Artifacts in body MR imaging: their appearance and how to eliminate them

AI in motion: the impact of data augmentation strategies on mitigating MRI motion artifacts

OBJECTIVES

Artifacts in clinical MRI can compromise the performance of AI models. This study evaluates how different data augmentation strategies affect an AI model's segmentation performance under variable artifact severity.

MATERIALS AND METHODS

We used an AI model based on the nnU-Net architecture to automatically quantify lower limb alignment using axial T2-weighted MR images. Three versions of the AI model were trained with different augmentation strategies: (1) no augmentation ("baseline"), (2) standard nnU-net augmentations ("default"), and (3) "default" plus augmentations that emulate MR artifacts ("MRI-specific"). Model performance was tested on 600 MR image stacks (right and left; hip, knee, and ankle) from 20 healthy participants (mean age, 23 ± 3 years, 17 men), each imaged five times under standardized motion to induce artifacts. Two radiologists graded each stack's artifact severity as none, mild, moderate, and severe, and manually measured torsional angles. Segmentation quality was assessed using the Dice similarity coefficient (DSC), while torsional angles were compared between manual and automatic measurements using mean absolute deviation (MAD), intraclass correlation coefficient (ICC), and Pearson's correlation coefficient (r). Statistical analysis included parametric tests and a Linear Mixed-Effects Model.

RESULTS

MRI-specific augmentation resulted in slightly (yet not significantly) better performance than the default strategy. Segmentation quality decreased with increasing artifact severity, which was partially mitigated by default and MRI-specific augmentations (e.g., severe artifacts, proximal femur: DSCbaseline = 0.58 ± 0.22; DSCdefault = 0.72 ± 0.22; DSCMRI-specific = 0.79 ± 0.14 [p < 0.001]). These augmentations also maintained precise torsional angle measurements (e.g., severe artifacts, femoral torsion: MADbaseline = 20.6 ± 23.5°; MADdefault = 7.0 ± 13.0°; MADMRI-specific = 5.7 ± 9.5° [p < 0.001]; ICCbaseline = -0.10 [p = 0.63; 95% CI: -0.61 to 0.47]; ICCdefault = 0.38 [p = 0.08; -0.17 to 0.76]; ICCMRI-specific = 0.86 [p < 0.001; 0.62 to 0.95]; rbaseline = 0.58 [p < 0.001; 0.44 to 0.69]; rdefault = 0.68 [p < 0.001; 0.56 to 0.77]; rMRI-specific = 0.86 [p < 0.001; 0.81 to 0.9]).

CONCLUSION

Motion artifacts negatively impact AI models, but general-purpose augmentations enhance robustness effectively. MRI-specific augmentations offer minimal additional benefit.

KEY POINTS

Question Motion artifacts negatively impact the performance of diagnostic AI models for MRI, but mitigation methods remain largely unexplored. Findings Domain-specific augmentation during training can improve the robustness and performance of a model for quantifying lower limb alignment in the presence of severe artifacts. Clinical relevance Excellent robustness and accuracy are crucial for deploying diagnostic AI models in clinical practice. Including domain knowledge in model training can benefit clinical adoption.

Advancements in Medical Radiology Through Multimodal Machine Learning: A Comprehensive Overview

The majority of data collected and obtained from various sources over a patient's lifetime can be assumed to comprise pertinent information for delivering the best possible treatment. Medical data, such as radiographic and histopathology images, electrocardiograms, and medical records, all guide a physician's diagnostic approach. Nevertheless, most machine learning techniques in the healthcare field emphasize data analysis from a single modality, which is insufficiently reliable. This is especially evident in radiology, which has long been an essential topic of machine learning in healthcare because of its high data density, availability, and interpretation capability. In the future, computer-assisted diagnostic systems must be intelligent to process a variety of data simultaneously, similar to how doctors examine various resources while diagnosing patients. By extracting novel characteristics from diverse medical data sources, advanced identification techniques known as multimodal learning may be applied, enabling algorithms to analyze data from various sources and eliminating the need to train each modality. This approach enhances the flexibility of algorithms by incorporating diverse data. A growing quantity of current research has focused on the exploration of extracting data from multiple sources and constructing precise multimodal machine/deep learning models for medical examinations. A comprehensive analysis and synthesis of recent publications focusing on multimodal machine learning in detecting diseases is provided. Potential future research directions are also identified. This review presents an overview of multimodal machine learning (MMML) in radiology, a field at the cutting edge of integrating artificial intelligence into medical imaging. As radiological practices continue to evolve, the combination of various imaging and non-imaging data modalities is gaining increasing significance. This paper analyzes current methodologies, applications, and trends in MMML while outlining challenges and predicting upcoming research directions. Beginning with an overview of the different data modalities involved in radiology, namely, imaging, text, and structured medical data, this review explains the processes of modality fusion, representation learning, and modality translation, showing how they boost diagnosis efficacy and improve patient care. Additionally, this review discusses key datasets that have been instrumental in advancing MMML research. This review may help clinicians and researchers comprehend the spatial distribution of the field, outline the current level of advancement, and identify areas of research that need to be explored regarding MMML in radiology.

Non-contrast-enhanced MR-angiography of the abdominal arteries: intraindividual comparison between relaxation-enhanced angiography without contrast and triggering (REACT) and 4D contrast-enhanced MR-angiography

PURPOSE

To evaluate Relaxation-Enhanced Angiography without Contrast and Triggering (REACT), a novel 3D isotropic flow-independent non-contrast-enhanced magnetic resonance angiography (non-CE-MRA) for imaging of the abdominal arteries, by comparing image quality and assessment of vessel stenosis intraindidually with 4D CE-MRA.

METHODS

Thirty patients (mean age 35.7 ± 16.8 years; 20 females) referred for the assessment of the arterial abdominal vasculature at 3 T were included in this retrospective, single-centre study. The protocol comprised both 4D CE-MRA and REACT (navigator-triggering, Compressed SENSE factor 10, nominal scan time 02:54 min, and reconstructed voxel size 0.78 × 0.78 × 0.85  mm3). Two radiologists independently evaluated 14 abdominal artery segments for stenoses, anatomical variants, and vascular findings (aortic dissection, abdominal aorta aneurysms and its branches). Subjective image quality was assessed using a 4-point Likert scale (1 = non-diagnostic, 4 = excellent).

RESULTS

REACT had a total acquisition time of 5:36 ± 00:40 min, while 4D CE-MRA showed a total acquisition time (including the native scan and bolus tracking sequence) of 3:45 ± 00:59 min (p = 0.001). Considering 4D CE-MRA as the reference standard, REACT achieved a sensitivity of 87.5% and specificity of 100.0% for relevant (≥ 50%) stenosis while detecting 89.5% of all vascular findings other than stenosis. For all vessels combined, subjective vessel quality was slightly higher in 4D CE-MRA (3.0 [IQR: 2.0; 4.0.]; P = 0.040), although comparable to REACT (3.0 [IQR: 2.0; 3.5]).

