An improved algorithm for 2-D translational motion artifact correction

Retrospective motion artifact correction of structural MRI images using deep learning improves the quality of cortical surface reconstructions

Head motion during MRI acquisition presents significant challenges for neuroimaging analyses. In this work, we present a retrospective motion correction framework built on a Fourier domain motion simulation model combined with established 3D convolutional neural network (CNN) architectures. Quantitative evaluation metrics were used to validate the method on three separate multi-site datasets. The 3D CNN was trained using motion-free images that were corrupted using simulated artifacts. CNN based correction successfully diminished the severity of artifacts on real motion affected data on a separate test dataset as measured by significant improvements in image quality metrics compared to a minimal motion reference image. On the test set of 13 image pairs, the mean peak signal-to-noise-ratio was improved from 31.7 to 33.3 dB. Furthermore, improvements in cortical surface reconstruction quality were demonstrated using a blinded manual quality assessment on the Parkinson's Progression Markers Initiative (PPMI) dataset. Upon applying the correction algorithm, out of a total of 617 images, the number of quality control failures was reduced from 61 to 38. On this same dataset, we investigated whether motion correction resulted in a more statistically significant relationship between cortical thickness and Parkinson's disease. Before correction, significant cortical thinning was found to be restricted to limited regions within the temporal and frontal lobes. After correction, there was found to be more widespread and significant cortical thinning bilaterally across the temporal lobes and frontal cortex. Our results highlight the utility of image domain motion correction for use in studies with a high prevalence of motion artifacts, such as studies of movement disorders as well as infant and pediatric subjects.

A k-Space Model of Movement Artefacts: Application to Segmentation Augmentation and Artefact Removal

Patient movement during the acquisition of magnetic resonance images (MRI) can cause unwanted image artefacts. These artefacts may affect the quality of clinical diagnosis and cause errors in automated image analysis. In this work, we present a method for generating realistic motion artefacts from artefact-free magnitude MRI data to be used in deep learning frameworks, increasing training appearance variability and ultimately making machine learning algorithms such as convolutional neural networks (CNNs) more robust to the presence of motion artefacts. By modelling patient movement as a sequence of randomly-generated, 'demeaned', rigid 3D affine transforms, we resample artefact-free volumes and combine these in k-space to generate motion artefact data. We show that by augmenting the training of semantic segmentation CNNs with artefacts, we can train models that generalise better and perform more reliably in the presence of artefact data, with negligible cost to their performance on clean data. We show that the performance of models trained using artefact data on segmentation tasks on real-world test-retest image pairs is more robust. We also demonstrate that our augmentation model can be used to learn to retrospectively remove certain types of motion artefacts from real MRI scans. Finally, we show that measures of uncertainty obtained from motion augmented CNN models reflect the presence of artefacts and can thus provide relevant information to ensure the safe usage of deep learning extracted biomarkers in a clinical pipeline.

Reconstruction of dynamic contrast enhanced magnetic resonance imaging of the breast with temporal constraints

A number of methods using temporal and spatial constraints have been proposed for reconstruction of undersampled dynamic magnetic resonance imaging (MRI) data. The complex data can be constrained or regularized in a number of different ways, for example, the time derivative of the magnitude and phase image voxels can be constrained separately or jointly. Intuitively, the performance of different regularizations will depend on both the data and the chosen temporal constraints. Here, a complex temporal total variation (TV) constraint was compared to the use of separate real and imaginary constraints, and to a magnitude constraint alone. Projection onto Convex Sets (POCS) with a gradient descent method was used to implement the diverse temporal constraints in reconstructions of DCE MRI data. For breast DCE data, serial POCS with separate real and imaginary TV constraints was found to give relatively poor results while serial/parallel POCS with a complex temporal TV constraint and serial POCS with a magnitude-only temporal TV constraint performed well with an acceleration factor as large as R=6. In the tumor area, the best method was found to be parallel POCS with complex temporal TV constraint. This method resulted in estimates for the pharmacokinetic parameters that were linearly correlated to those estimated from the fully-sampled data, with K(trans,R=6)=0.97 K(trans,R=1)+0.00 with correlation coefficient r=0.98, k(ep,R=6)=0.95 k(ep,R=1)+0.00 (r=0.85). These results suggest that it is possible to acquire highly undersampled breast DCE-MRI data with improved spatial and/or temporal resolution with minimal loss of image quality.

