Women’s Hospital, Harvard Medical School（哈佛医学院布莱根妇女医院）；Ecole de Technologie Superieure（高等技术学院）；Lehigh University（里海大学）；RIKEN（理化学研究所）
A reliable Ultrasound (US)-to-US registration method to compensate for brain shift would substantially improve Image-Guided Neurological Surgery. Developing such a registration method is very challenging, due to factors such as missing correspondence in images, the complexity of brain pathology and the demand for fast computation. We propose a novel feature-driven active framework. Here, landmarks and their displacement are first estimated from a pair of US images using corresponding local image features. Subsequently, a Gaussian Process (GP) model is used to interpolate a dense deformation fi…
Purpose: The purpose of this paper is to present a method for real-time 2D-3D non-rigid registration using a single fluoroscopic image. Such a method can find applications in surgery, interventional radiology and radiotherapy. By estimating a three-dimensional displacement field from a 2D X-ray image, anatomical structures segmented in the preoperative scan can be projected onto the 2D image, thus providing a mixed reality view. Methods: A dataset composed of displacement fields and 2D projections of the anatomy is generated from the preoperative scan. From this dataset, a neural network is tr…
Statistical shape modeling (SSM) has recently taken advantage of advances in deep learning to alleviate the need for a time-consuming and expert-driven workflow of anatomy segmentation, shape registration, and the optimization of population-level shape representations. DeepSSM is an end-to-end deep learning approach that extracts statistical shape representation directly from unsegmented images with little manual overhead. It performs comparably with state-of-the-art shape modeling methods for estimating morphologies that are viable for subsequent downstream tasks. Nonetheless, DeepSSM produce…