CONCLUSION

In a short scan time of about 5 min, REACT provides good diagnostic performance for detection of relevant stenoses, variants, and vascular findings of the abdominal arteries, while yielding to 4D CE-MRA comparable image quality.

Deep Learning Reconstruction of Prospectively Accelerated MRI of the Pancreas: Clinical Evaluation of Shortened Breath-Hold Examinations With Dixon Fat Suppression

OBJECTIVE

Deep learning (DL)-enabled magnetic resonance imaging (MRI) reconstructions can enable shortening of breath-hold examinations and improve image quality by reducing motion artifacts. Prospective studies with DL reconstructions of accelerated MRI of the upper abdomen in the context of pancreatic pathologies are lacking. In a clinical setting, the purpose of this study is to investigate the performance of a novel DL-based reconstruction algorithm in T1-weighted volumetric interpolated breath-hold examinations with partial Fourier sampling and Dixon fat suppression (hereafter, VIBE-Dixon DL ). The objective is to analyze its impact on acquisition time, image sharpness and quality, diagnostic confidence, pancreatic lesion conspicuity, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR).

METHODS

This prospective single-center study included participants with various pancreatic pathologies who gave written consent from January 2023 to September 2023. During the same session, each participant underwent 2 MRI acquisitions using a 1.5 T scanner: conventional precontrast and postcontrast T1-weighted VIBE acquisitions with Dixon fat suppression (VIBE-Dixon, reference standard) using 4-fold parallel imaging acceleration and 6-fold accelerated VIBE-Dixon acquisitions with partial Fourier sampling utilizing a novel DL reconstruction tailored to the acquisition. A qualitative image analysis was performed by 4 readers. Acquisition time, image sharpness, overall image quality, image noise and artifacts, diagnostic confidence, as well as pancreatic lesion conspicuity and size were compared. Furthermore, a quantitative analysis of SNR and CNR was performed.

RESULTS

Thirty-two participants were evaluated (mean age ± SD, 62 ± 19 years; 20 men). The VIBE-Dixon DL method enabled up to 52% reduction in average breath-hold time (7 seconds for VIBE-Dixon DL vs 15 seconds for VIBE-Dixon, P < 0.001). A significant improvement of image sharpness, overall image quality, diagnostic confidence, and pancreatic lesion conspicuity was observed in the images recorded using VIBE-Dixon DL ( P < 0.001). Furthermore, a significant reduction of image noise and motion artifacts was noted in the images recorded using the VIBE-Dixon DL technique ( P < 0.001). In addition, for all readers, there was no evidence of a difference in lesion size measurement between VIBE-Dixon and VIBE-Dixon DL . Interreader agreement between VIBE-Dixon and VIBE-Dixon DL regarding lesion size was excellent (intraclass correlation coefficient, >90). Finally, a statistically significant increase of pancreatic SNR in VIBE-DIXON DL was observed in both the precontrast ( P = 0.025) and postcontrast images ( P < 0.001). Also, an increase of splenic SNR in VIBE-DIXON DL was observed in both the precontrast and postcontrast images, but only reaching statistical significance in the postcontrast images ( P = 0.34 and P = 0.003, respectively). Similarly, an increase of pancreas CNR in VIBE-DIXON DL was observed in both the precontrast and postcontrast images, but only reaching statistical significance in the postcontrast images ( P = 0.557 and P = 0.026, respectively).

CONCLUSIONS

The prospectively accelerated, DL-enhanced VIBE with Dixon fat suppression was clinically feasible. It enabled a 52% reduction in breath-hold time and provided superior image quality, diagnostic confidence, and pancreatic lesion conspicuity. This technique might be especially useful for patients with limited breath-hold capacity.

Similarity and quality metrics for MR image-to-image translation

Image-to-image translation can create large impact in medical imaging, as images can be synthetically transformed to other modalities, sequence types, higher resolutions or lower noise levels. To ensure patient safety, these methods should be validated by human readers, which requires a considerable amount of time and costs. Quantitative metrics can effectively complement such studies and provide reproducible and objective assessment of synthetic images. If a reference is available, the similarity of MR images is frequently evaluated by SSIM and PSNR metrics, even though these metrics are not or too sensitive regarding specific distortions. When reference images to compare with are not available, non-reference quality metrics can reliably detect specific distortions, such as blurriness. To provide an overview on distortion sensitivity, we quantitatively analyze 11 similarity (reference) and 12 quality (non-reference) metrics for assessing synthetic images. We additionally include a metric on a downstream segmentation task. We investigate the sensitivity regarding 11 kinds of distortions and typical MR artifacts, and analyze the influence of different normalization methods on each metric and distortion. Finally, we derive recommendations for effective usage of the analyzed similarity and quality metrics for evaluation of image-to-image translation models.

Enhancing repeatability of follicle counting with deep learning reconstruction high-resolution MRI in PCOS patients

Follicle count, a pivotal metric in the adjunct diagnosis of polycystic ovary syndrome (PCOS), is often underestimated when assessed via transvaginal ultrasonography compared to MRI. Nevertheless, the repeatability of follicle counting using traditional MR images is still compromised by motion artifacts or inadequate spatial resolution. In this prospective study involving 22 PCOS patients, we employed periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) and single-shot fast spin-echo (SSFSE) T2-weighted sequences to suppress motion artifacts in high-resolution ovarian MRI. Additionally, deep learning (DL) reconstruction was utilized to compensate noise in SSFSE imaging. We compared the performance of DL reconstruction SSFSE (SSFSE-DL) images with conventional reconstruction SSFSE (SSFSE-C) and PROPELLER images in follicle detection, employing qualitative indices (blurring artifacts, subjective noise, and conspicuity of follicles) and the repeatability of follicle number per ovary (FNPO) assessment. Despite similar subjective noise between SSFSE-DL and PROPELLER as assessed by one observer, SSFSE-DL images outperformed SSFSE-C and PROPELLER images across all three qualitative indices, resulting in enhanced repeatability in FNPO assessment. These results highlighted the potential of DL reconstruction high-resolution SSFSE imaging as a more dependable method for identifying polycystic ovary, thus facilitating more accurate diagnosis of PCOS in future clinical practices.

Comprehensive review of artifacts in cardiac MRI and their mitigation

Cardiac magnetic resonance imaging (CMR) is an important clinical tool that obtains high-quality images for assessment of cardiac morphology, function, and tissue characteristics. However, the technique may be prone to artifacts that may limit the diagnostic interpretation of images. This article reviews common artifacts which may appear in CMR exams by describing their appearance, the challenges they mitigate true pathology, and offering possible solutions to reduce their impact. Additionally, this article acts as an update to previous CMR artifacts reports by including discussion about new CMR innovations.

