Registration using sparse free-form deformations

Low-rank motion correction for accelerated free-breathing first-pass myocardial perfusion imaging

PURPOSE

Develop a novel approach for accelerated 2D free-breathing myocardial perfusion via low-rank motion-corrected (LRMC) reconstructions.

METHODS

Myocardial perfusion imaging requires high spatial and temporal resolution, despite scan time constraints. Here, we incorporate LRMC models into the reconstruction-encoding operator, together with high-dimensionality patch-based regularization, to produce high quality, motion-corrected myocardial perfusion series from free-breathing acquisitions. The proposed framework estimates beat-to-beat nonrigid respiratory (and any other incidental) motion and the dynamic contrast subspace from the actual acquired data, which are then incorporated into the proposed LRMC reconstruction. LRMC was compared with iterative SENSitivity Encoding (SENSE) (itSENSE) and low-rank plus sparse (LpS) reconstruction in 10 patients based on image-quality scoring and ranking by two clinical expert readers.

RESULTS

LRMC achieved significantly improved results relative to itSENSE and LpS in terms of image sharpness, temporal coefficient of variation, and expert reader evaluation. Left ventricle image sharpness was approximately 75%, 79%, and 86% for itSENSE, LpS and LRMC, respectively, indicating improved image sharpness for the proposed approach. Corresponding temporal coefficient of variation results were 23%, 11% and 7%, demonstrating improved temporal fidelity of the perfusion signal with the proposed LRMC. Corresponding clinical expert reader scores (1-5, from poor to excellent image quality) were 3.3, 3.9 and 4.9, demonstrating improved image quality with the proposed LRMC, in agreement with the automated metrics.

CONCLUSION

LRMC produces motion-corrected myocardial perfusion in free-breathing acquisitions with substantially improved image quality when compared with iterative SENSE and LpS reconstructions.

Identifying Myocardial Infarction Using Hierarchical Template Matching-Based Myocardial Strain: Algorithm Development and Usability Study

Background

Myocardial infarction (MI; location and extent of infarction) can be determined by late enhancement cardiac magnetic resonance (CMR) imaging, which requires the injection of a potentially harmful gadolinium-based contrast agent (GBCA). Alternatively, emerging research in the area of myocardial strain has shown potential to identify MI using strain values.

Objective

This study aims to identify the location of MI by developing an applied algorithmic method of circumferential strain (CS) values, which are derived through a novel hierarchical template matching (HTM) method.

Methods

HTM-based CS H-spread from end-diastole to end-systole was used to develop an applied method. Grid-tagging magnetic resonance imaging was used to calculate strain values in the left ventricular (LV) myocardium, followed by the 16-segment American Heart Association model. The data set was used with k-fold cross-validation to estimate the percentage reduction of H-spread among infarcted and noninfarcted LV segments. A total of 43 participants (38 MI and 5 healthy) who underwent CMR imaging were retrospectively selected. Infarcted segments detected by using this method were validated by comparison with late enhancement CMR, and the diagnostic performance of the applied algorithmic method was evaluated with a receiver operating characteristic curve test.

Results

The H-spread of the CS was reduced in infarcted segments compared with noninfarcted segments of the LV. The reductions were 30% in basal segments, 30% in midventricular segments, and 20% in apical LV segments. The diagnostic accuracy of detection, using the reported method, was represented by area under the curve values, which were 0.85, 0.82, and 0.87 for basal, midventricular, and apical slices, respectively, demonstrating good agreement with the late-gadolinium enhancement–based detections.

Conclusions

The proposed applied algorithmic method has the potential to accurately identify the location of infarcted LV segments without the administration of late-gadolinium enhancement. Such an approach adds the potential to safely identify MI, potentially reduce patient scanning time, and extend the utility of CMR in patients who are contraindicated for the use of GBCA.

Sparse Data-Driven Learning for Effective and Efficient Biomedical Image Segmentation

Sparsity is a powerful concept to exploit for high-dimensional machine learning and associated representational and computational efficiency. Sparsity is well suited for medical image segmentation. We present a selection of techniques that incorporate sparsity, including strategies based on dictionary learning and deep learning, that are aimed at medical image segmentation and related quantification.

