Magnetic Resonance Imaging Artifacts Research Articles

Association between dental restorations and artefacts on head magnetic resonance images in paediatric patients.

Magnetic resonance imaging (MRI) has become an important diagnostic tool for paediatric patients. The association between dental restorations and MRI artefacts/distortions, however, is unclear. To investigate the association between dental restorations and artefacts in head MRI in children. This retrospective analysis included patients who underwent head MRI and dental examination at Ramathibodi Hospital from January 2015 to March 2021. From dental records and dental radiographs, a dentist reviewed the amount and type of restorative materials used. Two radiologists examined the MRI scans in five sequences for the presence of distortions and quantified the magnitude and grading of any artefacts. Ninety-four patients aged 3-15 years were included. Twenty-four patients who received preformed metal crowns (PMCs) had MRI distortions. Subjects with no restorations or with tooth-coloured material or amalgam restorations or both did not exhibit distortions. The number of PMCs was related to the size of an artefact. Almost all distortions were confined to the oral cavity and maxillary sinus and did not affect the diagnostic brain area. Among the commonly used dental restorative materials for children, only PMCs were associated with artefacts on head MRI scans.

AI-based motion artifact severity estimation in undersampled MRI allowing for selection of appropriate reconstruction models.

Magnetic Resonance acquisition is a time consuming process, making it susceptible to patient motion during scanning. Even motion in the order of a millimeter can introduce severe blurring and ghosting artifacts, potentially necessitating re-acquisition. Magnetic Resonance Imaging (MRI) can be accelerated by acquiring only a fraction of k-space, combined with advanced reconstruction techniques leveraging coil sensitivity profiles and prior knowledge. Artificial intelligence (AI)-based reconstruction techniques have recently been popularized, but generally assume an ideal setting without intra-scanmotion. To retrospectively detect and quantify the severity of motion artifacts in undersampled MRI data. This may prove valuable as a safety mechanism for AI-based approaches, provide useful information to the reconstruction method, or prompt for re-acquisition while the patient is still in thescanner. We developed a deep learning approach that detects and quantifies motion artifacts in undersampled brain MRI. We demonstrate that synthetically motion-corrupted data can be leveraged to train the convolutional neural network (CNN)-based motion artifact estimator, generalizing well to real-world data. Additionally, we leverage the motion artifact estimator by using it as a selector for a motion-robust reconstruction model in case a considerable amount of motion was detected, and a high data consistency model otherwise. Training and validation were performed on 4387 and 1304 synthetically motion-corrupted images and their uncorrupted counterparts, respectively. Testing was performed on undersampled in vivo motion-corrupted data from 28 volunteers, where our model distinguished head motion from motion-free scans with 91% and 96% accuracy when trained on synthetic and on real data, respectively. It predicted a manually defined quality label ('Good', 'Medium' or 'Bad' quality) correctly in 76% and 85% of the time when trained on synthetic and real data, respectively. When used as a selector it selected the appropriate reconstruction network 93% of the time, achieving near optimal SSIMvalues. The proposed method quantified motion artifact severity in undersampled MRI data with high accuracy, enabling real-time motion artifact detection that can help improve the safety and quality of AI-basedreconstructions.

Radiofrequency interference in magnetic resonance imaging: Identification and rectification.

Radiofrequency (RF) interference artifact is a common type of magnetic resonance imaging (MRI) artifacts caused by the presence of unwanted RF field inside the scanner room. The artifact has the appearance of parallel bright lines or bands that resemble zippers, which can mimic pathology, obstruct the viewing of underlining tissues, and lower image signal-to-noise ratio, affecting the diagnostic evaluation of the image and sometimes even rendering it non-diagnostic. Due to the presence of multiple possible sources of RF interference in MRI and potential nonrelated MRI artifacts that resemble RF interference artifact, it may be difficult to effectively and timely resolve the artifact problem. The objective of this paper is to provide a review of RF interference in MRI and to offer guidance in the prompt and correct identification of the associated image artifacts as well as efficient approaches to resolve and prevent RF interference problems. This article should serve as a useful educational reference to magnetic resonance (MR) technologists and radiologists in dealing with MR image artifacts that may be caused by RF interference.

Reduction of Motion Artifacts in Liver MRI Using Deep Learning with High-pass Filtering

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.