Ultrafast Brain MRI at 3 T for MS: Evaluation of a 51-Second Deep Learning-Enhanced T2-EPI-FLAIR Sequence

In neuroimaging, there is no equivalent alternative to magnetic resonance imaging (MRI). However, image acquisitions are generally time-consuming, which may limit utilization in some cases, e.g., in patients who cannot remain motionless for long or suffer from claustrophobia, or in the event of extensive waiting times. For multiple sclerosis (MS) patients, MRI plays a major role in drug therapy decision-making. The purpose of this study was to evaluate whether an ultrafast, T2-weighted (T2w), deep learning-enhanced (DL), echo-planar-imaging-based (EPI) fluid-attenuated inversion recovery (FLAIR) sequence (FLAIRUF) that has targeted neurological emergencies so far might even be an option to detect MS lesions of the brain compared to conventional FLAIR sequences. Therefore, 17 MS patients were enrolled prospectively in this exploratory study. Standard MRI protocols and ultrafast acquisitions were conducted at 3 tesla (T), including three-dimensional (3D)-FLAIR, turbo/fast spin-echo (TSE)-FLAIR, and FLAIRUF. Inflammatory lesions were grouped by size and location. Lesion conspicuity and image quality were rated on an ordinal five-point Likert scale, and lesion detection rates were calculated. Statistical analyses were performed to compare results. Altogether, 568 different lesions were found. Data indicated no significant differences in lesion detection (sensitivity and positive predictive value [PPV]) between FLAIRUF and axially reconstructed 3D-FLAIR (lesion size ≥3 mm × ≥2 mm) and no differences in sensitivity between FLAIRUF and TSE-FLAIR (lesion size ≥3 mm total). Lesion conspicuity in FLAIRUF was similar in all brain regions except for superior conspicuity in the occipital lobe and inferior conspicuity in the central brain regions. Further findings include location-dependent limitations of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) as well as artifacts such as spatial distortions in FLAIRUF. In conclusion, FLAIRUF could potentially be an expedient alternative to conventional methods for brain imaging in MS patients since the acquisition can be performed in a fraction of time while maintaining good image quality.

MRI super-resolution using similarity distance and multi-scale receptive field based feature fusion GAN and pre-trained slice interpolation network

Challenges arise in achieving high-resolution Magnetic Resonance Imaging (MRI) to improve disease diagnosis accuracy due to limitations in hardware, patient discomfort, long acquisition times, and high costs. While Convolutional Neural Networks (CNNs) have shown promising results in MRI super-resolution, they often don't look into the structural similarity and prior information available in consecutive MRI slices. By leveraging information from sequential slices, more robust features can be obtained, potentially leading to higher-quality MRI slices. We propose a multi-slice two-dimensional (2D) MRI super-resolution network that combines a Generative Adversarial Network (GAN) with feature fusion and a pre-trained slice interpolation network to achieve three-dimensional (3D) super-resolution. The proposed model requires consecutively acquired three low-resolution (LR) MRI slices along a specific axis, and achieves the reconstruction of the MRI slices in the remaining two axes. The network effectively enhances both in-plane and out-of-plane resolution along the sagittal axis while addressing computational and memory constraints in 3D super-resolution. The proposed generator has a in-plane and out-of-plane Attention (IOA) network that fuses both in-plane and out-plane features of MRI dynamically. In terms of out-of-plane attention, the network merges features by considering the similarity distance between features and for in-plane attention, the network employs a two-level pyramid structure with varying receptive fields to extract features at different scales, ensuring the inclusion of both global and local features. Subsequently, to achieve 3D MRI super-resolution, a pre-trained slice interpolation network is used that takes two consecutive super-resolved MRI slices to generate a new intermediate slice. To further enhance the network performance and perceptual quality, we introduce a feature up-sampling layer and a feature extraction block with Scaled Exponential Linear Unit (SeLU). Moreover, our super-resolution network incorporates VGG loss from a fine-tuned VGG-19 network to provide additional enhancement. Through experimental evaluations on the IXI dataset and BRATS dataset, using the peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM) and the number of training parameters, we demonstrate the superior performance of our method compared to the existing techniques. Also, the proposed model can be adapted or modified to achieve super-resolution for both 2D and 3D MRI data.

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

PURPOSE

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.

METHODS

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.

RESULTS

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.

CONCLUSION

The learning model in this study is indicated to be reduced motion artifacts without decreasing the sharpness of liver MR images.

Swin Transformer and the Unet Architecture to Correct Motion Artifacts in Magnetic Resonance Image Reconstruction

We present a deep learning-based method that corrects motion artifacts and thus accelerates data acquisition and reconstruction of magnetic resonance images. The novel model, the Motion Artifact Correction by Swin Network (MACS-Net), uses a Swin transformer layer as the fundamental block and the Unet architecture as the neural network backbone. We employ a hierarchical transformer with shifted windows to extract multiscale contextual features during encoding. A new dual upsampling technique is employed to enhance the spatial resolutions of feature maps in the Swin transformer-based decoder layer. A raw magnetic resonance imaging dataset is used for network training and testing; the data contain various motion artifacts with ground truth images of the same subjects. The results were compared to six state-of-the-art MRI image motion correction methods using two types of motions. When motions were brief (within 5 s), the method reduced the average normalized root mean square error (NRMSE) from 45.25% to 17.51%, increased the mean structural similarity index measure (SSIM) from 79.43% to 91.72%, and increased the peak signal-to-noise ratio (PSNR) from 18.24 to 26.57 dB. Similarly, when motions were extended from 5 to 10 s, our approach decreased the average NRMSE from 60.30% to 21.04%, improved the mean SSIM from 33.86% to 90.33%, and increased the PSNR from 15.64 to 24.99 dB. The anatomical structures of the corrected images and the motion-free brain data were similar.

Cerebrospinal fluid flow artifact reduction with deep learning to optimize the evaluation of spinal canal stenosis on spine MRI

PURPOSE

The aim of study was to employ the Cycle Generative Adversarial Network (CycleGAN) deep learning model to diminish the cerebrospinal fluid (CSF) flow artifacts in cervical spine MRI. We also evaluate the agreement in quantifying spinal canal stenosis.

METHODS

For training model, we collected 9633 axial MR image pairs from 399 subjects. Then, additional 104 image pairs from 19 subjects were gathered for the test set. The deep learning model was developed using CycleGAN to reduce CSF flow artifacts, where T2 TSE images served as input, and T2 FFE images, known for fewer CSF flow artifacts. Post training, CycleGAN-generated images were subjected to both quantitative and qualitative evaluations for CSF artifacts. For assessing the agreement of spinal canal stenosis, four raters utilized an additional 104 pairs of original and CycleGAN-generated images, with inter-rater agreement evaluated using a weighted kappa value.

