Deformable medical image registration: a survey

Image synthesis-based multi-modal image registration framework by using deep fully convolutional networks

Multi-modal image registration has significant meanings in clinical diagnosis, treatment planning, and image-guided surgery. Since different modalities exhibit different characteristics, finding a fast and accurate correspondence between images of different modalities is still a challenge. In this paper, we propose an image synthesis-based multi-modal registration framework. Image synthesis is performed by a ten-layer fully convolutional network (FCN). The network is composed of 10 convolutional layers combined with batch normalization (BN) and rectified linear unit (ReLU), which can be trained to learn an end-to-end mapping from one modality to the other. After the cross-modality image synthesis, multi-modal registration can be transformed into mono-modal registration. The mono-modal registration can be solved by methods with lower computational complexity, such as sum of squared differences (SSD). We tested our method in T1-weighted vs T2-weighted, T1-weighted vs PD, and T2-weighted vs PD image registrations with BrainWeb phantom data and IXI real patients' data. The result shows that our framework can achieve higher registration accuracy than the state-of-the-art multi-modal image registration methods, such as local mutual information (LMI) and α-mutual information (α-MI). The average registration errors of our method in experiment with IXI real patients' data were 1.19, 2.23, and 1.57 compared to 1.53, 2.60, and 2.36 of LMI and 1.34, 2.39, and 1.76 of α-MI in T2-weighted vs PD, T1-weighted vs PD, and T1-weighted vs T2-weighted image registration, respectively. In this paper, we propose an image synthesis-based multi-modal image registration framework. A deep FCN model is developed to perform image synthesis for this framework, which can capture the complex nonlinear relationship between different modalities and discover complex structural representations automatically by a large number of trainable mapping and parameters and perform accurate image synthesis. The framework combined with the deep FCN model and mono-modal registration methods (SSD) can achieve fast and robust results in multi-modal medical image registration. Graphical abstract The workflow of proposed multi-modal image registration framework.

The evaluation of a hybrid biomechanical deformable registration method on a multistage physical phantom with reproducible deformation

BACKGROUND

Advanced clinical applications, such as dose accumulation and adaptive radiation therapy, require deformable image registration (DIR) algorithms capable of voxel-wise accurate mapping of treatment dose or functional imaging. By utilizing a multistage deformable phantom, the authors investigated scenarios where biomechanical refinement method (BM-DIR) may be better than the pure image intensity based deformable registration (IM-DIR).

METHODS

The authors developed a biomechanical-model based DIR refinement method (BM-DIR) to refine the deformable vector field (DVF) from any initial intensity-based DIR (IM-DIR). The BM-DIR method was quantitatively evaluated on a novel phantom capable of ten reproducible gradually-increasing deformation stages using the urethra tube as a surrogate. The internal DIR accuracy was inspected in term of the Dice similarity coefficient (DSC), Hausdorff and mean surface distance as defined in of the urethra structure inside the phantom and compared with that of the initial IM-DIR under various stages of deformation. Voxel-wise deformation vector discrepancy and Jacobian regularity were also inspected to evaluate the output DVFs. In addition to phantom, two pairs of Head&Neck patient MR images with expert-defined landmarks inside parotids were utilized to evaluate the BM-DIR accuracy with target registration error (TRE).

RESULTS

The DSC and surface distance measures of the inner urethra tube indicated the BM-DIR method can improve the internal DVF accuracy on masked MR images for the phases of a large degree of deformation. The smoother Jacobian distribution from the BM-DIR suggests more physically-plausible internal deformation. For H&N cancer patients, the BM-DIR improved the TRE from 0.339 cm to 0.210 cm for the landmarks inside parotid on the masked MR images.

CONCLUSIONS

We have quantitatively demonstrated on a multi-stage physical phantom and limited patient data that the proposed BM-DIR can improve the accuracy inside solid organs with large deformation where distinctive image features are absent.

Automatic Multiorgan Segmentation via Multiscale Registration and Graph Cut

We propose an automatic multiorgan segmentation method for 3-D radiological images of different anatomical contents and modalities. The approach is based on a simultaneous multilabel graph cut optimization of location, appearance, and spatial configuration criteria of target structures. Organ location is defined by target-specific probabilistic atlases (PA) constructed from a training dataset using a fast (2+1)D SURF-based multiscale registration method involving a simple four-parameter transformation. PAs are also used to derive target-specific organ appearance models represented as intensity histograms. The spatial configuration prior is derived from shortest-path constraints defined on the adjacency graph of structures. Thorough evaluations on Visceral project benchmarks and training dataset, as well as comparisons with the state-of-the-art confirm that our approach is comparable to and often outperforms similar approaches in multiorgan segmentation, thus proving that the combination of multiple suboptimal but complementary information sources can yield very good performance.

ESTIMATING DIFFEOMORPHIC MAPPINGS BETWEEN TEMPLATES AND NOISY DATA: VARIANCE BOUNDS ON THE ESTIMATED CANONICAL VOLUME FORM

Anatomy is undergoing a renaissance driven by the availability of large digital data sets generated by light microscopy. A central computational task is to map individual data volumes to standardized templates. This is accomplished by regularized estimation of a diffeomorphic transformation between the coordinate systems of the individual data and the template, building the transformation incrementally by integrating a smooth flow field. The canonical volume form of this transformation is used to quantify local growth, atrophy, or cell density. While multiple implementations exist for this estimation, less attention has been paid to the variance of the estimated diffeomorphism for noisy data. Notably, there is an infinite dimensional unobservable space defined by those diffeomorphisms which leave the template invariant. These form the stabilizer subgroup of the diffeomorphic group acting on the template. The corresponding flat directions in the energy landscape are expected to lead to increased estimation variance. Here we show that a least-action principle used to generate geodesics in the space of diffeomor-phisms connecting the subject brain to the template removes the stabilizer. This provides reduced-variance estimates of the volume form. Using simulations we demonstrate that the asymmetric large deformation diffeomorphic mapping methods (LDDMM), which explicitly incorporate the asymmetry between idealized template images and noisy empirical images, provide lower variance estimators than their symmetrized counterparts (cf. ANTs). We derive Cramer-Rao bounds for the variances in the limit of small deformations. Analytical results are shown for the Jacobian in terms of perturbations of the vector fields and divergence of the vector field.

