Reducing Motion Artifacts in Brain MRI Using Vision Transformers and Self-Supervised Learning

To investigate whether deep learning with high-pass filtering can be used to effectively reduce motion artifacts in magnetic resonance (MR) images of the liver. The subjects were 69 patients who underwent liver MR examination at our hospital. Simulated motion artifact images (SMAIs) were created from non-artifact images (NAIs) and used for deep learning. Structural similarity index measure (SSIM) and contrast ratio (CR) were used to verify the effect of reducing motion artifacts in motion artifact reduction image (MARI) output from the obtained deep learning model. In the visual assessment, reduction of motion artifacts and image sharpness were evaluated between motion artifact images (MAIs) and MARIs. The SSIM values were 0.882 on the MARIs and 0.869 on the SMAIs. There was no statistically significant difference in CR between NAIs and MARIs. The visual assessment showed that MARIs had reduced motion artifacts and improved sharpness compared to MAIs. The learning model in this study is indicated to be reduced motion artifacts without decreasing the sharpness of liver MR images.

Optical mapping is a high-resolution fluorescence imaging technique, which provides highly detailed visualizations of the electrophysiological wave phenomena, which trigger the beating of the heart. Recent advancements in optical mapping have demonstrated that the technique can now be performed with moving and contracting hearts and that motion and motion artifacts, once a major limitation, can now be overcome by numerically tracking and stabilizing the heart's motion. As a result, the optical measurement of electrical activity can be obtained from the moving heart surface in a co-moving frame of reference and motion artifacts can be reduced substantially. The aim of this study is to assess and validate the performance of a 2D marker-free motion tracking algorithm, which tracks motion and non-rigid deformations in video images. Because the tracking algorithm does not require markers to be attached to the tissue, it is necessary to verify that it accurately tracks the displacements of the cardiac tissue surface, which not only contracts and deforms, but also fluoresces and exhibits spatio-temporal physiology-related intensity changes. We used computer simulations to generate synthetic optical mapping videos, which show the contracting and fluorescing ventricular heart surface. The synthetic data reproduces experimental data as closely as possible and shows electrical waves propagating across the deforming tissue surface, as seen during voltage-sensitive imaging. We then tested the motion tracking and motion-stabilization algorithm on the synthetic as well as on experimental data. The motion tracking and motion-stabilization algorithm decreases motion artifacts approximately by 80% and achieves sub-pixel precision when tracking motion of 1–10 pixels (in a video image with 100 by 100 pixels), effectively inhibiting motion such that little residual motion remains after tracking and motion-stabilization. To demonstrate the performance of the algorithm, we present optical maps with a substantial reduction in motion artifacts showing action potential waves propagating across the moving and strongly deforming ventricular heart surface. The tracking algorithm reliably tracks motion if the tissue surface is illuminated homogeneously and shows sufficient contrast or texture which can be tracked or if the contrast is artificially or numerically enhanced. In this study, we also show how a reduction in dissociation-related motion artifacts can be quantified and linked to tracking precision. Our results can be used to advance optical mapping techniques, enabling them to image contracting hearts, with the ultimate goal of studying the mutual coupling of electrical and mechanical phenomena in healthy and diseased hearts.

Patient motion during computed tomography (CT) scan can result in serious degradation of imaging quality, and is of increasing concern due to the aging population and associated diseases. In this paper, we address this problem by focusing on the reduction of head motion artifacts. To achieve this, we introduce a head motion simulation system and a multi-scale deep learning architecture. The proposed motion simulation system can simulate rigid movement including translation and rotation. The images with simulated motion serve as the training set for the network, and the original motion free images serve as the gold standard. Motion artifacts exhibit in the image space as streaks and patchy shadows. We propose a multiscale neural network to learn the artifact. With different branches equipped with ResBlock and down-sampling, the network can learn long scale streaks and short scale shadow artifacts. Although we trained the network on simulated images, we find that the learned network generalizes well to images with real motion artifacts.