RESULTS

CSF flow artifacts were reduced in the CycleGAN-generated images compared to the T2 TSE and FFE images in both quantitative and qualitative analysis. All raters concordantly displayed satisfactory estimation results when assessing spinal canal stenosis using the CycleGAN-generated images with T2 TSE images (kappa = 0.61-0.75) compared to the original FFE with T2 TSE images (kappa = 0.48-0.71).

CONCLUSIONS

CycleGAN demonstrated the capability to produce images with diminished CSF flow artifacts. When paired with T2 TSE images, the CycleGAN-generated images allowed for more consistent assessment of spinal canal stenosis and exhibited agreement levels that were comparable to the combination of T2 TSE and FFE images.

Extranodal Extension at Pretreatment MRI and the Prognostic Value for Patients with Rectal Cancer

Background Detection of extranodal extension (ENE) at pathology is a poor prognostic indicator for rectal cancer, but whether ENE can be identified at pretreatment MRI is, to the knowledge of the authors, unknown. Purpose To evaluate the performance of pretreatment MRI in detecting ENE using a matched pathologic reference standard and to assess its prognostic value in patients with rectal cancer. Materials and Methods This single-center study included a prospective development data set consisting of participants with rectal adenocarcinoma who underwent pretreatment MRI and radical surgery (December 2021 to January 2023). MRI characteristics were identified by their association with ENE-positive nodes (χ2 test and multivariable logistic regression) and the performance of these MRI features was assessed (area under the receiver operating characteristic curve [AUC]). Interobserver agreement was assessed by Cohen κ coefficient. The prognostic value of ENE detected with MRI for predicting 3-year disease-free survival was assessed by Cox regression analysis in a retrospective independent validation cohort of patients with locally advanced rectal cancer (December 2019 to July 2020). Results The development data set included 147 participants (mean age, 62 years ± 11 [SD]; 87 male participants). The retrospective cohort included 110 patients (mean age, 60 years ± 9; 79 male participants). Presence of vessel interruption and fusion (both P < .001), heterogeneous internal structure, and the broken-ring and tail signs (odds ratio range, 4.10-23.20; P value range, <.001 to .002) were predictors of ENE at MRI, and together achieved an AUC of 0.91 (95% CI: 0.88, 0.93) in detecting ENE. Interobserver agreement was moderate for the presence of vessel interruption and fusion (κ = 0.46 for both) and substantial for others (κ = 0.61-0.67). The presence of ENE at pretreatment MRI was independently associated with worse 3-year disease-free survival (hazard ratio, 3.00; P = .02). Conclusion ENE can be detected at pretreatment MRI, and its presence was associated with worse prognosis for patients with rectal cancer. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Eberhardt in this issue.

Retrospective comparison between MRI examinations during radiographer-administered intranasal sedation or general anesthesia

INTRODUCTION

In order for young children to be able to undergo a Magnetic Resonance Imaging (MRI) examination, general anesthesia is often required. The aim of this study was to compare the image quality, times, and costs of the examinations of infant brains performed with MRI either during sedation with dexmedetomidine administered by radiographers or anesthesia with propofol administered by anesthesia staff.

METHODS

This study was a quantitative retrospective study of 27 consecutive standard brain examinations performed under sedation or anesthesia, involving 15 children under sedation and 12 under anesthesia. The age of the children was from 0.5 to five years old. The image quality was evaluated by three radiologists experienced in pediatric MRI examinations. Information such as examination time and the expense of the examination was also collected.

RESULTS

There was no statistically significant difference in the general image quality, but one image series was assessed to have significantly better image quality under sedation than under anesthesia, but all images had very high quality. However, it emerged that children under anesthesia were at the hospital on average 55 min longer and the scanner room was occupied 20 min longer on average. The anesthesia examinations were three times more expensive.

CONCLUSION

This study demonstrated equivalent image quality between sedation and anesthesia. In addition, sedation was less time-consuming and had a lower price, partly because no extra anesthetic staff were required. The use of intranasal sedation offers a possibility to expand the competence area for radiographers.

IMPLICATIONS FOR PRACTICE

If radiographers learn to perform intranasal sedation, examinations can be performed in less time, at a third of the staff costs while maintaining image quality.

Improving explainable AI with patch perturbation-based evaluation pipeline: a COVID-19 X-ray image analysis case study

Recent advances in artificial intelligence (AI) have sparked interest in developing explainable AI (XAI) methods for clinical decision support systems, especially in translational research. Although using XAI methods may enhance trust in black-box models, evaluating their effectiveness has been challenging, primarily due to the absence of human (expert) intervention, additional annotations, and automated strategies. In order to conduct a thorough assessment, we propose a patch perturbation-based approach to automatically evaluate the quality of explanations in medical imaging analysis. To eliminate the need for human efforts in conventional evaluation methods, our approach executes poisoning attacks during model retraining by generating both static and dynamic triggers. We then propose a comprehensive set of evaluation metrics during the model inference stage to facilitate the evaluation from multiple perspectives, covering a wide range of correctness, completeness, consistency, and complexity. In addition, we include an extensive case study to showcase the proposed evaluation strategy by applying widely-used XAI methods on COVID-19 X-ray imaging classification tasks, as well as a thorough review of existing XAI methods in medical imaging analysis with evaluation availability. The proposed patch perturbation-based workflow offers model developers an automated and generalizable evaluation strategy to identify potential pitfalls and optimize their proposed explainable solutions, while also aiding end-users in comparing and selecting appropriate XAI methods that meet specific clinical needs in real-world clinical research and practice.

Body and Extremity MR Venography: Technique, Clinical Applications, and Advances

Magnetic resonance venography (MRV) represents a distinct imaging approach that may be used to evaluate a wide spectrum of venous pathology. Despite duplex ultrasound and computed tomography venography representing the dominant imaging modalities in investigating suspected venous disease, MRV is increasingly used due to its lack of ionizing radiation, unique ability to be performed without administration of intravenous contrast, and recent technical improvements resulting in improved sensitivity, image quality, and faster acquisition times. In this review, the authors discuss commonly used body and extremity MRV techniques, different clinical applications, and future directions.