Discontinuity Preserving Liver MR Registration with 3D Active Contour Motion Segmentation

OBJECTIVE

The sliding motion of the liver during respiration violates the homogeneous motion smoothness assumption in conventional non-rigid image registration and commonly results in compromised registration accuracy. This paper presents a novel approach, registration with 3D active contour motion segmentation (RAMS), to improve registration accuracy with discontinuity-aware motion regularization.

METHODS

A Markov random field-based discrete optimization with dense displacement sampling and self-similarity context metric is used for registration, while a graph cuts-based 3D active contour approach is applied to segment the sliding interface. In the first registration pass, a mask-free L1 regularization on an image-derived minimum spanning tree is performed to allow motion discontinuity. Based on the motion field estimates, a coarse segmentation finds the motion boundaries. Next, based on MR signal intensity, a fine segmentation aligns the motion boundaries with anatomical boundaries. In the second registration pass, smoothness constraints across the segmented sliding interface are removed by masked regularization on a minimum spanning forest and masked interpolation of the motion field.

RESULTS

For in vivo breath-hold abdominal MRI data, the motion masks calculated by RAMS are highly consistent with manual segmentations in terms of Dice similarity and bidirectional local distance measure. These automatically obtained masks are shown to substantially improve registration accuracy for both the proposed discrete registration as well as conventional continuous non-rigid algorithms.

CONCLUSION/SIGNIFICANCE

The presented results demonstrated the feasibility of automated segmentation of the respiratory sliding motion interface in liver MR images and the effectiveness of using the derived motion masks to preserve motion discontinuity.

Performance of a feature-based algorithm for 3D-3D registration of CT angiography to cone-beam CT for endovascular repair of complex abdominal aortic aneurysms

BACKGROUND

A crucial step in image fusion for intraoperative guidance during endovascular procedures is the registration of preoperative computed tomography angiography (CTA) with intraoperative Cone Beam CT (CBCT). Automatic tools for image registration facilitate the 3D image guidance workflow. However their performance is not always satisfactory. The aim of this study is to assess the accuracy of a new fully automatic, feature-based algorithm for 3D3D registration of CTA to CBCT.

METHODS

The feature-based algorithm was tested on clinical image datasets from 14 patients undergoing complex endovascular aortic repair. Deviations in Euclidian distances between vascular as well as bony landmarks were measured and compared to an intensity-based, normalized mutual information algorithm.

RESULTS

The results for the feature-based algorithm showed that the median 3D registration error between the anatomical landmarks of CBCT and CT images was less than 3 mm. The feature-based algorithm showed significantly better accuracy compared to the intensity-based algorithm (p < 0.001).

CONCLUSION

A feature-based algorithm for 3D image registration is presented.

MITT: Medical Image Tracking Toolbox

Over the years, medical image tracking has gained considerable attention from both medical and research communities due to its widespread utility in a multitude of clinical applications, from functional assessment during diagnosis and therapy planning to structure tracking or image fusion during image-guided interventions. Despite the ever-increasing number of image tracking methods available, most still consist of independent implementations with specific target applications, lacking the versatility to deal with distinct end-goals without the need for methodological tailoring and/or exhaustive tuning of numerous parameters. With this in mind, we have developed the medical image tracking toolbox (MITT)-a software package designed to ease customization of image tracking solutions in the medical field. While its workflow principles make it suitable to work with 2-D or 3-D image sequences, its modules offer versatility to set up computationally efficient tracking solutions, even for users with limited programming skills. MITT is implemented in both C/C++ and MATLAB, including several variants of an object-based image tracking algorithm and allowing to track multiple types of objects (i.e., contours, multi-contours, surfaces, and multi-surfaces) with several customization features. In this paper, the toolbox is presented, its features discussed, and illustrative examples of its usage in the cardiology field provided, demonstrating its versatility, simplicity, and time efficiency.

A momentum-based diffeomorphic demons framework for deformable MR-CT image registration

Neuro-navigated procedures require a high degree of geometric accuracy but are subject to geometric error from complex deformation in the deep brain-e.g. regions about the ventricles due to egress of cerebrospinal fluid (CSF) upon neuroendoscopic approach or placement of a ventricular shunt. We report a multi-modality, diffeomorphic, deformable registration method using momentum-based acceleration of the Demons algorithm to solve the transformation relating preoperative MRI and intraoperative CT as a basis for high-precision guidance. The registration method (pMI-Demons) extends the mono-modality, diffeomorphic form of the Demons algorithm to multi-modality registration using pointwise mutual information (pMI) as a similarity metric. The method incorporates a preprocessing step to nonlinearly stretch CT image values and incorporates a momentum-based approach to accelerate convergence. Registration performance was evaluated in phantom and patient images: first, the sensitivity of performance to algorithm parameter selection (including update and displacement field smoothing, histogram stretch, and the momentum term) was analyzed in a phantom study over a range of simulated deformations; and second, the algorithm was applied to registration of MR and CT images for four patients undergoing minimally invasive neurosurgery. Performance was compared to two previously reported methods (free-form deformation using mutual information (MI-FFD) and symmetric normalization using mutual information (MI-SyN)) in terms of target registration error (TRE), Jacobian determinant (J), and runtime. The phantom study identified optimal or nominal settings of algorithm parameters for translation to clinical studies. In the phantom study, the pMI-Demons method achieved comparable registration accuracy to the reference methods and strongly reduced outliers in TRE (p [Formula: see text] 0.001 in Kolmogorov-Smirnov test). Similarly, in the clinical study: median TRE  =  1.54 mm (0.83-1.66 mm interquartile range, IQR) for pMI-Demons compared to 1.40 mm (1.02-1.67 mm IQR) for MI-FFD and 1.64 mm (0.90-1.92 mm IQR) for MI-SyN. The pMI-Demons and MI-SyN methods yielded diffeomorphic transformations (J  >  0) that preserved topology, whereas MI-FFD yielded unrealistic (J  <  0) deformations subject to tissue folding and tearing. Momentum-based acceleration gave a ~35% speedup of the pMI-Demons method, providing registration runtime of 10.5 min (reduced to 2.2 min on GPU), compared to 15.5 min for MI-FFD and 34.7 min for MI-SyN. The pMI-Demons method achieved registration accuracy comparable to MI-FFD and MI-SyN, maintained diffeomorphic transformation similar to MI-SyN, and accelerated runtime in a manner that facilitates translation to image-guided neurosurgery.

