Automated Detection of Motion Artefacts in MR Imaging Using Decision Forests.
Ontology highlight
ABSTRACT:
SUBMITTER: Lorch B
PROVIDER: S-EPMC5485319 | biostudies-other | 2017
REPOSITORIES: biostudies-other
Similar Datasets
Project description:Good quality of medical images is a prerequisite for the success of subsequent image analysis pipelines. Quality assessment of medical images is therefore an essential activity and for large population studies such as the UK Biobank (UKBB), manual identification of artefacts such as those caused by unanticipated motion is tedious and time-consuming. Therefore, there is an urgent need for automatic image quality assessment techniques. In this paper, we propose a method to automatically detect the presence of motion-related artefacts in cardiac magnetic resonance (CMR) cine images. We compare two deep learning architectures to classify poor quality CMR images: 1) 3D spatio-temporal Convolutional Neural Networks (3D-CNN), 2) Long-term Recurrent Convolutional Network (LRCN). Though in real clinical setup motion artefacts are common, high-quality imaging of UKBB, which comprises cross-sectional population data of volunteers who do not necessarily have health problems creates a highly imbalanced classification problem. Due to the high number of good quality images compared to the relatively low number of images with motion artefacts, we propose a novel data augmentation scheme based on synthetic artefact creation in k-space. We also investigate a learning approach using a predetermined curriculum based on synthetic artefact severity. We evaluate our pipeline on a subset of the UK Biobank data set consisting of 3510 CMR images. The LRCN architecture outperformed the 3D-CNN architecture and was able to detect 2D+time short axis images with motion artefacts in less than 1ms with high recall. We compare our approach to a range of state-of-the-art quality assessment methods. The novel data augmentation and curriculum learning approaches both improved classification performance achieving overall area under the ROC curve of 0.89.
| S-EPMC6688894 | biostudies-literature
Project description:Image quality of positron emission tomography (PET) reconstructions is degraded by subject motion occurring during the acquisition. Magnetic resonance (MR)-based motion correction approaches have been studied for PET/MR scanners and have been successful at capturing regular motion patterns, when used in conjunction with surrogate signals (e.g. navigators) to detect motion. However, handling irregular respiratory motion and bulk motion remains challenging. In this work, we propose an MR-based motion correction method relying on subspace-based real-time MR imaging to estimate motion fields used to correct PET reconstructions. We take advantage of the low-rank characteristics of dynamic MR images to reconstruct high-resolution MR images at high frame rates from highly undersampled k-space data. Reconstructed dynamic MR images are used to determine motion phases for PET reconstruction and estimate phase-to-phase nonrigid motion fields able to capture complex motion patterns such as irregular respiratory and bulk motion. MR-derived binning and motion fields are used for PET reconstruction to generate motion-corrected PET images. The proposed method was evaluated on in vivo data with irregular motion patterns. MR reconstructions accurately captured motion, outperforming state-of-the-art dynamic MR reconstruction techniques. Evaluation of PET reconstructions demonstrated the benefits of the proposed method in terms of motion artifacts reduction, improving the contrast-to-noise ratio by up to a factor 3 and achieveing a target-to-background ratio up to 90% superior compared to standard/uncorrected methods. The proposed method can improve the image quality of motion-corrected PET reconstructions in clinical applications.
| S-EPMC7985095 | biostudies-literature
Project description:Magnetic Resonance Imaging (MRI) provides a unique opportunity to investigate neural changes in healthy and clinical conditions. Its large inherent susceptibility to motion, however, often confounds the measurement. Approaches assessing, correcting, or preventing motion corruption of MRI measurements are under active development, and such efforts can greatly benefit from carefully controlled datasets. We present a unique dataset of structural brain MRI images collected from 148 healthy adults which includes both motion-free and motion-affected data acquired from the same participants. This matched dataset allows direct evaluation of motion artefacts, their impact on derived data, and testing approaches to correct for them. Our dataset further stands out by containing images with different levels of motion artefacts from the same participants, is enriched with expert scoring characterizing the image quality from a clinical point of view and is also complemented with standard image quality metrics obtained from MRIQC. The goal of the dataset is to raise awareness of the issue and provide a useful resource to assess and improve current motion correction approaches.