Assessment of artifacts reduction and denoising techniques in Electrocardiographic signals using Ensemble Average-based method

AimTo subjectively and objectively evaluate the feasibility and diagnostic reliability of a low-dose, long-pitch dual-source chest CT protocol on third-generation dual-source CT (DSCT) with spectral shaping at 100Sn kVp for COVID-19 patients.Materials and methodsPatients with COVID-19 and positive swab-test undergoing to a chest CT on third-generation DSCT were included. The imaging protocol included a dual-energy acquisition (HD-DECT, 90/150Sn kVp) and fast, low-dose, long-pitch CT, dual-source scan at 100Sn kVp (LDCT). Subjective (Likert Scales) and objective (signal-to-noise and contrast-to-noise ratios, SNR and CNR) analyses were performed; radiation dose and acquisition times were recorded. Nonparametric tests were used.ResultsThe median radiation dose was lower for LDCT than HD-DECT (Effective dose, ED: 0.28 mSv vs. 3.28 mSv, p = 0.016). LDCT had median acquisition time of 0.62 s (vs 2.02 s, p = 0.016). SNR and CNR were significantly different in several thoracic structures between HD-DECT and LDCT, with exception of lung parenchyma. Qualitative analysis demonstrated significant reduction in motion artifacts (p = 0.031) with comparable diagnostic reliability between HD-DECT and LDCT.ConclusionsUltra-low-dose, dual-source, fast CT protocol provides highly diagnostic images for COVID-19 with potential for reduction in dose and motion artifacts.

Reduction of respiratory motion artifacts in free-breathing abdominal MRI using strategic averaging of reassembled k-space data with Self-Modeled respiratory state sorting.

A technique has been developed whereby motion can be detected in real time during the acquisition of data. This enables the implementation of several algorithms to reduce or eliminate motion effects from an image as it is being acquired. One such algorithm previously described is the acceptance/rejection method. This paper deals with another real-time algorithm called the diminishing variance algorithm (DVA). With this method, a complete set of preliminary data is acquired along with information about the relative motion position of each frame of data. After all the preliminary data are acquired, the position information is used to determine which data frames are most corrupted by motion. Frames of data are then reacquired, starting with the most corrupted one. The position information is continually updated in an iterative process; therefore, each subsequent reacquisition is always done on the worst frame of data. The algorithm has been implemented on several different types of sequences. Preliminary in vivo studies indicate that motion artifacts are dramatically reduced.

Deep learning based MRI reconstruction methods typically require databases of fully-sampled data as reference for training. However, fully-sampled acquisitions may be either challenging or impossible in numerous scenarios. Self-supervised learning enables training neural networks for MRI reconstruction without fully-sampled data by splitting available measurements into two disjoint sets. One of them is used in data consistency units in the network, and the other is used to define the loss. However, the performance of self-supervised learning degrades at high acceleration rates due to scarcity of acquired data. We propose a multi-mask self-supervised learning approach, which retrospectively splits available measurements into multiple 2-tuples of disjoint sets. Results on 3D knee and brain MRI shows that the proposed multi-mask self-supervised learning approach significantly improves upon single mask self-supervised learning at high acceleration rates.

Patient motion during the acquisition of a magnetic resonance image can cause blurring and ghosting artifacts in the image. This paper presents a new post-processing strategy that can reduce artifacts due to in-plane, rigid-body motion in times comparable to that required to re-scan a patient. The algorithm iteratively determines unknown patient motion such that corrections for this motion provide the best image quality, as measured by an entropy-related focus criterion. The new optimization strategy features a multi-resolution approach in the phase-encode direction, separate successive one-dimensional searches for rotations and translations, and a novel method requiring only one re-gridding calculation for each rotation angle considered. Applicability to general rigid-body in-plane rotational and translational motion and to a range of differently weighted images and k-space trajectories is demonstrated. Motion artifact reduction is observed for data from a phantom, volunteers, and patients.

Patient motion during the acquisition of a magnetic resonance image can cause blurring and ghosting artifacts in the image. This paper presents a new post-processing strategy that can reduce artifacts due to in-plane, rigid-body motion in times comparable to that required to re-scan a patient. The algorithm iteratively determines unknown patient motion such that corrections for this motion provide the best image quality, as measured by an entropy-related focus criterion. The new optimization strategy features a multi-resolution approach in the phase-encode direction, separate successive one-dimensional searches for rotations and translations, and a novel method requiring only one re-gridding calculation for each rotation angle considered. Applicability to general rigid-body in-plane rotational and translational motion and to a range of differently weighted images and k-space trajectories is demonstrated. Motion artifact reduction is observed for data from a phantom, volunteers, and patients. Magn Reson Med 41:163-170, 1999. © 1999 Wiley-Liss, Inc.