Review of 2-D/3-D Reconstruction Using Statistical Shape and Intensity Models and X-Ray Image Synthesis: Toward a Unified Framework

Patient-specific three-dimensional (3-D) bone models are useful for a number of clinical applications such as surgery planning, postoperative evaluation, as well as implant and prosthesis design. Two-dimensional-to-3-D (2-D/3-D) reconstruction, also known as model-to-modality or atlas-based 2-D/3-D registration, provides a means of obtaining a 3-D model of a patient's bones from their 2-D radiographs when 3-D imaging modalities are not available. The preferred approach for estimating both shape and density information (that would be present in a patient's computed tomography data) for 2-D/3-D reconstruction makes use of digitally reconstructed radiographs and deformable models in an iterative, non-rigid, intensity-based approach. Based on a large number of state-of-the-art 2-D/3-D bone reconstruction methods, a unified mathematical formulation of the problem is proposed in a common conceptual framework, using unambiguous terminology. In addition, shortcomings, recent adaptations, and persisting challenges are discussed along with insights for future research.

3-D Measurements of Acceleration-Induced Brain Deformation via Harmonic Phase Analysis and Finite-Element Models

OBJECTIVE

To obtain dense spatiotemporal measurements of brain deformation from two distinct but complementary head motion experiments: linear and rotational accelerations.

METHODS

This study introduces a strategy for integrating harmonic phase analysis of tagged magnetic resonance imaging (MRI) and finite-element models to extract mechanically representative deformation measurements. The method was calibrated using simulated as well as experimental data, demonstrated in a phantom including data with image artifacts, and used to measure brain deformation in human volunteers undergoing rotational and linear acceleration.

RESULTS

Evaluation methods yielded a displacement error of 1.1 mm compared to human observers and strain errors between [Formula: see text] for linear acceleration and [Formula: see text] for rotational acceleration. This study also demonstrates an approach that can reduce error by 86% in the presence of corrupted data. Analysis of results shows consistency with 2-D motion estimation, agreement with external sensors, and the expected physical behavior of the brain.

CONCLUSION

Mechanical regularization is useful for obtaining dense spatiotemporal measurements of in vivo brain deformation under different loading regimes.

SIGNIFICANCE

The measurements suggest that the brain's 3-D response to mild accelerations includes distinct patterns observable using practical MRI resolutions. This type of measurement can provide validation data for computer models for the study of traumatic brain injury.

Spatially Consistent Supervoxel Correspondences of Cone-Beam Computed Tomography Images

Establishing dense correspondences of cone-beam computed tomography (CBCT) images is a crucial step for the attribute transfer and morphological variation assessment in clinical orthodontics. In this paper, a novel method, unsupervised spatially consistent clustering forest, is proposed to tackle the challenges for automatic supervoxel-wise correspondences of CBCT images. A complexity analysis of the proposed method with respect to the clustering hypotheses is provided with a data-dependent learning guarantee. The learning bound considers both the sequential tree traversals determined by questions stored in branch nodes and the clustering compactness of leaf nodes. A novel tree-pruning algorithm, guided by the learning bound, is also proposed to remove locally inconsistent leaf nodes. The resulting forest yields spatially consistent affinity estimations, thanks to the pruning penalizing trees with inconsistent leaf assignments and the combinational contextual feature channels used to learn the forest. A forest-based metric is utilized to derive the pairwise affinities and dense correspondences of CBCT images. The proposed method has been applied to the label propagation of clinically captured CBCT images. In the experiments, the method outperforms variants of both supervised and unsupervised forest-based methods and state-of-the-art label-propagation methods, achieving the mean dice similarity coefficients of 0.92, 0.89, 0.94, and 0.93 for the mandible, the maxilla, the zygoma arch, and the teeth data, respectively.

Deformable Image Registration Using a Cue-Aware Deep Regression Network

SIGNIFICANCE

Analysis of modern large-scale, multicenter or diseased data requires deformable registration algorithms that can cope with data of diverse nature.

OBJECTIVE

We propose a novel deformable registration method, which is based on a cue-aware deep regression network, to deal with multiple databases with minimal parameter tuning.

METHODS

Our method learns and predicts the deformation field between a reference image and a subject image. Specifically, given a set of training images, our method learns the displacement vector associated with a pair of reference-subject patches. To achieve this, we first introduce a key-point truncated-balanced sampling strategy to facilitate accurate learning from the image database of limited size. Then, we design a cue-aware deep regression network, where we propose to employ the contextual cue, i.e., the scale-adaptive local similarity, to more apparently guide the learning process. The deep regression network is aware of the contextual cue for accurate prediction of local deformation.

RESULTS AND CONCLUSION

Our experiments show that the proposed method can tackle various registration tasks on different databases, giving consistent good performance without the need of manual parameter tuning, which could be applicable to various clinical applications.

Hierarchical Sparse Representation for Robust Image Registration

Similarity measure is an essential component in image registration. In this article, we propose a novel similarity measure for registration of two or more images. The proposed method is motivated by the fact that optimally registered images can be sparsified hierarchically in the gradient domain and frequency domain with the separation of sparse errors. One of the key advantages of the proposed similarity measure is its robustness in dealing with severe intensity distortions, which widely exist on medical images, remotely sensed images and natural photos due to differences of acquisition modalities or illumination conditions. Two efficient algorithms are proposed to solve the batch image registration and pair registration problems in a unified framework. We have validated our method on extensive and challenging data sets. The experimental results demonstrate the robustness, accuracy and efficiency of our method over nine traditional and state-of-the-art algorithms on synthetic images and a wide range of real-world applications.

Equilibrated warping: Finite element image registration with finite strain equilibrium gap regularization

In this paper, we propose a novel continuum finite strain formulation of the equilibrium gap regularization for image registration. The equilibrium gap regularization essentially penalizes any deviation from the solution of a hyperelastic body in equilibrium with arbitrary loads prescribed at the boundary. It thus represents a regularization with strong mechanical basis, especially suited for cardiac image analysis. We describe the consistent linearization and discretization of the regularized image registration problem, in the framework of the finite elements method. The method is implemented using FEniCS & VTK, and distributed as a freely available python library. We show that the equilibrated warping method is effective and robust: regularization strength and image noise have minimal impact on motion tracking, especially when compared to strain-based regularization methods such as hyperelastic warping. We also show that equilibrated warping is able to extract main deformation features on both tagged and untagged cardiac magnetic resonance images.