A predictive signal model for dynamic cardiac magnetic resonance imaging

Robust dynamic cardiac magnetic resonance imaging (MRI) has been a long-standing endeavor-as real-time imaging can provide information on the temporal signatures of disease we currently cannot assess-with the past decade seeing remarkable advances in acceleration using compressed sensing (CS) and artificial intelligence (AI). However, substantial limitations to real-time imaging remain and reconstruction quality is not always guaranteed. To improve reconstruction fidelity in dynamic cardiac MRI, we propose a novel predictive signal model that uses a priori statistics to adaptively predict temporal cardiac dynamics. By using a small training set obtained from the same patient, the new signal model can achieve robust dynamic cardiac MRI in the presence of irregular cardiac rhythm. Evaluation on simulated irregular cardiac dynamics and prospectively undersampled clinical cardiac MRI data demonstrate improved reconstruction quality for two reconstruction frameworks: Kalman filter and CS. The predictive model also works with different undersampling patterns (cartesian, radial, spiral) and can serve as a versatile foundation for robust dynamic cardiac MRI.

Analysis of whole-body MRI artifacts in a pediatric population with a special emphasis on the effect of hands position

PURPOSE

The purpose of this retrospective study was to determine the prevalence of artifacts on whole-body (WB) magnetic resonance imaging (MRI) examination in pediatric patients and identify their causes.

MATERIALS AND METHODS

A total of 107 pediatric patients who underwent a total of 107 WB-MRI examinations, including short-tau inversion recovery (STIR) and T1-weighted sequences, were included. There were 62 girls and 45 boys with a mean age of 11 ± 3 (SD) years (age range: 2-16 years). WB-MRI examinations were analyzed for the presence of artifacts on STIR and T1-weighted sequences. Artifacts were further assigned to one of eight categories (motion, partial volume, cross-talk, phase sampling, susceptibility, equipment, noise, and "other") and 19 anatomical sites by a 4-year resident. Prevalence of artifacts were analyzed especially according to hands position during the examination for the upper limbs and patients' age. Age was expressed as a binary variable using median age (10 years) as the cut-off value. All qualitative variables were compared using chi-square test.

RESULTS

A total of 3436 artifacts were found. The STIR sequences showed more "noise" artifacts (93/1038; 8.96%) and more "cross-talk" (102/1038; 9.83%) artifacts than T1-weighted sequences (12/1038 [1.16%] and 7/1038 [0.67%], respectively) (P < 0.001 for both). T1-weighted sequences showed more "equipment" (84/1038; 8.09%) and "stair-step" (a subset of "other") (41/1038; 3.95%) artifacts than the STIR sequences (39/1038 [3.76%] and 21/1038 [2.02%], respectively) (P < 0.001 and P = 0.01, respectively). T1-weighted sequences showed fewer artifacts on the wrists when the hands were under the bottom (P = 0.001). T1-weighted sequences showed less "equipment" artifacts when the hands were alongside the body (22/296; 7%) than on the abdomen (48/432; 11%) or under the bottom (14/128; 11%) (P < 0.001). STIR sequences showed more "motion" artifacts when the hands were on the abdomen (54/432; 13%) than alongside the body (30/296; 10%) or under the bottom (15/128; 12%) (P < 0.001). WB-MRI examinations had more "susceptibility" artifacts (38/960; 4%) and more "equipment" artifacts (81/960; 8.4%) in patients older than 10 years than in those under 10 years (23/752 [3.1%] and 42/752 [5.6%]) (P = 0.01 and P < 0.001, respectively).

CONCLUSION

Artifacts on WB-MRI do not affect coronal STIR and T1-weighted sequences equally, so the use of both sequence types appears useful. Hands position should be considered with respect to both diagnostic benefit and safety.

Comparison of Improved Unidirectional Dual Velocity-Encoding MRI Methods

BACKGROUND

In phase-contrast (PC) MRI, several dual velocity encoding methods have been proposed to robustly increase velocity-to-noise ratio (VNR), including a standard dual-VENC (SDV), an optimal dual-VENC (ODV), and bi- and triconditional methods.

PURPOSE

To develop a correction method for the ODV approach and to perform a comparison between methods.

STUDY TYPE

Case-control study.

POPULATION

Twenty-six volunteers.

FIELD STRENGTH/SEQUENCE

1.5 T phase-contrast MRI with VENCs of 50, 75, and 150 cm/second.

ASSESSMENT

Since we acquired single-VENC protocols, we used the background phase from high-VENC (VENC_H ) to reconstruct the low-VENC (VENC_L ) phase. We implemented and compared the unwrapping methods for different noise levels and also developed a correction of the ODV method.

STATISTICAL TESTS

Shapiro-Wilk's normality test, two-way analysis of variance with homogeneity of variances was performed using Levene's test, and the significance level was adjusted by Tukey's multiple post hoc analysis with Bonferroni (P < 0.05).

RESULTS

Statistical analysis revealed no extreme outliers, normally distributed residuals, and homogeneous variances. We found statistically significant interaction between noise levels and the unwrapping methods. This implies that the number of non-unwrapped pixels increased with the noise level. We found that for β = VENC_L /VENC_H  = 1/2, unwrapping methods were more robust to noise. The post hoc test showed a significant difference between the ODV corrected and the other methods, offering the best results regarding the number of unwrapped pixels.

DATA CONCLUSIONS

All methods performed similarly without noise, but the ODV corrected method was more robust to noise at the price of a higher computational time.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY STAGE: 1.

Automatic detection of Gibbs artefact in MR images with transfer learning approach

BACKGROUND

Quality control of magnetic resonance imaging includes image validation, which covers also artefact detection. The daily manual review of magnetic resonance images for possible artefacts can be time-consuming, so automated methods for computer-assisted quality assessment of magnetic resonance imaging need to be developed.

OBJECTIVE

The aim of this study was to develop automatic detection of Gibbs artefacts in magnetic resonance imaging using a deep learning method called transfer learning, and to demonstrate the potential of this approach for the development of an automatic quality control tool for the detection of such artefacts in magnetic resonance imaging.

METHODS

The magnetic resonance image dataset of the scanned phantom for quality assurance was created using a turbo spin-echo pulse sequence in the transverse plane. Images were created to include Gibbs artefacts of varying intensities. The images were annotated by two independent reviewers. The annotated dataset was used to develop a method for Gibbs artefact detection using the transfer learning approach. The VGG-16, VGG-19, and ResNet-152 convolutional neural networks were used as pre-trained networks for transfer learning and compared using 5-fold cross-validation.

RESULTS

All accuracies of the classification models were above 97%, while the AUC values were all above 0.99, confirming the high quality of the constructed models.

CONCLUSION

We show that transfer learning can be successfully used to detect Gibbs artefacts on magnetic resonance images. The main advantages of transfer learning are that it can be applied on small training datasets, the procedures to build the models are not so complicated, and they do not require much computational power. This shows the potential of transfer learning for the more general task of detecting artefacts in magnetic resonance images of patients, which consequently can improve and speed up the process of quality assessment in medical imaging practice.