Spinal magnetic resonance imaging artifacts in lumboperitoneal shunt surgery using adjustable valve implantation on the paravertebral spinal muscles.

Adjustable shunt valves that have been developed for managing hydrocephalus rely on intrinsically magnetic components ; thus, artifacts with these valves on magnetic resonance imaging (MRI) are inevitable. No studies on valve-induced artifacts in lumboperitoneal shunt (LPS) surgery have been published. Therefore, this study aimed to evaluate valve-induced artifacts in LPS. We retrospectively reviewed all MRIs obtained between January 2023 and June 2023 in patients with an implanted Codman CERTAS Plus adjustable shunt valve (Integra Life Sciences, Princeton, New Jersey, USA). The valve was placed <1 cm subcutaneously on the paravertebral spinal muscle of the back, with its long axis perpendicular to the body axis. The scans were performed using a Toshiba Medical Systems 1.5 Tesla scanner. The in-plane artifact sizes were assessed as the maximum distance of the artifact from the expected region of the back. All spinal structures or spinal cords can be recognized, even with valve-induced artifacts. The median maximum valve-induced artifact distance on T1-weighted axial imaging was 25.63 mm (mean, 25.98 mm ; range, 22.24-30.94 mm). The median maximum valve-induced artifact distance on T2-weighted axial imaging was 25.56 mm (mean, 26.27 mm ; range, 21.83-29.53 mm). LPS surgery with adjustable valve implantation on paravertebral muscles did not cause valve-induced artifacts in the spine and spinal cord. We considered that LPS could simplify the postoperative care of these patients. J. Med. Invest. 71 : 154-157, February, 2024.

The impact of personal care products on the image quality of Magnetic Resonance Imaging

BackgroundMagnetic Resonance Imaging (MRI) is a crucial diagnostic imaging tool as it has a high contrast resolution for soft tissues. In MRI, the artifact is an unwanted appearance in the image which degrades the image quality and hence hampers the accurate diagnosis of disease. The presence of metallic compounds in several personal care products (PCPs) causes artifacts in MR images. ObjectivesThis study aimed to find the relationship between hair and body (healthcare) products and MRI artifacts. MethodsA total of 22 PCPs (hairs, body, and a few makeup products) were tested utilizing a 1.5 T MRI scanner. The products were filled in a small plastic bag taped to the performance phantom. The phantom was placed in a brain RF coil and scanned using T1-weighted and T2-weighted images. ResultsA total of 16 out of 22 PCPs showed artifacts in the clinical and quantitative analysis, with effects ranging from mild to severe artifacts. ConclusionBased on the quantitative and clinical analysis of personal care products, it can be reported that some hair and body products, as well as cosmetics, can generate visual artifacts. If the artifact is located in the same area of interest as the image, it may degrade the image quality and lead to a medical misdiagnosis.

Spatial Topological Structure Design of Porous Ti-6Al-4V Alloy with Low Modulus and Magnetic Susceptibility.

Ti-6Al-4V alloy is widely used as a biomaterial for hard tissue replacement, but its Young's modulus is still higher than that of human bone tissue, which may cause a "stress shielding" effect and lead to implant loosening. In addition, metal implants with low magnetic susceptibility are beneficial for obtaining minimal artifacts in magnetic resonance imaging. To reduce Young's modulus and magnetic susceptibility of Ti-6Al-4V alloy, a series of irregular prismatic porous structure models were designed based on the Voronoi principle, built by changing the irregularity, prism-diameter-to-initial-seed-spacing ratio, and seed number, and studied using finite-element analysis. Porous samples were prepared by selective laser melting and subjected to a compression test and magnetic susceptibility test. The simulation results show that the prism-diameter-to-initial-seed-spacing ratio has the greatest impact on porosity compared with the irregularity and seed number. The simulation-predicted porosity and compression modulus are highly consistent with the measured ones. The irregular prismatic porous Ti-6Al-4V samples exhibit mechanical properties similar to those of human bones and show a magnetic susceptibility of no more than 50% that of compact Ti-6Al-4V. A regulatable irregular prismatic porous structure is feasible for designing porous implants with desirable properties for biomedical applications.

Deep learning, data ramping, and uncertainty estimation for detecting artifacts in large, imbalanced databases of MRI images.