Automatic hyoid bone detection in fluoroscopic images using deep learning

The displacement of the hyoid bone is one of the key components evaluated in the swallow study, as its motion during swallowing is related to overall swallowing integrity. In daily research settings, experts visually detect the hyoid bone in the video frames and manually plot hyoid bone position frame by frame. This study aims to develop an automatic method to localize the location of the hyoid bone in the video sequence. To automatically detect the location of the hyoid bone in a frame, we proposed a single shot multibox detector, a deep convolutional neural network, which is employed to detect and classify the location of the hyoid bone. We also evaluated the performance of two other state-of-art detection methods for comparison. The experimental results clearly showed that the single shot multibox detector can detect the hyoid bone with an average precision of 89.14% and outperform other auto-detection algorithms. We conclude that this automatic hyoid bone tracking system is accurate enough to be widely applied as a pre-processing step for image processing in dysphagia research, as well as a promising development that may be useful in the diagnosis of dysphagia.

Gaussian Process Morphable Models

Models of shape variations have become a central component for the automated analysis of images. An important class of shape models are point distribution models (PDMs). These models represent a class of shapes as a normal distribution of point variations, whose parameters are estimated from example shapes. Principal component analysis (PCA) is applied to obtain a low-dimensional representation of the shape variation in terms of the leading principal components. In this paper, we propose a generalization of PDMs, which we refer to as Gaussian Process Morphable Models (GPMMs). We model the shape variations with a Gaussian process, which we represent using the leading components of its Karhunen-Loève expansion. To compute the expansion, we make use of an approximation scheme based on the Nyström method. The resulting model can be seen as a continuous analog of a standard PDM. However, while for PDMs the shape variation is restricted to the linear span of the example data, with GPMMs we can define the shape variation using any Gaussian process. For example, we can build shape models that correspond to classical spline models and thus do not require any example data. Furthermore, Gaussian processes make it possible to combine different models. For example, a PDM can be extended with a spline model, to obtain a model that incorporates learned shape characteristics but is flexible enough to explain shapes that cannot be represented by the PDM. We introduce a simple algorithm for fitting a GPMM to a surface or image. This results in a non-rigid registration approach whose regularization properties are defined by a GPMM. We show how we can obtain different registration schemes, including methods for multi-scale or hybrid registration, by constructing an appropriate GPMM. As our approach strictly separates modeling from the fitting process, this is all achieved without changes to the fitting algorithm. To demonstrate the applicability and versatility of GPMMs, we perform a set of experiments in typical usage scenarios in medical image analysis and computer vision: The model-based segmentation of 3D forearm images and the building of a statistical model of the face. To complement the paper, we have made all our methods available as open source.

Anatomically plausible models and quality assurance criteria for online mono- and multi-modal medical image registration

Medical imaging is currently employed in the diagnosis, planning, delivery and response monitoring of cancer treatments. Due to physiological motion and/or treatment response, the shape and location of the pathology and organs-at-risk may change over time. Establishing their location within the acquired images is therefore paramount for an accurate treatment delivery and monitoring. A feasible solution for tracking anatomical changes during an image-guided cancer treatment is provided by image registration algorithms. Such methods are, however, often built upon elements originating from the computer vision/graphics domain. Since the original design of such elements did not take into consideration the material properties of particular biological tissues, the anatomical plausibility of the estimated deformations may not be guaranteed. In the current work we adapt two existing variational registration algorithms, namely Horn-Schunck and EVolution, to online soft tissue tracking. This is achieved by enforcing an incompressibility constraint on the estimated deformations during the registration process. The existing and the modified registration methods were comparatively tested against several quality assurance criteria on abdominal in vivo MR and CT data. These criteria included: the Dice similarity coefficient (DSC), the Jaccard index, the target registration error (TRE) and three additional criteria evaluating the anatomical plausibility of the estimated deformations. Results demonstrated that both the original and the modified registration methods have similar registration capabilities in high-contrast areas, with DSC and Jaccard index values predominantly in the 0.8-0.9 range and an average TRE of 1.6-2.0 mm. In contrast-devoid regions of the liver and kidneys, however, the three additional quality assurance criteria have indicated a considerable improvement of the anatomical plausibility of the deformations estimated by the incompressibility-constrained methods. Moreover, the proposed registration models maintain the potential of the original methods for online image-based guidance of cancer treatments.

Kidney Detection in 3-D Ultrasound Imagery via Shape-to-Volume Registration Based on Spatially Aligned Neural Network

This paper introduces a computer-aided kidney shape detection method suitable for volumetric (3D) ultrasound images. Using shape and texture priors, the proposed method automates the process of kidney detection, which is a problem of great importance in computer-assisted trauma diagnosis. This paper introduces a new complex-valued implicit shape model, which represents the multiregional structure of the kidney shape. A spatially aligned neural network classifiers with complex-valued output is designed to classify voxels into background and multiregional structure of the kidney shape. The complex values of the shape model and classification outputs are selected and incorporated in a new similarity metric, such as the shape-to-volume registration process only fits the shape model on the actual kidney shape in input ultrasound volumes. The algorithm's accuracy and sensitivity are evaluated using both simulated and actual 3-D ultrasound images, and it is compared against the performance of the state of the art. The results support the claims about accuracy and robustness of the proposed kidney detection method, and statistical analysis validates its superiority over the state of the art.

Band-Limited Stokes Large Deformation Diffeomorphic Metric Mapping

The class of registration methods proposed in the framework of Stokes large deformation diffeomorphic metric mapping (LDDMM) is a particularly interesting family of physically meaningful diffeomorphic registration methods. Stokes-LDDMM methods are formulated as constrained variational problems, where the different physical models are imposed using the associated partial differential equations as hard constraints. The most significant limitation of Stokes-LDDMM framework is its huge computational complexity. The objective of this paper is to promote the use of Stokes-LDDMM in computational anatomy applications with an efficient approximation of the original variational problem. Thus, we propose a novel method for efficient Stokes-LDDMM diffeomorphic registration. Our method poses the constrained variational problem in the space of band-limited vector fields and it is implemented in the GPU. The performance of band-limited Stokes-LDDMM has been compared and evaluated with original Stokes-LDDMM, EPDiff-LDDMM, and band-limited EPDiff-LDDMM. The evaluation has been conducted in 3-D with the nonrigid image registration evaluation project database. Since the update equation in Stokes-LDDMM involves the action of low-pass filters, the computational complexity has been greatly alleviated with a modest accuracy lose. We have obtained a competitive performance for some method configurations. Overall, our proposed method may make feasible the extensive use of novel physically meaningful Stokes-LDDMM methods in different computational anatomy applications. In addition, our results reinforce the usefulness of band-limited vector fields in diffeomorphic registration methods involving the action of low-pass filters in the optimization, even in algorithmically challenging environments such as Stokes-LDDMM.