Biased instantaneous regional muscle activation maps: Embedded fuzzy topology and image feature analysis

The instantaneous spatial representation of electrical propagation produced by muscle contraction may introduce bias in surface electromyographical (sEMG) activation maps. Here, we described the effect of instantaneous spatial representation (sEMG segmentation) on embedded fuzzy topological polyhedrons and image features extracted from sEMG activation maps. We analyzed 73,008 topographic sEMG activation maps from seven healthy participants (age 21.4 ± 1.5 years and body mass 74.5 ± 8.5 kg) who performed submaximal isometric plantar flexions with 64 surface electrodes placed over the medial gastrocnemius muscle. Window lengths of 50, 100, 150, 250, 500, and 1,000 ms and overlap of 0, 25, 50, 75, and 90% to change sEMG map generation were tested in a factorial design (grid search). The Shannon entropy and volume of global embedded tri-dimensional geometries (polyhedron projections), and the Shannon entropy, location of the center (LoC), and image moments of maps were analyzed. The polyhedron volume increased when the overlap was <25% and >75%. Entropy decreased when the overlap was <25% and >75% and when the window length was <100 ms and >500 ms. The LoC in the x-axis, entropy, and the histogram moments of maps showed effects for overlap (p < 0.001), while the LoC in the y-axis and entropy showed effects for both overlap and window length (p < 0.001). In conclusion, the instantaneous sEMG maps are first affected by outer parameters of the overlap, followed by the length of the window. Thus, choosing the window length and overlap parameters can introduce bias in sEMG activation maps, resulting in distorted regional muscle activation.

Comparison of a deep learning-accelerated T2-weighted turbo spin echo sequence and its conventional counterpart for female pelvic MRI: reduced acquisition times and improved image quality

OBJECTIVES

To investigate the feasibility of a deep learning-accelerated T2-weighted turbo spin echo (TSE) sequence (T2_DL) applied to female pelvic MRI, using standard T2-weighted TSE (T2_S) as reference.

METHODS

In total, 24 volunteers and 48 consecutive patients with benign uterine diseases were enrolled. Patients in the menstrual phase were excluded. T2_S and T2_DL sequences in three planes were performed for each participant. Quantitative image evaluation was conducted by calculating the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Image geometric distortion was evaluated by measuring the diameters in all three directions of the uterus and lesions. Qualitative image evaluation including overall image quality, artifacts, boundary sharpness of the uterine zonal layers, and lesion conspicuity were assessed by three radiologists using a 5-point Likert scale, with 5 indicating the best quality. Comparative analyses were conducted for the two sequences.

RESULTS

T2_DL resulted in a 62.7% timing reduction (1:54 min for T2_DL and 5:06 min for T2_S in axial, sagittal, and coronal imaging, respectively). Compared to T2_S, T2_DL had significantly higher SNR (p ≤ 0.001) and CNR (p ≤ 0.007), and without geometric distortion (p = 0.925-0.981). Inter-observer agreement regarding qualitative evaluation was excellent (Kendall's W > 0.75). T2_DL provided superior image quality (all p < 0.001), boundary sharpness of the uterine zonal layers (all p < 0.001), lesion conspicuity (p = 0.002, p < 0.001, and p = 0.021), and fewer artifacts (all p < 0.001) in sagittal, axial, and coronal imaging.

CONCLUSIONS

Compared with standard TSE, deep learning-accelerated T2-weighted TSE is feasible to reduce acquisition time of female pelvic MRI with significant improvement of image quality.

Simulated MRI Artifacts: Testing Machine Learning Failure Modes

Objective. Seven types of MRI artifacts, including acquisition and preprocessing errors, were simulated to test a machine learning brain tumor segmentation model for potential failure modes. Introduction. Real-world medical deployments of machine learning algorithms are less common than the number of medical research papers using machine learning. Part of the gap between the performance of models in research and deployment comes from a lack of hard test cases in the data used to train a model. Methods. These failure modes were simulated for a pretrained brain tumor segmentation model that utilizes standard MRI and used to evaluate the performance of the model under duress. These simulated MRI artifacts consisted of motion, susceptibility induced signal loss, aliasing, field inhomogeneity, sequence mislabeling, sequence misalignment, and skull stripping failures. Results. The artifact with the largest effect was the simplest, sequence mislabeling, though motion, field inhomogeneity, and sequence misalignment also caused significant performance decreases. The model was most susceptible to artifacts affecting the FLAIR (fluid attenuation inversion recovery) sequence. Conclusion. Overall, these simulated artifacts could be used to test other brain MRI models, but this approach could be used across medical imaging applications.

CSR-PERT: Joint framework for MRI and HARDI data reconstruction using perturbed radial trajectory estimated from compressively sensed measurements

Radial sampling pattern is an important signal acquisition strategy in magnetic resonance imaging (MRI) owing to better immunity to motion-induced artifacts and less pronounced aliasing due to undersampling compared to the Cartesian sampling. These advantages of radial sampling can be exploited in acquisition of multidimensional signals such as High Angular Resolution Diffusion Imaging (HARDI), with tremendous scope of acceleration. Despite such benefits, gradient delays lead to samples being acquired from unknown miscentered radial trajectories, severely degrading the image reconstruction quality. In the present work, we propose Csr-Pert that is a joint framework, wherein these perturbed radial trajectories are estimated and utilized for image reconstruction from the compressively sensed measurements of (i) MRI data and (ii) HARDI data. The proposed Csr-Pert method is tested on one real MRI dataset with trajectory deviations and is observed to perform better than the existing state-of-the-art method at high acceleration factors up to 8. To the best of our knowledge, this is the first work to address the problem of estimating perturbed trajectories using the compressively sensed MRI and HARDI data. The method is also tested for varying combinations of trajectory deviations and sampling proportions. It is observed to yield very good quality HARDI reconstruction for a wide variety of scenarios. We have also demonstrated the robustness of the proposed method on real datasets in clinical settings assuming perturbed as well as noisy trajectories.

Magnetic Resonance Imaging of Head and Neck Emergencies, a Symptom-Based Review, Part 1: General Considerations, Vision Loss, and Eye Pain

Use of magnetic resonance (MR) imaging in the emergency department continues to increase. Although computed tomography is the first-line imaging modality for most head and neck emergencies, MR is superior in some situations and imparts no ionizing radiation. This article provides a symptom-based approach to nontraumatic head and neck pathologic conditions most relevant to emergency head and neck MR imaging, emphasizing relevant anatomy, "do not miss" findings affecting clinical management, and features that may aid differentiation from potential mimics. Essential MR sequences and strategies for obtaining high-quality images when faced with patient motion and other technical challenges are also discussed.