Microarray missing data imputation based on a set theoretic framework and biological knowledge

Gene expressions measured using microarrays usually suffer from the missing value problem. However, in many data analysis methods, a complete data matrix is required. Although existing missing value imputation algorithms have shown good performance to deal with missing values, they also have their limitations. For example, some algorithms have good performance only when strong local correlation exists in data while some provide the best estimate when data is dominated by global structure. In addition, these algorithms do not take into account any biological constraint in their imputation. In this paper, we propose a set theoretic framework based on projection onto convex sets (POCS) for missing data imputation. POCS allows us to incorporate different types of a priori knowledge about missing values into the estimation process. The main idea of POCS is to formulate every piece of prior knowledge into a corresponding convex set and then use a convergence-guaranteed iterative procedure to obtain a solution in the intersection of all these sets. In this work, we design several convex sets, taking into consideration the biological characteristic of the data: the first set mainly exploit the local correlation structure among genes in microarray data, while the second set captures the global correlation structure among arrays. The third set (actually a series of sets) exploits the biological phenomenon of synchronization loss in microarray experiments. In cyclic systems, synchronization loss is a common phenomenon and we construct a series of sets based on this phenomenon for our POCS imputation algorithm. Experiments show that our algorithm can achieve a significant reduction of error compared to the KNNimpute, SVDimpute and LSimpute methods.

Correcting bulk in-plane motion artifacts in MRI using the point spread function

A technique is proposed for correcting both translational and rotational motion artifacts in magnetic resonance imaging without the need to collect additional navigator data or to perform intensive postprocessing. The method is based on measuring the point spread function (PSF) by attaching one or two point-sized markers to the main imaging object. Following the isolation of a PSF marker from the acquired image, translational motion could be corrected directly from the modulation transfer function, without the need to determine the object's positions during the scan, although the shifts could be extracted if desired. Rotation is detected by analyzing the relative displacements of two such markers. The technique was evaluated with simulations, phantom and in vivo experiments.

Retrospective intra-scan motion correction

This paper analyzes the effects of intra-scan motion and demonstrates the possibility of correcting them directly in k-space with a new automatic retrospective method. The method is presented for series of 2D acquisitions with Cartesian sampling. Using a reference k-space acquisition (corrected for translations) within the series, intra-scan motion parameters are accurately estimated for each trajectory in k-space of each data set in the series resulting in pseudo-random sample positions. The images are reconstructed with a Bayesian estimator that can handle sparse arbitrary sampling in k-space and reduces intra-scan rotation artefacts to the noise level. The method has been assessed by means of a Monte Carlo study on axial brain images for different signal-to-noise ratios. The accuracy of motion estimates is better than 0.1 degrees for rotation, and 0.1 and 0.05 pixel, respectively, for translation along the read and phase directions for signal-to-noise ratios higher than 6 of the signals on each trajectory. An example of reconstruction from experimental data corrupted by head motion is also given.

Motion artifact reduction technique for dual-contrast FSE imaging

There is considerable similarity between proton density-weighted (PDw) and T2-weighted (T2w) images acquired by dual-contrast fast spin-echo (FSE) sequences. The similarity manifests itself in image space as consistency between the phases of PDw and T2w images and in k-space as correspondence between PDw and T2w k-space data. A method for motion artifact reduction for dual-contrast FSE imaging has been developed. The method uses projection onto convex sets (POCS) formalism and is based on image space phase consistency and the k-space similarity between PDw and T2w images. When coupled with a modified dual-contrast FSE phase encoding scheme the method can yield considerable artifact reduction, as long as less than half of the acquired data is corrupted by motion. The feasibility and efficiency of the developed method were demonstrated using phantom and human MRI data.