Cardiac Motion Correction for Helical CT Scan With an Ordinary Pitch

Cardiac X-ray computed tomography (CT) imaging is still challenging due to the cardiac motion during CT scanning, which leads to the presence of motion artifacts in the reconstructed image. In response, many cardiac X-ray CT imaging algorithms have been proposed, based on motion estimation (ME) and motion compensation (MC), to improve the image quality by alleviating the motion artifacts in the reconstructed image. However, these ME/MC algorithms are mainly based on an axial scan or a low-pitch helical scan. In this paper, we propose a ME/MC-based cardiac imaging algorithm for the data set acquired from a helical scan with an ordinary pitch of around 1.0 so as to obtain the whole cardiac image within a single scan of short time without ECG gating. In the proposed algorithm, a sequence of partial angle reconstructed (PAR) images is generated by using consecutive parts of the sinogram, each of which has a small angular span. Subsequently, an initial 4-D motion vector field (MVF) is obtained using multiple pairs of conjugate PAR images. The 4-D MVF is then refined based on an image quality metric so as to improve the quality of the motion-compensated image. Finally, a time-resolved cardiac image is obtained by performing motion-compensated image reconstruction by using the refined 4-D MVF. Using digital XCAT phantom data sets and a human data set commonly obtained via a helical scan with a pitch of 1.0, we demonstrate that the proposed algorithm significantly improves the image quality by alleviating motion artifacts.

Cardiac contraction motion compensation in gated myocardial perfusion SPECT: A comparative study

INTRODUCTION

Cardiac contraction significantly degrades quality and quantitative accuracy of gated myocardial perfusion SPECT (MPS) images. In this study, we aimed to explore different techniques in motion-compensated temporal processing of MPS images and their impact on image quality and quantitative accuracy.

MATERIAL AND METHOD

50 patients without known heart condition underwent gated MPS. 3D motion compensation methods using Motion Freezing by Cedars Sinai (MF), Log-domain Diffeomorphic Demons (LDD) and Free-Form Deformation (FFD) were applied to warp all image phases to fit the end-diastolic (ED) phase. Afterwards, myocardial wall thickness, myocardial to blood pool contrast, and image contrast-to noise ratio (CNR) were measured in summed images with no motion compensation (NoMC) and compensated images (MF, LDD and FFD). Total Perfusion Defect (TPD) was derived from Cedars-Sinai software, on the basis of sex-specific normal limits.

RESULT

Left ventricle (LV) lateral wall thickness was reduced after applying motion compensation (p < 0.05). Myocardial to blood pool contrast and CNR in compensated images were greater than NoMC (p < 0.05). TPD_LDD was in good agreement with the corresponding TPD_MF (p = 0.13).

CONCLUSION

All methods have improved image quality and quantitative performance relative to NoMC. LDD and FFD are fully automatic and do not require any manual intervention, while MF is dependent on contour definition. In terms of diagnostic parameters LDD is in good agreement with MF which is a clinically accepted method. Further investigation along with diagnostic reference standards, in order to specify diagnostic value of each technique is recommended.

MR-CBCT image-guided system for radiotherapy of orthotopic rat prostate tumors

Multi-modality image-guided radiotherapy is the standard of care in contemporary cancer management; however, it is not common in preclinical settings due to both hardware and software limitations. Soft tissue lesions, such as orthotopic prostate tumors, are difficult to identify using cone beam computed tomography (CBCT) imaging alone. In this study, we characterized a research magnetic resonance (MR) scanner for preclinical studies and created a protocol for combined MR-CBCT image-guided small animal radiotherapy. Two in-house dual-modality, MR and CBCT compatible, phantoms were designed and manufactured using 3D printing technology. The phantoms were used for quality assurance tests and to facilitate end-to-end testing for combined preclinical MR and CBCT based treatment planning. MR and CBCT images of the phantoms were acquired utilizing a Varian 4.7 T scanner and XRad-225Cx irradiator, respectively. The geometry distortion was assessed by comparing MR images to phantom blueprints and CBCT. The corrected MR scans were co-registered with CBCT and subsequently used for treatment planning. The fidelity of 3D printed phantoms compared to the blueprint design yielded favorable agreement as verified with the CBCT measurements. The geometric distortion, which varied between -5% and 11% throughout the scanning volume, was substantially reduced to within 0.4% after correction. The distortion free MR images were co-registered with the corresponding CBCT images and imported into a commercial treatment planning software SmART Plan. The planning target volume (PTV) was on average 19% smaller when contoured on the corrected MR-CBCT images relative to raw images without distortion correction. An MR-CBCT based preclinical workflow was successfully designed and implemented for small animal radiotherapy. Combined MR-CBCT image-guided radiotherapy for preclinical research potentially delivers enhanced relevance to human radiotherapy for various disease sites. This novel protocol is wide-ranging and not limited to the orthotopic prostate tumor study presented in the study.

Nonrigid Image Registration Using Spatially Region-Weighted Correlation Ratio and GPU-Acceleration

OBJECTIVE

Nonrigid image registration with high accuracy and efficiency remains a challenging task for medical image analysis. In this paper, we present the spatially region-weighted correlation ratio (SRWCR) as a novel similarity measure to improve the registration performance.

METHODS

SRWCR is rigorously deduced from a three-dimension joint probability density function combining the intensity channels with an extra spatial information channel. SRWCR estimates the optimal functional dependence between the intensities for each spatial bin, in which the spatial distribution modeled by a cubic B-spline function is used to differentiate the contribution of voxels. We also analytically derive the gradient of SRWCR with respect to the transformation parameters and optimize it using a quasi-Newton approach. Furthermore, we propose a GPU-based parallel mechanism to accelerate the computation of SRWCR and its derivatives.

RESULTS

The experiments on synthetic images, public four-dimensional thoracic computed tomography (CT) dataset, retinal optical coherence tomography data, and clinical CT and positron emission tomography images confirm that SRWCR significantly outperforms some state-of-the-art techniques such as spatially encoded mutual information and Robust PaTch-based cOrrelation Ration.

CONCLUSION

This study demonstrates the advantages of SRWCR in tackling the practical difficulties due to distinct intensity changes, serious speckle noise, or different imaging modalities.

