Deformable Medical Image Registration: A Survey

By Aristeidis Sotiras, Christos Davatzikos, Nikos Paragios. 2013

1,642 citations recorded by the source corpus.

Deformable image registration is a fundamental task in medical image processing. Among its most important applications, one may cite: 1) multi-modality fusion, where information acquired by different imaging devices or protocols is fused to facilitate diagnosis and treatment planning; 2) longitudinal studies, where temporal structural or anatomical changes are investigated; and 3) population modeling and statistical atlases used to study normal anatomical variability. In this paper, we attempt to give an overview of deformable registration methods, putting emphasis on the most recent advances in the domain. Additional emphasis has been given to techniques applied to medical images. In order to study image registration methods in depth, their main components are identified and studied independently. The most recent techniques are presented in a systematic fashion. The contribution of this paper is to provide an extensive account of registration techniques in a systematic manner.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

An overview of deep learning in medical imaging focusing on MRI (2018, methodology): “on correction, real-time MR physics is also an important part of the picture [224, 225]. A wide range of methodological approaches have been developed and tested for various organs and applications40 [229, 230, 231, 232, 233, 234, 235, 236, 237, 238], including \previous generation" articial ne”
A deep learning framework for unsupervised affine and deformable image registration (2018, methodology): “Commonly used image registration approaches include intensity-based methods, and featurebased methods that use handcrafted image features (Sotiras et al., 2013; Viergever et al., 2016).”
Partial Policy-Based Reinforcement Learning for Anatomical Landmark Localization in 3D Medical Images (2018, background): “LANDMARK localization plays a vital role in medical image analysis, facilitating the automatic process for registration, classification, and segmentation [1], [2].”
A survey of medical image registration - under review (2016, neutral): “There is a multitude of publications on nonlinear registration, witness the > 400 references on such methods in the survey article of Sotiras et al. (2013) .”
Optical flow modeling and computation: A survey (2015, background): “Complex nonlinear and physi-cal-based models can be exploited to model deformations for image registration [224].”
Deep Learning-based Image Segmentation on Multimodal Medical Imaging (2019, methodology): “Yet we also note that there exist unsupervised methods in medical image analysis such as gradient flow-based methods for image segmentation [47], as well as well-established deformable image registration algorithms [48].”
MSM: a new flexible framework for Multimodal Surface Matching☆ (2014, neutral): “Optimisation Optimisation of the cost function can take many forms (see overview in (Sotiras et al., 2013)) including combinatorial (Boykov et al.”
Real-time Deep Pose Estimation with Geodesic Loss for Image-to-Template Rigid Registration (2018, background): “The most widely used transformations in biomedical image registration range from rigid and affine to high-dimensional small or large deformations based on biophysical/biomechanical, elastic, or viscous fluid models [6].”
Deep Learning in Medical Image Analysis (2017, background): “Noticeably, it is very difficult to learn meaningful features given such inaccurate correspondences derived from imperfect image registration, as suffered by many supervised learning methods (79, 80, 81).”
Survey of Non-Rigid Registration Tools in Medicine (2017, methodology): “registration methods [18] classifying methods on the basis of the core registration components: (i) deformation models, (ii) matching criteria, and (iii) optimization.”
MUSE: MUlti-atlas region Segmentation utilizing Ensembles of registration algorithms and parameters, and locally optimal atlas selection (2015, neutral): “, 2013), deformable image registration (Sotiras et al., 2013) is a core component of allMASmethods, and the quality of individual registrations has a very high impact on the accuracy of the final segmentation.”
VoxelMorph: A Learning Framework for Deformable Medical Image Registration (2018, neutral): “Most existing deformable registration algorithms iteratively optimize a transformation based on an energy function [7].”
Slice-to-volume medical image registration: a survey (2017, methodology): “We propose a taxonomy based on previous surveys on image registration (Markelj et al., 2010; Sotiras et al., 2013) and adapted to the particular slice-to-volume case (see Figure 1).”
Multi-Atlas Segmentation of Biomedical Images: A Survey (2014, background): “There are a wide range of registration algorithms, which employ diﬀerent objective functions, deformation models, and optimization strategies (Sotiras et al., 2013).”
Image Matching from Handcrafted to Deep Features: A Survey (2020, background): “Please refer to Zitova and Flusser (2003), Dawn et al. (2010), Sotiras et al. (2013) and Ferrante and Paragios (2017) for representative literature and further details.”
Quicksilver: Fast Predictive Image Registration – a Deep Learning Approach (2017, background): “x). Here, ddenotes the spatial dimension and xis the spatial coordinate of the xed target image T.Due to the importance of image registration, a large number of dierent approaches have been proposed [1,37,38,39]. Typically, these approaches are formulated as optimization problems, where one seeks to”
A review of multimodal image matching: Methods and applications (2021, methodology): “However, the MI experiences difficulty in determining the global maximum of the entire searching space, inevitably reducing its robustness [29].”