Electrooculogram signal is a well-known physiological metric. Electrooculogram measurements suffer from motion artifact and environmental vibrations. Such artifact are random in nature, may have large dynamic range, and may saturate the overall measurement system output. In this manuscript, we present a single channel, wireless, flexible EOG monitoring system which has capability to reduce motion artifact. The system uses dry non-contact electrodes which makes it mountable with minimal assistance required. The entire EOG system is implemented on a four-layer flexible polyimide substrate, with the EOG acquisition unit on the top layer, noncontact measurement electrodes printed on the bottom layer, circuit ground on the second layer, and active shielding on the third layer. The system uses parallel non-contact electrode pair for EOG signal detection and motion artifact reduction. The battery operated system utilizes only 56 mW of power while using a BLE 5.0 transceiver for wireless EOG data transmission. The system is designed for an effective EOG signal bandwidth of 1 Hz to 40 Hz with an effective signal gain above 35 dB over the signal bandwidth. The capability of the system for motion artifact reduction and EOG detection are experimentally validated. With only 8.75 gram weight the system does not cause any discomfort to the wearer during EOG recording.

We focused on deep learning for a reduction of motion artifacts in MRI. It is difficult to collect a large number of images with and without motion artifacts from clinical images. The purpose of this study was to create motion artifact images in MRI by simulation. We created motion artifact images by computer simulation. First, 20 different types of vertical pixel-shifted images were created with different shifts, and the amount of pixel shift was set from -10 to 10 pixels. The same method was used to create pixel-shifted images for horizontal shift, diagonal shift, and rotational shift, and a total of 80 types of pixel-shifted images were prepared. These images were Fourier transformed to create 80 types of k-space data. Then, phase encodings in these k-space data were randomly sampled and Fourier transformed to create artifact images. The reproducibility of the simulation images was verified using the deep learning network model of U-net. In this study, the evaluation indices used were the structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR). The average SSIM and PSNR for the simulation images were 0.95 and 31.5, respectively; those for the clinical images were 0.96 and 31.1, respectively. Our simulation method enables us to create a large number of artifact images in a short time, equivalent to clinical artifact images.

We proposed a simple technique for reduction of cardiac-related motion artifacts on contrast-enhanced images in the breast by using cylindrical regional-suppression technique (CREST) that can directly suppress the heart signals. The purpose of this study was to select the optimal scan parameters and to evaluate the feasibility in the breast. We demonstrated that the optimized CREST could dramatically reduce the cardiac-related flow artifacts without any penalty to the acquisition time, signal-to-noise ratio and contrast-enhanced lesion-to-parenchyma contrast.

Photoplethysmography (PPG) is a non-invasive and economical technique to extract vital signs of the human body. Although it has been widely used in consumer and research grade wrist devices to track a user's physiology, the PPG signal is very sensitive to motion which can corrupt the signal's quality. Existing Motion Artifact (MA) reduction techniques have been developed and evaluated using either synthetic noisy signals or signals collected during high-intensity activities - both of which are difficult to generalize for real-life scenarios. Therefore, it is valuable to collect realistic PPG signals while performing Activities of Daily Living (ADL) to develop practical signal denoising and analysis methods. In this work, we propose an automatic pseudo clean PPG generation process for reliable PPG signal selection. For each noisy PPG segment, the corresponding pseudo clean PPG reduces the MAs and contains rich temporal details depicting cardiac features. Our experimental results show that 71% of the pseudo clean PPG collected from ADL can be considered as high quality segment where the derived MAE of heart rate and respiration rate are 1.46 BPM and 3.93 BrPM, respectively. Therefore, our proposed method can determine the reliability of the raw noisy PPG by considering quality of the corresponding pseudo clean PPG signal.

Efficacy of periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) for shoulder magnetic resonance (MR) imaging