SIGNIFICANCE

The proposed registration framework might be more reliable to correct the nonrigid deformations and more potential for clinical applications.

Iterative inversion of deformation vector fields with feedback control

PURPOSE

Often, the inverse deformation vector field (DVF) is needed together with the corresponding forward DVF in four-dimesional (4D) reconstruction and dose calculation, adaptive radiation therapy, and simultaneous deformable registration. This study aims at improving both accuracy and efficiency of iterative algorithms for DVF inversion, and advancing our understanding of divergence and latency conditions.

METHOD

We introduce a framework of fixed-point iteration algorithms with active feedback control for DVF inversion. Based on rigorous convergence analysis, we design control mechanisms for modulating the inverse consistency (IC) residual of the current iterate, to be used as feedback into the next iterate. The control is designed adaptively to the input DVF with the objective to enlarge the convergence area and expedite convergence. Three particular settings of feedback control are introduced: constant value over the domain throughout the iteration; alternating values between iteration steps; and spatially variant values. We also introduce three spectral measures of the displacement Jacobian for characterizing a DVF. These measures reveal the critical role of what we term the nontranslational displacement component (NTDC) of the DVF. We carry out inversion experiments with an analytical DVF pair, and with DVFs associated with thoracic CT images of six patients at end of expiration and end of inspiration.

RESULTS

The NTDC-adaptive iterations are shown to attain a larger convergence region at a faster pace compared to previous nonadaptive DVF inversion iteration algorithms. By our numerical experiments, alternating control yields smaller IC residuals and inversion errors than constant control. Spatially variant control renders smaller residuals and errors by at least an order of magnitude, compared to other schemes, in no more than 10 steps. Inversion results also show remarkable quantitative agreement with analysis-based predictions.

CONCLUSION

Our analysis captures properties of DVF data associated with clinical CT images, and provides new understanding of iterative DVF inversion algorithms with a simple residual feedback control. Adaptive control is necessary and highly effective in the presence of nonsmall NTDCs. The adaptive iterations or the spectral measures, or both, may potentially be incorporated into deformable image registration methods.

GIFTed Demons: deformable image registration with local structure-preserving regularization using supervoxels for liver applications

Deformable image registration, a key component of motion correction in medical imaging, needs to be efficient and provides plausible spatial transformations that reliably approximate biological aspects of complex human organ motion. Standard approaches, such as Demons registration, mostly use Gaussian regularization for organ motion, which, though computationally efficient, rule out their application to intrinsically more complex organ motions, such as sliding interfaces. We propose regularization of motion based on supervoxels, which provides an integrated discontinuity preserving prior for motions, such as sliding. More precisely, we replace Gaussian smoothing by fast, structure-preserving, guided filtering to provide efficient, locally adaptive regularization of the estimated displacement field. We illustrate the approach by applying it to estimate sliding motions at lung and liver interfaces on challenging four-dimensional computed tomography (CT) and dynamic contrast-enhanced magnetic resonance imaging datasets. The results show that guided filter-based regularization improves the accuracy of lung and liver motion correction as compared to Gaussian smoothing. Furthermore, our framework achieves state-of-the-art results on a publicly available CT liver dataset.

Survey of Non-Rigid Registration Tools in Medicine

We catalogue available software solutions for non-rigid image registration to support scientists in selecting suitable tools for specific medical registration purposes. Registration tools were identified using non-systematic search in Pubmed, Web of Science, IEEE Xplore® Digital Library, Google Scholar, and through references in identified sources (n = 22). Exclusions are due to unavailability or inappropriateness. The remaining (n = 18) tools were classified by (i) access and technology, (ii) interfaces and application, (iii) living community, (iv) supported file formats, and (v) types of registration methodologies emphasizing the similarity measures implemented. Out of the 18 tools, (i) 12 are open source, 8 are released under a permissive free license, which imposes the least restrictions on the use and further development of the tool, 8 provide graphical processing unit (GPU) support; (ii) 7 are built on software platforms, 5 were developed for brain image registration; (iii) 6 are under active development but only 3 have had their last update in 2015 or 2016; (iv) 16 support the Analyze format, while 7 file formats can be read with only one of the tools; and (v) 6 provide multiple registration methods and 6 provide landmark-based registration methods. Based on open source, licensing, GPU support, active community, several file formats, algorithms, and similarity measures, the tools Elastics and Plastimatch are chosen for the platform ITK and without platform requirements, respectively. Researchers in medical image analysis already have a large choice of registration tools freely available. However, the most recently published algorithms may not be included in the tools, yet.

A Statistically Representative Atlas for Mapping Neuronal Circuits in the Drosophila Adult Brain

Imaging the expression patterns of reporter constructs is a powerful tool to dissect the neuronal circuits of perception and behavior in the adult brain of Drosophila, one of the major models for studying brain functions. To date, several Drosophila brain templates and digital atlases have been built to automatically analyze and compare collections of expression pattern images. However, there has been no systematic comparison of performances between alternative atlasing strategies and registration algorithms. Here, we objectively evaluated the performance of different strategies for building adult Drosophila brain templates and atlases. In addition, we used state-of-the-art registration algorithms to generate a new group-wise inter-sex atlas. Our results highlight the benefit of statistical atlases over individual ones and show that the newly proposed inter-sex atlas outperformed existing solutions for automated registration and annotation of expression patterns. Over 3,000 images from the Janelia Farm FlyLight collection were registered using the proposed strategy. These registered expression patterns can be searched and compared with a new version of the BrainBaseWeb system and BrainGazer software. We illustrate the validity of our methodology and brain atlas with registration-based predictions of expression patterns in a subset of clock neurons. The described registration framework should benefit to brain studies in Drosophila and other insect species.

Computational neuroanatomy of baby brains: A review

The first postnatal years are an exceptionally dynamic and critical period of structural, functional and connectivity development of the human brain. The increasing availability of non-invasive infant brain MR images provides unprecedented opportunities for accurate and reliable charting of dynamic early brain developmental trajectories in understanding normative and aberrant growth. However, infant brain MR images typically exhibit reduced tissue contrast (especially around 6 months of age), large within-tissue intensity variations, and regionally-heterogeneous, dynamic changes, in comparison with adult brain MR images. Consequently, the existing computational tools developed typically for adult brains are not suitable for infant brain MR image processing. To address these challenges, many infant-tailored computational methods have been proposed for computational neuroanatomy of infant brains. In this review paper, we provide a comprehensive review of the state-of-the-art computational methods for infant brain MRI processing and analysis, which have advanced our understanding of early postnatal brain development. We also summarize publically available infant-dedicated resources, including MRI datasets, computational tools, grand challenges, and brain atlases. Finally, we discuss the limitations in current research and suggest potential future research directions.