Magnetic resonance imaging (MRI) is increasingly being used to delineate morphological changes underlying neurological disorders. Successfully detecting these changes depends on the MRI data quality. Unfortunately, image artifacts frequently compromise the MRI utility, making it critical to screen the data. Currently, quality assessment requires visual inspection, a time-consuming process that suffers from inter-rater variability. Automated methods to detect MRI artifacts could improve the efficiency of the process. Such automated methods have achieved high accuracy using small datasets, with balanced proportions of MRI data with and without artifacts. With the current trend towards big data in neuroimaging, there is a need for automated methods that achieve accurate detection in large and imbalanced datasets. Deep learning (DL) is the ideal MRI artifact detection algorithm for large neuroimaging databases. However, the inference generated by DL does not commonly include a measure of uncertainty. Here, we present the first stochastic DL algorithm to generate automated, high-performing MRI artifact detection implemented on a large and imbalanced neuroimaging database. We implemented Monte Carlo dropout in a 3D AlexNet to generate probabilities and epistemic uncertainties. We then developed a method to handle class imbalance, namely data-ramping to transfer the learning by extending the dataset size and the proportion of the artifact-free data instances. We used a 34,800 scans (98% clean) dataset. At baseline, we obtained 89.3% testing accuracy (F1 = 0.230). Following the transfer learning (with data-ramping), we obtained 94.9% testing accuracy (F1 = 0.357) outperforming focal cross-entropy (92.9% testing accuracy, F1 = 0.304) incorporated for comparison at handling class imbalance. By implementing epistemic uncertainties, we improved the testing accuracy to 99.5% (F1 = 0.834), outperforming the results obtained in previous comparable studies. In addition, we estimated aleatoric uncertainties by incorporating random flips to the MRI volumes, and demonstrated that aleatoric uncertainty can be implemented as part of the pipeline. The methods we introduce enhance the efficiency of managing large databases and the exclusion of artifact images from big data analyses.

Sophisticated Study of Time, Frequency and Statistical Analysis for Gradient-Switching-Induced Potentials during MRI.

Magnetic resonance imaging (MRI) is a standard procedure in medical imaging, on a par with echography and tomodensitometry. In contrast to radiological procedures, no harmful radiation is produced. The constant development of magnetic resonance imaging (MRI) techniques has enabled the production of higher resolution images. The switching of magnetic field gradients for MRI imaging generates induced voltages that strongly interfere with the electrophysiological signals (EPs) collected simultaneously. When the bandwidth of the collection amplifiers is higher than 150 Hz, these induced voltages are difficult to eliminate. Understanding the behavior of these artefacts contributes to the development of new digital processing tools for better quality EPs. In this paper, we present a study of induced voltages collected in vitro using a device (350 Hz bandwidth). The experiments were conducted on a 1.5T MRI machine with two MRI sequences (fast spin echo (FSE) and cine gradient echo (CINE)) and three slice orientations. The recorded induced voltages were then segmented into extract patterns called "artefact puffs". Two analysis series, "global" and "local", were then performed. The study found that the temporal and frequency characteristics were specific to the sequences and orientations of the slice and that, despite the pseudo-periodic character of the artefacts, the variabilities within the same recording were significant. These evolutions were confirmed by two stationarity tests: the Kwiatkowski-Phillips-Schmidt-Shin (KPSS) and the time-frequency approach. The induced potentials, all stationary at the global scale, are no longer stationary at the local scale, which is an important issue in the design of optimal filters adapted to reduce MRI artifacts contaminating a large bandwidth, which varies between 0 and 500 Hz.