| S-EPMC9576686 | biostudies-literature
Project description:IntroductionCerebral microbleeds (CMBs) are associated with white matter damage, and various neurodegenerative and cerebrovascular diseases. CMBs occur as small, circular hypointense lesions on T2*-weighted gradient recalled echo (GRE) and susceptibility-weighted imaging (SWI) images, and hyperintense on quantitative susceptibility mapping (QSM) images due to their paramagnetic nature. Accurate automated detection of CMBs would help to determine quantitative imaging biomarkers (e.g., CMB count) on large datasets. In this work, we propose a fully automated, deep learning-based, 3-step algorithm, using structural and anatomical properties of CMBs from any single input image modality (e.g., GRE/SWI/QSM) for their accurate detections.MethodsIn our method, the first step consists of an initial candidate detection step that detects CMBs with high sensitivity. In the second step, candidate discrimination step is performed using a knowledge distillation framework, with a multi-tasking teacher network that guides the student network to classify CMB and non-CMB instances in an offline manner. Finally, a morphological clean-up step further reduces false positives using anatomical constraints. We used four datasets consisting of different modalities specified above, acquired using various protocols and with a variety of pathological and demographic characteristics.ResultsOn cross-validation within datasets, our method achieved a cluster-wise true positive rate (TPR) of over 90% with an average of <2 false positives per subject. The knowledge distillation framework improves the cluster-wise TPR of the student model by 15%. Our method is flexible in terms of the input modality and provides comparable cluster-wise TPR and better cluster-wise precision compared to existing state-of-the-art methods. When evaluating across different datasets, our method showed good generalizability with a cluster-wise TPR >80 % with different modalities. The python implementation of the proposed method is openly available.
| S-EPMC10363739 | biostudies-literature
Project description:Trimodal simultaneous acquisition of positron emission tomography (PET), magnetic resonance imaging (MRI), and electroencephalography (EEG) has become feasible due to the development of hybrid PET-MR scanners. To capture the temporal dynamics of neuronal activation on a millisecond-by-millisecond basis, an EEG system is appended to the quantitative high resolution PET-MR imaging modality already established in our institute. One of the major difficulties associated with the development of simultaneous trimodal acquisition is that the components traditionally used in each modality can cause interferences in its counterpart. The mutual interferences of MRI components and PET components on PET and MR images, and the influence of EEG electrodes on functional MRI images have been studied and reported on. Building on this, this study aims to investigate the influence of the EEG cap on the quality and quantification of PET images acquired during simultaneous PET-MR measurements. A preliminary transmission scan study on the ECAT HR+ scanner, using an Iida phantom, showed visible attenuation effect due to the EEG cap. The BrainPET-MR emission images of the Iida phantom with [18F]Fluordeoxyglucose, as well as of human subjects with the EEG cap, did not show significant effects of the EEG cap, even though the applied attenuation correction did not take into account the attenuation of the EEG cap itself.
| S-EPMC5597218 | biostudies-literature
Project description:Artifacts caused by head motion present a major challenge in brain positron emission tomography (PET) imaging. The authors investigated the feasibility of using wired active MR microcoils to track head motion and incorporate the measured rigid motion fields into iterative PET reconstruction.Several wired active MR microcoils and a dedicated MR coil-tracking sequence were developed. The microcoils were attached to the outer surface of an anthropomorphic(18)F-filled Hoffman phantom to mimic a brain PET scan. Complex rotation/translation motion of the phantom was induced by a balloon, which was connected to a ventilator. PET list-mode and MR tracking data were acquired simultaneously on a PET-MR scanner. The acquired dynamic PET data were reconstructed iteratively with and without motion correction. Additionally, static phantom data were acquired and used as the gold standard.Motion artifacts in PET images were effectively removed by wired active MR microcoil based motion correction. Motion correction yielded an activity concentration bias ranging from -0.6% to 3.4% as compared to a bias ranging from -25.0% to 16.6% if no motion correction was applied. The contrast recovery values were improved by 37%-156% with motion correction as compared to no motion correction. The image correlation (mean ± standard deviation) between the motion corrected (uncorrected) images of 20 independent noise realizations and static reference was R(2) = 0.978 ± 0.007 (0.588 ± 0.010, respectively).Wired active MR microcoil based motion correction significantly improves brain PET quantitative accuracy and image contrast.
| S-EPMC3978416 | biostudies-other
Project description:BackgroundCardiac PET has recently found novel applications in coronary atherosclerosis imaging using [18F]NaF as a radiotracer, highlighting vulnerable plaques. However, the resulting uptakes are relatively small, and cardiac motion and respiration-induced movement of the heart can impair the reconstructed images due to motion blurring and attenuation correction mismatches. This study aimed to apply an MR-based motion compensation framework to [18F]NaF data yielding high-resolution motion-compensated PET and MR images.MethodsFree-breathing 3-dimensional Dixon MR data were acquired, retrospectively binned into multiple respiratory and cardiac motion states, and split into fat and water fraction using a model-based reconstruction framework. From the dynamic MR reconstructions, both a non-rigid cardiorespiratory motion model and a motion-resolved attenuation map were generated and applied to the PET data to improve image quality. The approach was tested in 10 patients and focal tracer hotspots were evaluated concerning their target-to-background ratio, contrast-to-background ratio, and their diameter.ResultsMR-based motion models were successfully applied to compensate for physiological motion in both PET and MR. Target-to-background ratios of identified plaques improved by 7 ± 7%, contrast-to-background ratios by 26 ± 38%, and the plaque diameter decreased by -22 ± 18%. MR-based dynamic attenuation correction strongly reduced attenuation correction artefacts and was not affected by stent-related signal voids in the underlying MR reconstructions.ConclusionsThe MR-based motion correction framework presented here can improve the target-to-background, contrast-to-background, and width of focal tracer hotspots in the coronary system. The dynamic attenuation correction could effectively mitigate the risk of attenuation correction artefacts in the coronaries at the lung-soft tissue boundary. In combination, this could enable a more reproducible and reliable plaque localisation.