A Novel Hierarchical Template Matching Model for Cardiac Motion Estimation

Cardiovascular disease diagnosis and prognosis can be improved by measuring patient-specific in-vivo local myocardial strain using Magnetic Resonance Imaging. Local myocardial strain can be determined by tracking the movement of sample muscles points during cardiac cycle using cardiac motion estimation model. The tracking accuracy of the benchmark Free Form Deformation (FFD) model is greatly affected due to its dependency on tunable parameters and regularisation function. Therefore, Hierarchical Template Matching (HTM) model, which is independent of tunable parameters, regularisation function, and image-specific features, is proposed in this article. HTM has dense and uniform points correspondence that provides HTM with the ability to estimate local muscular deformation with a promising accuracy of less than half a millimetre of cardiac wall muscle. As a result, the muscles tracking accuracy has been significantly (p < 0.001) improved (30%) compared to the benchmark model. Such merits of HTM provide reliably calculated clinical measures which can be incorporated into the decision-making process of cardiac disease diagnosis and prognosis.

Landmark-based evaluation of a deformable motion correction for DCE-MRI of the liver

Purpose

Annotation of meaningful landmark ground truth on DCE-MRI is difficult and laborious. Motion correction methods applied to DCE-MRI of the liver are thus mostly evaluated using qualitative or indirect measures. We propose a novel landmark annotation scheme that facilitates the generation of landmark ground truth on larger clinical datasets.

Methods

In our annotation scheme, landmarks are equally distributed over all time points of all available dataset cases and annotated by multiple observers on a per-pair basis. The scheme is used to annotate 26 DCE-MRI of the liver. A subset of the ground truth is used to optimize parameters of a deformable motion correction. Several variants of the motion correction are evaluated on the remaining cases with respect to distances of corresponding landmarks after registration, deformation field properties, and qualitative measures.

Results

A landmark ground truth on 26 cases could be generated in under 12 h per observer with a mean inter-observer distance below the mean voxel diagonal. Furthermore, the landmarks are spatially well distributed within the liver. Parameter optimization significantly improves the performance of the motion correction, and landmark distance after registration is 2 mm. Qualitative evaluation of the motion correction reflects the quantitative results.

Conclusions

The annotation scheme makes a landmark-based evaluation of motion corrections for hepatic DCE-MRI practically feasible for larger clinical datasets. The comparably large number of cases enables both optimization and evaluation of motion correction methods.

Electronic supplementary material

The online version of this article (10.1007/s11548-018-1710-1) contains supplementary material, which is available to authorized users.

Framework for shape analysis of white matter fiber bundles

Diffusion imaging coupled with tractography algorithms allows researchers to image human white matter fiber bundles in-vivo. These bundles are three-dimensional structures with shapes that change over time during the course of development as well as in pathologic states. While most studies on white matter variability focus on analysis of tissue properties estimated from the diffusion data, e.g. fractional anisotropy, the shape variability of white matter fiber bundle is much less explored. In this paper, we present a set of tools for shape analysis of white matter fiber bundles, namely: (1) a concise geometric model of bundle shapes; (2) a method for bundle registration between subjects; (3) a method for deformation estimation. Our framework is useful for analysis of shape variability in white matter fiber bundles. We demonstrate our framework by applying our methods on two datasets: one consisting of data for 6 normal adults and another consisting of data for 38 normal children of age 11 days to 8.5 years. We suggest a robust and reproducible method to measure changes in the shape of white matter fiber bundles. We demonstrate how this method can be used to create a model to assess age-dependent changes in the shape of specific fiber bundles. We derive such models for an ensemble of white matter fiber bundles on our pediatric dataset and show that our results agree with normative human head and brain growth data. Creating these models for a large pediatric longitudinal dataset may improve understanding of both normal development and pathologic states and propose novel parameters for the examination of the pediatric brain.

Local All-Pass Geometric Deformations

This paper deals with the estimation of a deformation that describes the geometric transformation between two images. To solve this problem, we propose a novel framework that relies upon the brightness consistency hypothesis-a pixel's intensity is maintained throughout the transformation. Instead of assuming small distortion and linearizing the problem (e.g. via Taylor Series expansion), we propose to interpret the brightness hypothesis as an all-pass filtering relation between the two images. The key advantages of this new interpretation are that no restrictions are placed on the amplitude of the deformation or on the spatial variations of the images. Moreover, by converting the all-pass filtering to a linear forward-backward filtering relation, our solution to the estimation problem equates to solving a linear system of equations, which leads to a highly efficient implementation. Using this framework, we develop a fast algorithm that relates one image to another, on a local level, using an all-pass filter and then extracts the deformation from the filter-hence the name "Local All-Pass" (LAP) algorithm. The effectiveness of this algorithm is demonstrated on a variety of synthetic and real deformations that are found in applications, such as image registration and motion estimation. In particular, when compared with a selection of image registration algorithms, the LAP obtains very accurate results for significantly reduced computation time and is very robust to noise corruption.

Multi-modal and multi-vendor retina image registration

Multi-modal retinal image registration is often required to utilize the complementary information from different retinal imaging modalities. However, a robust and accurate registration is still a challenge due to the modality-varied resolution, contrast, and luminosity. In this paper, a two step registration method is proposed to address this problem. Descriptor matching on mean phase images is used to globally register images in the first step. Deformable registration based on modality independent neighbourhood descriptor (MIND) method is followed to locally refine the registration result in the second step. The proposed method is extensively evaluated on color fundus images and scanning laser ophthalmoscope (SLO) images. Both qualitative and quantitative tests demonstrate improved registration using the proposed method compared to the state-of-the-art. The proposed method produces significantly and substantially larger mean Dice coefficients compared to other methods (p<0.001). It may facilitate the measurement of corresponding features from different retinal images, which can aid in assessing certain retinal diseases.