Complex adult congenital heart disease on cross-sectional imaging: an introductory overview

Congenital heart disease is the most common group of congenital pathology. Over the past few decades, advances in surgical treatment have resulted in a rising population of adult patients with repaired complex congenital heart disease. Although the quality of life has greatly improved, a significant proportion of morbidities encountered in clinical practice is now seen in adults rather than in children. These patients often have significant haemodynamic pathophysiology necessitating repeat intervention. CT and MRI are excellent imaging modalities, which help elucidate potential complications that may need urgent management. Although imaging should be performed in specialised centres, occasionally patients may present acutely to emergency departments in hospitals with little experience in managing potentially complex patients. The purpose of this article is to provide an introductory overview to the radiologist who may not be familiar with complex congenital heart disease in adult patients. This educational review has three main sections: (1) a brief overview of the post-operative anatomy and surgical management of the most common complex conditions followed by (2) a discussion on CT/MRI protocols and (3) a review of the various complications and their CT/MRI findings.

Free-Breathing Phase-Resolved Oxygen-Enhanced Pulmonary MRI Based on 3D Stack-of-Stars UTE Sequence

Compared with hyperpolarized noble gas MRI, oxygen-enhanced lung imaging is a cost-effective approach to investigate lung function. In this study, we investigated the feasibility of free-breathing phase-resolved oxygen-enhanced pulmonary MRI based on a 3D stack-of-stars ultra-short echo time (UTE) sequence. We conducted both computer simulation and in vivo experiments and calculated percent signal enhancement maps of four different respiratory phases on four healthy volunteers from the end of expiration to the end of inspiration. The phantom experiment was implemented to verify simulation results. The respiratory phase was segmented based on the extracted respiratory signal and sliding window reconstruction, providing phase-resolved pulmonary MRI. Demons registration algorithm was applied to compensate for respiratory motion. The mean percent signal enhancement of the average phase increases from anterior to posterior region, matching previous literature. More details of pulmonary tissues were observed on post-oxygen inhalation images through the phase-resolved technique. Phase-resolved UTE pulmonary MRI shows the potential as a valuable method for oxygen-enhanced MRI that enables the investigation of lung ventilation on middle states of the respiratory cycle.

Why upright standing men urinate more efficiently than in supine position: A morphological analysis with real-time magnetic resonance imaging

PURPOSE

Few studies have examined the effects of body position on urination efficiency morphologically. We aimed to dissect out the anatomical changes of pelvic organs during urination in the upright and supine positions by a real-time magnetic resonance imaging (rtMRI) system.

METHODS

Thirteen healthy male volunteers aged 26-60 years were included in the study. The sagittal real-time two-dimensional images were taken to evaluate urinary efficiency, along with change in six morphological indices at the time of storage and the beginning of voiding, in both upright ant supine positions.

RESULTS

Urination was more efficient in upright position than in supine position, as expressed by higher average rate of bladder emptying (9.9 ± 4.2 vs. 6.8 ± 2.9 ml/s, p < 0.05) and also by fewer participants showing significant residual urine (1/13 vs. 7/13, p < 0.05). At the onset of voiding in standing position, the levator ani (LA) muscle moves downward and backward followed by descent of the bladder neck and rotation of the prostate around the symphysis. Such changes were expressed by two morphological indices. One was posterior vesicourethral angle at the start of voiding, 152 ± 7 versus 140 ± 1 in upright and supine position (p < 0.05). The other index was the change in angle between the LA line and pubo-coccygeal line in upright and supine position, 9.4 ± 9.9 versus 1.6 ± 7.9 before voiding (p < 0.05) and 30.2 ± 14.0 versus 17.3 ± 12.9 after the start of voiding (p < 0.05).

CONCLUSION

The dynamic relaxation of LA seemed to be a key movement that enables more efficient urination in standing position than in supine position.

Varying undersampling directions for accelerating multiple acquisition magnetic resonance imaging

In this study, we propose a new sampling strategy for efficiently accelerating multiple acquisition MRI. The new sampling strategy is to obtain data along different phase-encoding directions across multiple acquisitions. The proposed sampling strategy was evaluated in multicontrast MR imaging (T1, T2, proton density) and multiple phase-cycled (PC) balanced steady-state free precession (bSSFP) imaging by using convolutional neural networks with central and random sampling patterns. In vivo MRI acquisitions as well as a public database were used to test the concept. Based on both visual inspection and quantitative analysis, the proposed sampling strategy showed better performance than sampling along the same phase-encoding direction in both multicontrast MR imaging and multiple PC-bSSFP imaging, regardless of sampling pattern (central, random) or datasets (public, retrospective and prospective in vivo). For the prospective in vivo applications, acceleration was performed by sampling along different phase-encoding directions at the time of acquisition with a conventional rectangular field of view, which demonstrated the advantage of the proposed sampling strategy in the real environment. Preliminary trials on compressed sensing (CS) also demonstrated improvement of CS with the proposed idea. Sampling along different phase-encoding directions across multiple acquisitions is advantageous for accelerating multiacquisition MRI, irrespective of sampling pattern or datasets, with further improvement through transfer learning.

Optimised passive marker device visibility and automatic marker detection for 3-T MRI-guided endovascular interventions: a pulsatile flow phantom study

BACKGROUND

Passive paramagnetic markers on magnetic resonance imaging (MRI)-compatible endovascular devices induce susceptibility artifacts, enabling MRI-visibility and real-time MRI-guidance. Optimised visibility is crucial for automatic detection and device tracking but depends on MRI technical parameters and marker characteristics. We assessed marker visibility and automatic detection robustness for varying MRI parameters and marker characteristics in a pulsatile flow phantom.

METHODS

Guidewires with varying iron(II,III) oxide nanoparticle (IONP) concentration markers were imaged using gradient-echo (GRE) and balanced steady-state free precession (bSSFP) sequences at 3 T. Furthermore, echo time (TE), slice thickness (ST) and phase encoding direction (PED) were varied. Artifact width was measured and contrast-to-noise ratios were calculated. Marker visibility and image quality were scored by two MRI interventional radiologists. Additionally, a deep learning model for automatic marker detection was trained and the effects of the parameters on detection performance were evaluated. Two-tailed Wilcoxon signed-rank tests were used (significance level, p < 0.05).

RESULTS

Medan artifact width (IQR) was larger in bSSFP compared to GRE images (12.7 mm (11.0-15.2) versus 8.4 mm (6.5-11.0)) (p < 0.001) and showed a positive relation with TE and IONP concentration. Switching PED and doubling ST had limited effect on artifact width. Image quality assessment scores were higher for GRE compared to bSSFP images. The deep learning model automatically detected the markers. However, the model performance was reduced after adjusting PED, TE, and IONP concentration.