Quantification of MRI Artifacts in Carbon Fiber Reinforced Polyetheretherketone Thoracolumbar Pedicle Screw Constructs prior to Spinal Stereotactic Radiosurgery

Carbon fiber reinforced polyetheretherketone (CFRP) is a nonmetallic material that is a subject of growing interest in the field of spinal instrumentation manufacturing. The radiolucency and low magnetic susceptibility of CFRP has potential to create less interference with diagnostic imaging compared with titanium implants. However, an objective comparison of the image artifact produced by titanium and CFRP implants has not been described. Spinal oncology, particularly after resection of spinal tumors and at the time of spinal stereotactic radiosurgery planning, relies heavily on imaging interpretation for evaluating resection, adjuvant treatment planning, and surveillance. We present a study comparing measurements of postoperative magnetic resonance imaging artifacts between titanium and CFRP pedicle screw constructs in the setting of separation surgery for metastatic disease. The diameter of the signal drop around the screws (pedicle screw artifact) and the diameter of the spinal canal free from artifacts (canal visualization) were measured in consecutive patients who had spinal instrumentation followed by spinal stereotactic radiosurgery in the June 2019 to May 2022 timeframe. The spinal cord presented a shift at the screw level in sagittal images which was also measured (Sagittal Distortion, SagD). Fifty patients, corresponding to 356 screws and 183 vertebral levels, were evaluated overall. CFRP produced less artifacts in all the 3 parameters compared with titanium: mean pedicle screw artifact (CFRP = 5.8 mm, Ti = 13.2 mm), canal visualization (CFRP = 19.2 mm, Ti = 15.5 mm), and SagD (CFRP = .5 mm, Ti = 1.9 mm), all P < .001. In practice, these findings translate into better-quality magnetic resonance imaging. The initial perceived advantages are easier evaluation of postoperative imaging, facilitating radiation treatment planning, recurrence detection, and avoidance in repeating a suboptimal computed tomography myelogram. Further clinical studies analyzing long-term outcomes of patients treated with CFRP implants are necessary.

White Matter Tract Density Index Prediction Model of Overall Survival in Glioblastoma

The prognosis of overall survival (OS) in patients with glioblastoma (GBM) may depend on the underlying structural connectivity of the brain. To examine the association between white matter tracts affected by GBM and patients' OS by means of a new tract density index (TDI). This prognostic study in patients with a histopathologic diagnosis of GBM examined a discovery cohort of 112 patients who underwent surgery between February 1, 2015, and November 30, 2020 (follow-up to May 31, 2023), in Italy and 70 patients in a replicative cohort (n = 70) who underwent surgery between September 1, 2012, and November 30, 2015 (follow-up to May 31, 2023), in Germany. Statistical analyses were performed from June 1, 2021, to May 31, 2023. Thirteen and 12 patients were excluded from the discovery and the replicative sets, respectively, because of magnetic resonance imaging artifacts. The density of white matter tracts encompassing GBM. Correlation, linear regression, Cox proportional hazards regression, Kaplan-Meier, and prediction analysis were used to assess the association between the TDI and OS. Results were compared with common prognostic factors of GBM, including age, performance status, O6-methylguanine-DNA methyltransferase methylation, and extent of surgery. In the discovery cohort (n = 99; mean [SD] age, 62.2 [11.5] years; 29 female [29.3%]; 70 male [70.7%]), the TDI was significantly correlated with OS (r = -0.34; P < .001). This association was more stable compared with other prognostic factors. The TDI showed a significant regression pattern (Cox: hazard ratio, 0.28 [95% CI, 0.02-0.55; P = .04]; linear: t = -2.366; P = .02). and a significant Kaplan-Meier stratification of patients as having lower or higher OS based on the TDI (log-rank test = 4.52; P = .03). Results were confirmed in the replicative cohort (n = 58; mean [SD] age, 58.5 [11.1] years, 14 female [24.1%]; 44 male [75.9%]). High (24-month cutoff) and low (18-month cutoff) OS was predicted based on the TDI computed in the discovery cohort (accuracy = 87%). In this study, GBMs encompassing regions with low white matter tract density were associated with longer OS. These findings indicate that the TDI is a reliable presurgical outcome predictor that may be considered in clinical trials and clinical practice. These findings support a framework in which the outcome of GBM depends on the patient's brain organization.

Prevalence and influencing factors for artifact development in breast MRI-derived maximum intensity projections.