Weakly-supervised convolutional neural networks for multimodal image registration

One of the fundamental challenges in supervised learning for multimodal image registration is the lack of ground-truth for voxel-level spatial correspondence. This work describes a method to infer voxel-level transformation from higher-level correspondence information contained in anatomical labels. We argue that such labels are more reliable and practical to obtain for reference sets of image pairs than voxel-level correspondence. Typical anatomical labels of interest may include solid organs, vessels, ducts, structure boundaries and other subject-specific ad hoc landmarks. The proposed end-to-end convolutional neural network approach aims to predict displacement fields to align multiple labelled corresponding structures for individual image pairs during the training, while only unlabelled image pairs are used as the network input for inference. We highlight the versatility of the proposed strategy, for training, utilising diverse types of anatomical labels, which need not to be identifiable over all training image pairs. At inference, the resulting 3D deformable image registration algorithm runs in real-time and is fully-automated without requiring any anatomical labels or initialisation. Several network architecture variants are compared for registering T2-weighted magnetic resonance images and 3D transrectal ultrasound images from prostate cancer patients. A median target registration error of 3.6 mm on landmark centroids and a median Dice of 0.87 on prostate glands are achieved from cross-validation experiments, in which 108 pairs of multimodal images from 76 patients were tested with high-quality anatomical labels.

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.

Phase Vector Incompressible Registration Algorithm for Motion Estimation From Tagged Magnetic Resonance Images

Tagged magnetic resonance imaging has been used for decades to observe and quantify motion and strain of deforming tissue. It is challenging to obtain 3-D motion estimates due to a tradeoff between image slice density and acquisition time. Typically, interpolation methods are used either to combine 2-D motion extracted from sparse slice acquisitions into 3-D motion or to construct a dense volume from sparse acquisitions before image registration methods are applied. This paper proposes a new phase-based 3-D motion estimation technique that first computes harmonic phase volumes from interpolated tagged slices and then matches them using an image registration framework. The approach uses several concepts from diffeomorphic image registration with a key novelty that defines a symmetric similarity metric on harmonic phase volumes from multiple orientations. The material property of harmonic phase solves the aperture problem of optical flow and intensity-based methods and is robust to tag fading. A harmonic magnitude volume is used in enforcing incompressibility in the tissue regions. The estimated motion fields are dense, incompressible, diffeomorphic, and inverse-consistent at a 3-D voxel level. The method was evaluated using simulated phantoms, human brain data in mild head accelerations, human tongue data during speech, and an open cardiac data set. The method shows comparable accuracy to three existing methods while demonstrating low computation time and robustness to tag fading and noise.

Intensity based methods for brain MRI longitudinal registration. A study on multiple sclerosis patients

Registration is a key step in many automatic brain Magnetic Resonance Imaging (MRI) applications. In this work we focus on longitudinal registration of brain MRI for Multiple Sclerosis (MS) patients. First of all, we analyze the effect that MS lesions have on registration by synthetically eliminating some of the lesions. Our results show how a widely used method for longitudinal registration such as rigid registration is practically unconcerned by the presence of MS lesions while several non-rigid registration methods produce outputs that are significantly different. We then focus on assessing which is the best registration method for longitudinal MRI images of MS patients. In order to analyze the results obtained for all studied criteria, we use both descriptive statistics and statistical inference: one way ANOVA, pairwise t-tests and permutation tests.

Edge- and detail-preserving sparse image representations for deformable registration of chest MRI and CT volumes

Deformable medical image registration requires the optimisation of a function with a large number of degrees of freedom. Commonly-used approaches to reduce the computational complexity, such as uniform B-splines and Gaussian image pyramids, introduce translation-invariant homogeneous smoothing, and may lead to less accurate registration in particular for motion fields with discontinuities. This paper introduces the concept of sparse image representation based on supervoxels, which are edge-preserving and therefore enable accurate modelling of sliding organ motions frequently seen in respiratory and cardiac scans. Previous shortcomings of using supervoxels in motion estimation, in particular inconsistent clustering in ambiguous regions, are overcome by employing multiple layers of supervoxels. Furthermore, we propose a new similarity criterion based on a binary shape representation of supervoxels, which improves the accuracy of single-modal registration and enables multimodal registration. We validate our findings based on the registration of two challenging clinical applications of volumetric deformable registration: motion estimation between inhale and exhale phase of CT scans for radiotherapy planning, and deformable multi-modal registration of diagnostic MRI and CT chest scans. The experiments demonstrate state-of-the-art registration accuracy, and require no additional anatomical knowledge with greatly reduced computational complexity.

3D intraventricular flow mapping from colour Doppler images and wall motion

We propose a new method to recover 3D time-resolved velocity vectors within the left ventricle (LV) using a combination of multiple registered 3D colour Doppler images and LV wall motion. Incorporation of wall motion, calculated from 3D B-Mode images, and the use of a multi-scale reconstruction framework allow recovery of 3D velocity over the entire ventricle, even in regions where there is little or no Doppler data. Our method is tested on the LV of a paediatric patient and is compared to 2D and 3D flow Magnetic Resonance Imaging (MRI). Use of wall motion information increased stroke volume accuracy by 14%, and enabled full 3D velocity mapping within the ventricle. Velocity distribution showed good agreement with respect to MRI, and vortex formation during diastole was successfully reconstructed.