| S-EPMC8241750 | biostudies-literature
Project description: Not available
| S-BSST32 | biostudies-other
Project description:Key pointsMotion artefacts associated with motor behaviour are an inevitable problem of multiphoton imaging in awake behaving animals, particularly when imaging synapses. Correction of axial motion artefacts usually requires volumetric imaging resulting in slower rates of acquisition. We describe a method to correct z-motion artefacts that is easy to implement and allows population imaging of synaptic activity while scanning a single plane in a standard multiphoton microscope. The method uses a reference volume acquired in two colour channels - an activity reporter and an anatomical marker of blood vessels. The procedure estimates the z-displacement in every frame and applies an intensity correction in which the z intensity profile for each synapse is modelled as a Moffat function. We demonstrate that the method allows synaptic calcium signals to be collected from populations of synaptic boutons in mouse primary visual cortex during locomotion.AbstractFunctional imaging of head-fixed, behaving mice using two-photon imaging of fluorescent activity reporters has become a powerful tool for studying the function of the brain. Motion artefacts are an inevitable problem during such experiments and are routinely corrected for in x and y dimensions. However, axial (z) shifts of several microns can also occur, leading to intensity fluctuations in structures such as synapses that are small compared to the axial point-spread function of the microscope. Here we present a simple strategy to correct z-motion artefacts arising over the course of a time-series experiment in a single optical plane. Displacement in z was calculated using dye-filled blood vessels as an anatomical marker, providing high contrast images and accuracy to within ∼0.1 µm. The axial profiles of ROIs corresponding to synapses were described using a Moffat function and this 'ROI-spread function' used to correct activity traces on an ROI-by-ROI basis. We demonstrate the accuracy and utility of the procedures in simulation experiments using fluorescent beads and then apply them to correcting measurements of synaptic activity in populations of vasoactive-intestinal peptide (VIP) interneurons expressing the synaptic reporter SyGCaMP6f. Correction of z-motion artefacts had a substantial impact on the apparent correlation between synaptic activity and running speed, demonstrating the importance of correcting these when performing imaging experiments in awake mice.
| S-EPMC7318612 | biostudies-literature
Project description:ObjectivesTo determine the potential of intravoxel incoherent motion (IVIM) MR imaging for staging of hepatic fibrosis (HF).MethodsWe searched PubMed and EMBASE from their inception to 31 July 2015 to select studies reporting IVIM MR imaging and HF staging. We defined F1-2 as non-advanced HF, F3-4 as advanced HF, F0 as normal liver, F1 as very early HF, and F2-4 as significant HF. Then we compared stage F0 with F1, F0-1 with F2-3, and F1-2 with F3-4 using IVIM-derived parameters (pseudo-diffusion coefficient D*, perfusion fraction f, and pure molecular diffusion parameter D). The effect estimate was expressed as a pooled weighted mean difference (WMD) with 95% confidence interval (CI), using the fixed-effects model.ResultsOverall, we included six papers (406 patients) in this study. Significant differences in D* were observed between F0 and F1, F0-1 and F2-3, and F1-2 and F3-4 (WMD 2.46, 95% CI 0.83-4.09, P = 0.006; WMD 13.10, 95% CI 9.53-16.67, P < 0.001; WMD 14.34, 95% CI 10.26-18.42, P < 0.001, respectively). Significant differences in f were also found between F0 and F1, F0-1 and F2-3, and F1-2 and F3-4 (WMD 1.62, 95% CI 0.06-3.18, P = 0.027; WMD 5.63, 95% CI 2.74-8.52, P < 0.001; WMD 3.30, 95% CI 2.10-4.50, P < 0.001, respectively). However, D showed no differences between F0 and F1, F0-1 and F2-3, and F1-2 and F3-4 (WMD 0.05, 95% CI -0.01─0.11, P = 0.105; WMD 0.04, 95% CI -0.01─0.10, P = 0.230; WMD 0.02, 95% CI -0.02─0.06, P = 0.378, respectively).ConclusionsIVIM MR imaging provides an effective method of staging HF and can distinguish early HF from normal liver, significant HF from normal liver or very early HF, and advanced HF from non-advanced HF.
| S-EPMC4731200 | biostudies-literature