Magnetic resonance imaging (MRI) provides high diagnostic sensitivity for breast cancer. However, MRI artifacts may impede the diagnostic assessment. This is particularly important when evaluating maximum intensity projections (MIPs), such as in abbreviated MRI (AB-MRI) protocols, because high image quality is desired as a result of fewer sequences being available to compensate for problems. To describe the prevalence of artifacts on dynamic contrast enhanced (DCE) MRI-derived MIPs and to investigate potentially associated attributes. For this institutional review board approved retrospective analysis, MIPs were generated from subtraction series and cropped to represent the left and right breasts as regions of interest. These images were labeled by three independent raters regarding the presence of MRI artifacts. MRI artifact prevalence and associations with patient characteristics and technical attributes were analyzed using descriptive statistics and generalized linear models (GLMMs). The study included 2524 examinations from 1794 patients (median age 50 years), performed on 1.5 and 3.0 Tesla MRI systems. Overall inter-rater agreement was kappa = 0.54. Prevalence of significant unilateral artifacts was 29.2% (736/2524), whereas bilateral artifacts were present in 37.8% (953/2524) of all examinations. According to the GLMM, artifacts were significantly positive associated with age (odds ratio [OR]=1.52) and magnetic field strength (OR=1.55), whereas a negative effect could be shown for body mass index (OR=0.95). MRI artifacts on DCE subtraction MIPs of the breast, as used in AB-MRI, are a relevant topic. Our results show that, besides the magnetic field strength, further associated attributes are patient age and body mass index, which can provide possible targets for artifact reduction.

Evaluation of Artifact Appearance and Burden in Pediatric Brain Tumor MR Imaging with Compressed Sensing in Comparison to Conventional Parallel Imaging Acceleration.

Clinical magnetic resonance imaging (MRI) aims for the highest possible image quality, while balancing the need for acceptable examination time, reasonable signal-to-noise ratio (SNR), and lowest artifact burden. With a recently introduced imaging acceleration technique, compressed sensing, the acquisition speed and image quality of pediatric brain tumor exams can be improved. However, little attention has been paid to its impact on method-related artifacts in pediatric brain MRI. This study assessed the overall artifact burden and artifact appearances in a standardized pediatric brain tumor MRI by comparing conventional parallel imaging acceleration with compressed sensing. This showed that compressed sensing resulted in fewer physiological artifacts in the FLAIR sequence, and a reduction in technical artifacts in the 3D T1 TFE sequences. Only a slight difference was noted in the T2 TSE sequence. A relatively new range of artifacts, which are likely technique-related, was noted in the 3D T1 TFE sequences. In conclusion, by equipping a basic pediatric brain tumor protocol for 3T MRI with compressed sensing, the overall burden of common artifacts can be reduced. However, attention should be paid to novel compressed-sensing-specific artifacts.

Artifacts in magnetic resonance imaging of the head and neck: Unwanted effects caused by implant-supported restorations fabricated with different alloys

Implant-supported restorations may cause artifacts in magnetic resonance imaging (MRI) of the head and neck area. However, the effect of different alloys remains unclear. The purpose of this in vitro study was to assess artifacts in head and neck MRI caused by implant-supported restorations with different alloys. Three dry mandibles were prepared to receive bilateral dental implants at the second premolar and second molar sites. Different alloy combinations were evaluated: titanium implants+cobalt chromium restorations; titanium-zirconium implants+cobalt chromium restorations; and zirconia implants+ceramic restorations. Specimens were imaged by using a 3-Tesla magnetic resonance scanner system (Achieva 3.0T TX; Philips GmbH) with a turbo-spin-echo sequence. Scan protocols were adjusted to optimize metal artifact reduction and shorten scan time. Artifact volumes were assessed and statistically analyzed by using the Kruskal-Wallis and Spearman tests (α=.05). A statistically significant difference was found among artifact volume caused by different materials (P=.002). The presence of titanium alloy was correlated with the artifact volume (r=-.87). Artifacts were greater for titanium and fewer for titanium-zirconium alloys, whereas zirconia implants found only minimal artifacts. The dimension of artifacts produced by implant-supported restorations varied according to the material.