Concurrent tumor segmentation and registration with uncertainty-based sparse non-uniform graphs

In this paper, we present a graph-based concurrent brain tumor segmentation and atlas to diseased patient registration framework. Both segmentation and registration problems are modeled using a unified pairwise discrete Markov Random Field model on a sparse grid superimposed to the image domain. Segmentation is addressed based on pattern classification techniques, while registration is performed by maximizing the similarity between volumes and is modular with respect to the matching criterion. The two problems are coupled by relaxing the registration term in the tumor area, corresponding to areas of high classification score and high dissimilarity between volumes. In order to overcome the main shortcomings of discrete approaches regarding appropriate sampling of the solution space as well as important memory requirements, content driven samplings of the discrete displacement set and the sparse grid are considered, based on the local segmentation and registration uncertainties recovered by the min marginal energies. State of the art results on a substantial low-grade glioma database demonstrate the potential of our method, while our proposed approach shows maintained performance and strongly reduced complexity of the model.

Contour tracking in echocardiographic sequences via sparse representation and dictionary learning

This paper presents a dynamical appearance model based on sparse representation and dictionary learning for tracking both endocardial and epicardial contours of the left ventricle in echocardiographic sequences. Instead of learning offline spatiotemporal priors from databases, we exploit the inherent spatiotemporal coherence of individual data to constraint cardiac contour estimation. The contour tracker is initialized with a manual tracing of the first frame. It employs multiscale sparse representation of local image appearance and learns online multiscale appearance dictionaries in a boosting framework as the image sequence is segmented frame-by-frame sequentially. The weights of multiscale appearance dictionaries are optimized automatically. Our region-based level set segmentation integrates a spectrum of complementary multilevel information including intensity, multiscale local appearance, and dynamical shape prediction. The approach is validated on twenty-six 4D canine echocardiographic images acquired from both healthy and post-infarct canines. The segmentation results agree well with expert manual tracings. The ejection fraction estimates also show good agreement with manual results. Advantages of our approach are demonstrated by comparisons with a conventional pure intensity model, a registration-based contour tracker, and a state-of-the-art database-dependent offline dynamical shape model. We also demonstrate the feasibility of clinical application by applying the method to four 4D human data sets.

Simultaneous multiresolution strategies for nonrigid image registration

Multiresolution strategies are commonly used in the nonrigid registration to avoid local minima in the optimization space. Generally, a step-by-step hierarchical approach is adopted, in which the registration starts on a level with reduced complexity (downsampled images, global transformations), then continuing to levels with increased complexity, until the finest level is reached. In this paper, we propose two alternative multiresolution strategies for both the data and transformation models, in which different resolution levels are considered simultaneously instead of subsequently. Through combining the different strategies for data and transformation, we systematically define 3 × 3 multiresolution schemes, including both existing and novel methods. Experiments on 10 pairs of computed tomography lung data sets showed that the best performing strategy resulted in a reduction of the upper quartile of the mean target registration error from 2 to 1.5 mm, compared with the conventionally hierarchical multiresolution method, while achieving smoother deformations. Experiments with intersubject registration of 18 3D T1-weighted MRI brain scans confirmed that simultaneous multiresolution strategies produce more accurate registration results (median of mean overlap increased from 0.55 to 0.57) and smoother deformation fields than the traditionally hierarchical method. Evaluation of robustness indicated that the largest differences in accuracy between methods are observed for structures with a relatively large initial misalignment.

A locally adaptive regularization based on anisotropic diffusion for deformable image registration of sliding organs

We propose a deformable image registration algorithm that uses anisotropic smoothing for regularization to find correspondences between images of sliding organs. In particular, we apply the method for respiratory motion estimation in longitudinal thoracic and abdominal computed tomography scans. The algorithm uses locally adaptive diffusion tensors to determine the direction and magnitude with which to smooth the components of the displacement field that are normal and tangential to an expected sliding boundary. Validation was performed using synthetic, phantom, and 14 clinical datasets, including the publicly available DIR-Lab dataset. We show that motion discontinuities caused by sliding can be effectively recovered, unlike conventional regularizations that enforce globally smooth motion. In the clinical datasets, target registration error showed improved accuracy for lung landmarks compared to the diffusive regularization. We also present a generalization of our algorithm to other sliding geometries, including sliding tubes (e.g., needles sliding through tissue, or contrast agent flowing through a vessel). Potential clinical applications of this method include longitudinal change detection and radiotherapy for lung or abdominal tumours, especially those near the chest or abdominal wall.

Deformable medical image registration: a survey

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.