Improving oncoplastic breast tumor bed localization for radiotherapy planning using image registration algorithms

Knowledge about tumor bed localization and its shape analysis is a crucial factor for preventing irradiation of healthy tissues during supportive radiotherapy and as a result, cancer recurrence. The localization process is especially hard for tumors placed nearby soft tissues, which undergo complex, nonrigid deformations. Among them, breast cancer can be considered as the most representative example. A natural approach to improving tumor bed localization is the use of image registration algorithms. However, this involves two unusual aspects which are not common in typical medical image registration: the real deformation field is discontinuous, and there is no direct correspondence between the cancer and its bed in the source and the target 3D images respectively. The tumor no longer exists during radiotherapy planning. Therefore, a traditional evaluation approach based on known, smooth deformations and target registration error are not directly applicable. In this work, we propose alternative artificial deformations which model the tumor bed creation process. We perform a comprehensive evaluation of the most commonly used deformable registration algorithms: B-Splines free form deformations (B-Splines FFD), different variants of the Demons and TV-L¹ optical flow. The evaluation procedure includes quantitative assessment of the dedicated artificial deformations, target registration error calculation, 3D contour propagation and medical experts visual judgment. The results demonstrate that the currently, practically applied image registration (rigid registration and B-Splines FFD) are not able to correctly reconstruct discontinuous deformation fields. We show that the symmetric Demons provide the most accurate soft tissues alignment in terms of the ability to reconstruct the deformation field, target registration error and relative tumor volume change, while B-Splines FFD and TV-L¹ optical flow are not an appropriate choice for the breast tumor bed localization problem, even though the visual alignment seems to be better than for the Demons algorithm. However, no algorithm could recover the deformation field with sufficient accuracy in terms of vector length and rotation angle differences.

A Meshfree Representation for Cardiac Medical Image Computing

The prominent advantage of meshfree method, is the way to build the representation of computational domain, based on the nodal points without any explicit meshing connectivity. Therefore, meshfree method can conveniently process the numerical computation inside interested domains with large deformation or inhomogeneity. In this paper, we adopt the idea of meshfree representation into cardiac medical image analysis in order to overcome the difficulties caused by large deformation and inhomogeneous materials of the heart. In our implementation, as element-free Galerkin method can efficiently build a meshfree representation using its shape function with moving least square fitting, we apply this meshfree method to handle large deformation or inhomogeneity for solving cardiac segmentation and motion tracking problems. We evaluate the performance of meshfree representation on a synthetic heart data and an in-vivo cardiac MRI image sequence. Results showed that the error of our framework against the ground truth was 0.1189 ± 0.0672 while the error of the traditional FEM was 0.1793 ± 0.1166. The proposed framework has minimal consistency constraints, handling large deformation and material discontinuities are simple and efficient, and it provides a way to avoid the complicated meshing procedures while preserving the accuracy with a relatively small number of nodes.

Multi-GPU configuration of 4D intensity modulated radiation therapy inverse planning using global optimization

We report on the design, implementation and characterization of a multi-graphic processing unit (GPU) computational platform for higher-order optimization in radiotherapy treatment planning. In collaboration with a commercial vendor (Varian Medical Systems, Palo Alto, CA), a research prototype GPU-enabled Eclipse (V13.6) workstation was configured. The hardware consisted of dual 8-core Xeon processors, 256 GB RAM and four NVIDIA Tesla K80 general purpose GPUs. We demonstrate the utility of this platform for large radiotherapy optimization problems through the development and characterization of a parallelized particle swarm optimization (PSO) four dimensional (4D) intensity modulated radiation therapy (IMRT) technique. The PSO engine was coupled to the Eclipse treatment planning system via a vendor-provided scripting interface. Specific challenges addressed in this implementation were (i) data management and (ii) non-uniform memory access (NUMA). For the former, we alternated between parameters over which the computation process was parallelized. For the latter, we reduced the amount of data required to be transferred over the NUMA bridge. The datasets examined in this study were approximately 300 GB in size, including 4D computed tomography images, anatomical structure contours and dose deposition matrices. For evaluation, we created a 4D-IMRT treatment plan for one lung cancer patient and analyzed computation speed while varying several parameters (number of respiratory phases, GPUs, PSO particles, and data matrix sizes). The optimized 4D-IMRT plan enhanced sparing of organs at risk by an average reduction of [Formula: see text] in maximum dose, compared to the clinical optimized IMRT plan, where the internal target volume was used. We validated our computation time analyses in two additional cases. The computation speed in our implementation did not monotonically increase with the number of GPUs. The optimal number of GPUs (five, in our study) is directly related to the hardware specifications. The optimization process took 35 min using 50 PSO particles, 25 iterations and 5 GPUs.

A novel contour-based registration of lateral cephalogram and profile photograph

A contour-based automatic registration method of lateral cephalograms and profile photographs is proposed to facilitate the accurate measurement of anteroposterior (AP) position of maxillary central incisors relative to the forehead. There are mainly three steps in the proposed method. First, a hierarchical contour detection algorithm is employed to obtain contours of forehead and nose in lateral cephalograms and profile photographs, respectively. Curve deviation around Nasion of Soft Tissue (Ns) is further corrected using an iterative polynomial curve fitting algorithm according to the characteristics of cephalograms. Second, the coarse registration is performed based on four landmark pairs using a routine least squares method for each image pair, and then the contours are roughly matched. Finally, the coarse registration is further refined by applying the coherent point drift (CPD) algorithm to all the contour points. Using image pairs of lateral cephalograms and profile photographs from 49 Chinese patients, we show that the proposed method achieves higher performance in terms of accuracy and robustness than the existing methods.

7T MRI subthalamic nucleus atlas for use with 3T MRI

Deep brain stimulation (DBS) of the subthalamic nucleus (STN) reduces motor symptoms in most patients with Parkinson disease (PD), yet may produce untoward effects. Investigation of DBS effects requires accurate localization of the STN, which can be difficult to identify on magnetic resonance images collected with clinically available 3T scanners. The goal of this study is to develop a high-quality STN atlas that can be applied to standard 3T images. We created a high-definition STN atlas derived from seven older participants imaged at 7T. This atlas was nonlinearly registered to a standard template representing 56 patients with PD imaged at 3T. This process required development of methodology for nonlinear multimodal image registration. We demonstrate mm-scale STN localization accuracy by comparison of our 3T atlas with a publicly available 7T atlas. We also demonstrate less agreement with an earlier histological atlas. STN localization error in the 56 patients imaged at 3T was less than 1 mm on average. Our methodology enables accurate STN localization in individuals imaged at 3T. The STN atlas and underlying 3T average template in MNI space are freely available to the research community. The image registration methodology developed in the course of this work may be generally applicable to other datasets.