Unsupervised dual-domain disentangled network for removal of rigid motion artifacts in MRI

Motion artifacts in magnetic resonance imaging (MRI) have always been a serious issue because they can affect subsequent diagnosis and treatment. Supervised deep learning methods have been investigated for the removal of motion artifacts; however, they require paired data that are difficult to obtain in clinical settings. Although unsupervised methods are widely proposed to fully use clinical unpaired data, they generally focus on anatomical structures generated by the spatial domain while ignoring phase error (deviations or inaccuracies in phase information that are possibly caused by rigid motion artifacts during image acquisition) provided by the frequency domain. In this study, a 2D unsupervised deep learning method named unsupervised disentangled dual-domain network (UDDN) was proposed to effectively disentangle and remove unwanted rigid motion artifacts from images. In UDDN, a dual-domain encoding module was presented to capture different types of information from the spatial and frequency domains to enrich the information. Moreover, a cross-domain attention fusion module was proposed to effectively fuse information from different domains, reduce information redundancy, and improve the performance of motion artifact removal. UDDN was validated on a publicly available dataset and a clinical dataset. Qualitative and quantitative experimental results showed that our method could effectively remove motion artifacts and reconstruct image details. Moreover, the performance of UDDN surpasses that of several state-of-the-art unsupervised methods and is comparable with that of the supervised method. Therefore, our method has great potential for clinical application in MRI, such as real-time removal of rigid motion artifacts.

Magnetic Resonance Imaging Artifact Associated With Transcutaneous Bone Conduction Implants: Cholesteatoma and Vestibular Schwannoma Surveillance.

To evaluate the magnetic resonance (MR) image artifact and image distortion associated with the two transcutaneous bone conduction implants currently available in the United States. Cadaveric study. Two cadaveric head specimens (1 male, 1 female) were unilaterally implanted according to manufacturer guidelines and underwent MR imaging (General Electric and Siemens 1.5 T scanners) under the following device conditions: (1) no device, (2) Cochlear Osia with magnet and headwrap, (3) Cochlear Osia without magnet, and (4) MED-EL Bonebridge with magnet. Maximum metal mitigation techniques were employed in all conditions, and identical sequences were obtained. Blinded image scoring (diagnostic vs nondiagnostic image) was performed by experienced neuroradiologists according to anatomical subsites. All device conditions produced artifact and image distortion. The Osia with magnet produced diagnostic T1- and T2-weighted images of the ipsilateral temporal bone, however, non-echo planar imaging diffusion-weighted imaging (DWI) was nondiagnostic. The Osia without magnet scanned on the Siemens MR imaging demonstrated the least amount of artifact and was the only condition that allowed for diagnostic imaging of the ipsilateral temporal bone on DWI. The Bonebridge produced a large area of artifact and distortion with the involvement of the ipsilateral and contralateral temporal bones. In summary, of the three device conditions (Osia with magnet, Osia without magnet, and Bonebridge), Osia without magnet offered the least amount of artifact and distortion and was the only condition in which diagnostic DWI was available for the middle ear and mastoid regions on the Siemens MR imaging scanner.

Automatic brain MRI motion artifact detection based on end-to-end deep learning is similarly effective as traditional machine learning trained on image quality metrics.

Head motion artifacts in magnetic resonance imaging (MRI) are an important confounding factor concerning brain research as well as clinical practice. For this reason, several machine learning-based methods have been developed for the automatic quality control of structural MRI scans. Deep learning offers a promising solution to this problem, however, given its data-hungry nature and the scarcity of expert-annotated datasets, its advantage over traditional machine learning methods in identifying motion-corrupted brain scans is yet to be determined. In the present study, we investigated the relative advantage of the two methods in structural MRI quality control. To this end, we collected publicly available T1-weighted images and scanned subjects in our own lab under conventional and active head motion conditions. The quality of the images was rated by a team of radiologists from the point of view of clinical diagnostic use. We present a relatively simple, lightweight 3D convolutional neural network trained in an end-to-end manner that achieved a test set (N=411) balanced accuracy of 94.41% in classifying brain scans into clinically usable or unusable categories. A support vector machine trained on image quality metrics achieved a balanced accuracy of 88.44% on the same test set. Statistical comparison of the two models yielded no significant difference in terms of confusion matrices, error rates, or receiver operating characteristic curves. Our results suggest that these machine learning methods are similarly effective in identifying severe motion artifacts in brain MRI scans, and underline the efficacy of end-to-end deep learning-based systems in brain MRI quality control, allowing the rapid evaluation of diagnostic utility without the need for elaborate image pre-processing.

Magnetic Resonance Safety Evaluation of a Novel Alumina Matrix Composite Ceramic Knee and Image Artifact Comparison to a Metal Knee Implant of Analogous Design.