Autocorrection in MR imaging: adaptive motion correction without navigator echoes

A technique for automatic retrospective correction of motion artifacts on magnetic resonance (MR) images was developed that uses only the raw (complex) data from the MR imager and requires no knowledge of patient motion during the acquisition. The algorithm was tested on coronal images of the rotator cuff in a series of 144 patients, and the improvements in image quality were similar to those achieved with navigator echoes. The results demonstrate that autocorrection can significantly reduce motion artifacts in a technically demanding MR imaging application.

Cancellation of motion artifact in MRI due to 2D rigid translational motion

A new algorithm for cancelling MRI artifact due to translational motion in the image plane is described. Unlike the conventional iterative phase retrieval algorithm, in which there is no guarantee for the convergence, a direct method for estimating the motion is proposed. In the previous approach, the motions in the readout(x-) direction and the phase encoding(y-) direction are estimated simultaneously. However, the feature of the each x- and y-directional motion is different. Based on the analysis of their features, each x- and y-directional motion is cancelled by different algorithms in two steps. First, we notice that the x-directional motion corresponds to a shift of the x-directional spectrum of the MRI signal, so the x-directional motion can be cancelled by shifting the spectrum in inverse direction. Next, the y-directional motion is cancelled using a new constraint, with which the motion component and the true image component can be separated. The algorithm is shown to be effective by simulations.

MRI artifact cancellation due to rigid motion in the imaging plane

A post-processing technique has been developed to suppress the magnetic resonance imaging (MRI) artifact arising from object planar rigid motion. In two-dimensional Fourier transform (2-DFT) MRI, rotational and translational motions of the target during magnetic resonance magnetic resonance (MR) scan respectively impose nonuniform sampling and a phase error an the collected MRI signal. The artifact correction method introduced considers the following three conditions: (1) for planar rigid motion with known parameters, a reconstruction algorithm based on bilinear interpolation and the super-position method is employed to remove the MRI artifact, (2) for planar rigid motion with known rotation angle and unknown translational motion (including an unknown rotation center), first, a super-position bilinear interpolation algorithm is used to eliminate artifact due to rotation about the center of the imaging plane, following which a phase correction algorithm is applied to reduce the remaining phase error of the MRI signal, and (3) to estimate unknown parameters of a rigid motion, a minimum energy method is proposed which utilizes the fact that planar rigid motion increases the measured energy of an ideal MR image outside the boundary of the imaging object; by using this property all unknown parameters of a typical rigid motion are accurately estimated in the presence of noise. To confirm the feasibility of employing the proposed method in a clinical setting, the technique was used to reduce unknown rigid motion artifact arising from the head movements of two volunteers.

An improved method for MRI artifact correction due to translational motion in the imaging plane

A computer postprocessing technique is developed to remove MRI artifact arising from unknown translational motion in the imaging plane. Based on previous artifact correction methods, the improved technique uses two successive steps to reduce read out and phase-encoding direction artifacts: First, the spectrum shift method is applied to remove read-out axis translational motion. Then, the phase retrieval method is employed to eliminate the remaining subpixel motion of the read-out axis and the entire motion of the phase-encoding axis. In the presence of noise, to protect edge detection (in the spectrum shift method), two high-density gray-level markers are added, one to each side of the imaging object. Experimental results with an actual MR scan confirmed the ability of the method to correct the artifact of an MR image caused by unknown translational motion in the imaging plane.

Motion artifact suppression: a review of post-processing techniques

Patient motion during data acquisition in magnetic resonance imaging causes artifacts in the reconstructed image, which for two-dimensional Fourier transform imaging techniques appear as blurring and ghost repetitions of the moving structures. While the problem with intra-view effects has been effectively addressed using gradient moment nulling techniques, there is no corresponding technique for inter-view effects with equal effectiveness and general applicability. A number of techniques have been proposed for correcting the inter-view effects, and these may be divided into those that minimise the corruption of the data, and those that post-process the data to restore the image. The techniques in the former category are briefly reviewed, then those in the latter category are examined in detail. These are analysed in terms of motion model, model parameter estimation, and data correction.