Image artifacts caused by metal knee implants in 1.5T and 3T magnetic resonance imaging (MRI) systems complicate imaging-based diagnosis of the peri-implant region after total knee arthroplasty. Alternatively, metal-free knee prostheses could effectively minimize MRI safety hazards and offer the potential for higher quality diagnostic images. A novel knee arthroplasty device composed of BIOLOX delta, an alumina matrix composite (AMC) ceramic, was tested in a magnetic resonance (MR) environment. American Society for Testing and Materials test methods were used for evaluating magnetically induced displacement force, magnetically induced torque, radiofrequency-induced heating, and MR image artifact. Magnetically induced displacement force and magnetically induced torque results of the AMC ceramic knee indicated that these effects do not pose a known risk in a clinical MR environment, as assessed in a 3T magnetic field. Moreover, minimal radiofrequency-induced heating of the device was observed. In addition, the AMC ceramic knee demonstrated minimal MR image artifacts (7 mm) in comparison to a cobalt-chromium knee (88 mm). The extremely low magnetic susceptibility of AMC (2 ppm) underlines that it is a nonmetallic and nonmagnetic material well suited for the manufacturing of MR Safe orthopaedic implants. The AMC ceramic knee is a novel metal-free total knee arthroplasty device that can be regarded as MR Safe, as suggested by the absence of hazards from the exposure of this implant to a MR environment. The AMC ceramic knee presents the advantage of being scanned with superior imaging results in 3T MRI systems compared to alternative metal implants on the market.

Ventriculoperitoneal shunt with the valve placed on the chest wall using a fixation technique that uses titanium screws for securing the reservoir to the cranium

BackgroundThe adjustable shunt valves of ventriculoperitoneal shunts (VPS) produce magnetic artifacts, which could disturb magnetic resonance imaging (MRI), and should therefore be placed on the chest wall. However, some significant complications, including ventricular catheter migration, disconnection, and rupture, should be considered. This study proposed a novel method for VPS placement with the valve placed on the chest wall using a fixation technique that uses titanium screws for securing the reservoir to the cranium. MethodsAfter a right-angled ventricular catheter with reservoir was inserted into the lateral ventricle, a 4-mm self-tapping titanium screw was inserted directly through the collars of the reservoir to fix it to the cranium. Adjustable shunt valves were implanted in the infraclavicular fossa of the chest wall. The connection site between the valve and tube was fastened using 3–0 nonabsorbable braided nylon surgical sutures. ResultsIn this study, following VPS placement in 83 patients with normal-pressure hydrocephalus, the review of all postprocedural images showed that of the 83 patients, four patients (4.8%) had catheter placement complications: two patients (2.4%) had incorrect placement of the ventricular catheter and two patients (2.4%) had subcutaneous migration of the abdominal catheter. None of the patients complained of ventricular catheter migration, disconnection, or rupture. ConclusionIn adult patients, placing the VPS valve in the chest and fixing the proximal catheter to the cranium using surgical screws can be an effective way to avoid MRI artifacts and to counteract mechanical failure due to the dislodgment of the proximal catheter.

Image quality assessment using deep learning in high b-value diffusion-weighted breast MRI

The objective of this IRB approved retrospective study was to apply deep learning to identify magnetic resonance imaging (MRI) artifacts on maximum intensity projections (MIP) of the breast, which were derived from diffusion weighted imaging (DWI) protocols. The dataset consisted of 1309 clinically indicated breast MRI examinations of 1158 individuals (median age [IQR]: 50 years [16.75 years]) acquired between March 2017 and June 2020, in which a DWI sequence with a high b-value equal to 1500 s/mm2 was acquired. From these, 2D MIP images were computed and the left and right breast were cropped out as regions of interest (ROI). The presence of MRI image artifacts on the ROIs was rated by three independent observers. Artifact prevalence in the dataset was 37% (961 out of 2618 images). A DenseNet was trained with a fivefold cross-validation to identify artifacts on these images. In an independent holdout test dataset (n = 350 images) artifacts were detected by the neural network with an area under the precision-recall curve of 0.921 and a positive predictive value of 0.981. Our results show that a deep learning algorithm is capable to identify MRI artifacts in breast DWI-derived MIPs, which could help to improve quality assurance approaches for DWI sequences of breast examinations in the future.