CONCLUSION

Marker visibility was sufficient and a large range of artifact sizes was generated by adjusting TE and IONP concentration. Deep learning-based marker detection was feasible but performance decreased for altered MR parameters. These factors should be considered to optimise device visibility and ensure reliable automatic marker detectability in MRI-guided endovascular interventions.

ArtifactID: Identifying artifacts in low-field MRI of the brain using deep learning

Low-field MR scanners are more accessible in resource-constrained settings where skilled personnel are scarce. Images acquired in such scenarios are prone to artifacts such as wrap-around and Gibbs ringing. Such artifacts negatively affect the diagnostic quality and may be confused with pathology or reduce the region of interest visibility. As a first step solution, ArtifactID identifies wrap-around and Gibbs ringing in low-field brain MRI. We utilized two datasets: 179 T₁-weighted pathological brain images from a 0.36 T scanner and 581 publicly available T₁-weighted brain images. Individual binary classification models were trained to identify through-plane wrap-around, in-plane wrap-around, and Gibbs ringing. Visual explanations obtained via the GradCAM method helped develop trust in the wrap-around model. The mean precision and recall metrics across the four implemented models were 97.6% and 92.83% respectively. Agreement analysis of the models and the radiologists' labels returned Cohen's kappa values of 0.768 ± 0.062, 1.00 ± 0.000, 0.89 ± 0.085, and 0.878 ± 0.103 for the through-plane wrap-around, in-plane wrap-around, and Gibbs ringing models, respectively.

Improved Multi-Echo Gradient-Echo-Based Myelin Water Fraction Mapping Using Dimensionality Reduction

Multi-echo gradient-echo (mGRE)-based myelin water fraction (MWF) mapping is a promising myelin water imaging (MWI) modality but is vulnerable to noise and artifact corruption. The linear dimensionality reduction (LDR) method has recently shown improvements with regard to these challenges. However, the magnitude value based low rank operators have been shown to misestimate the MWF for regions with [Formula: see text] anisotropy. This paper presents a nonlinear dimensionality reduction (NLDR) method to estimate the MWF map better by encouraging nonlinear low dimensionality of mGRE signal sources. Specifically, we implemented a fully connected deep autoencoder to extract the low-dimensional features of complex-valued signals and incorporated a sparse regularization to separate the anomaly sources that do not reside in the low-dimensional manifold. Simulations and in vivo experiments were performed to evaluate the accuracy of the MWF map under various situations. The proposed NLDR-based MWF improves the accuracy of the MWF map over the conventional nonlinear least-squares method and the LDR-based MWF and maintains robustness against noise and artifact corruption.

Post-injury ventricular enlargement associates with iron in choroid plexus but not with seizure susceptibility nor lesion atrophy-6-month MRI follow-up after experimental traumatic brain injury

Ventricular enlargement is one long-term consequence of a traumatic brain injury, and a risk factor for memory disorders and epilepsy. One underlying mechanisms of the chronic ventricular enlargement is disturbed cerebrospinal-fluid secretion or absorption by choroid plexus. We set out to characterize the different aspects of ventricular enlargement in lateral fluid percussion injury (FPI) rat model by magnetic resonance imaging (MRI) and discovered choroid plexus injury in rats that later developed hydrocephalus. We followed the brain pathology progression for 6 months and studied how the ventricular growth was associated with the choroid plexus injury, cortical lesion expansion, hemorrhagic load or blood perfusion deficits. We correlated MRI findings with the seizure susceptibility in pentylenetetrazol challenge and memory function in Morris water-maze. Choroid plexus injury was validated by ferric iron (Prussian blue) and cytoarchitecture (Nissl) stainings. We discovered choroid plexus injury that accumulates iron in 90% of FPI rats by MRI. The amount of the choroid plexus iron remained unaltered 1-, 3- and 6-month post-injury. During this time, the ventricles kept on growing bilaterally. Ventricular growth did not depend on the cortical lesion severity or the cortical hemorrhagic load suggesting a separate pathology. Instead, the results indicate choroidal injury as one driver of the post-traumatic hydrocephalus, since the higher the choroid plexus iron load the larger were the ventricles at 6 months. The ventricle size or the choroid plexus iron load did not associate with seizure susceptibility. Cortical hypoperfusion and memory deficits were worse in rats with greater ventricular growth.

Brain tumor detection and classification using machine learning: a comprehensive survey

Brain tumor occurs owing to uncontrolled and rapid growth of cells. If not treated at an initial phase, it may lead to death. Despite many significant efforts and promising outcomes in this domain, accurate segmentation and classification remain a challenging task. A major challenge for brain tumor detection arises from the variations in tumor location, shape, and size. The objective of this survey is to deliver a comprehensive literature on brain tumor detection through magnetic resonance imaging to help the researchers. This survey covered the anatomy of brain tumors, publicly available datasets, enhancement techniques, segmentation, feature extraction, classification, and deep learning, transfer learning and quantum machine learning for brain tumors analysis. Finally, this survey provides all important literature for the detection of brain tumors with their advantages, limitations, developments, and future trends.

Study of needle punctures into soft tissue through audio and force sensing: can audio be a simple alternative for needle guidance?

PURPOSE

Percutaneous needle insertion is one of the most common minimally invasive procedures. The clinician's experience and medical imaging support are essential to the procedure's safety. However, imaging comes with inaccuracies due to artifacts, and therefore sensor-based solutions were proposed to improve accuracy. However, sensors are usually embedded in the needle tip, leading to design limitations. A novel concept was proposed for capturing tip-tissue interaction information through audio sensing, showing promising results for needle guidance. This work demonstrates that this audio approach can provide important puncture information by comparing audio and force signal dynamics during insertion.

METHODS

An experimental setup for inserting a needle into soft tissue was prepared. Audio and force signals were synchronously recorded at four different insertion velocities, and a dataset of 200 recordings was acquired. Indicators related to different aspects of the force and audio were compared through signal-to-signal and event-to-event correlation analysis.

RESULTS

High signal-to-signal correlations between force and audio indicators regardless of the insertion velocity were obtained. The force curvature indicator obtained the best correlation performances to audio with more than [Formula: see text] of the correlations higher than 0.6. The event-to-event correlation analysis shows that a puncture event in the force is generally identifiable in audio and that their intensities firmly related.

CONCLUSIONS

Audio contains valuable information for monitoring needle tip/tissue interaction. Significant dynamics obtained from a well-known sensor as force can also be extracted from audio, regardless of insertion velocities.

Statement of the German Roentgen Society, German Society of Neuroradiology, and Society of German-speaking Pediatric Radiologists on Requirements for the Performance and Reporting of MR Imaging Examinations Outside of Radiology

BACKGROUND

 Magnetic Resonance Imaging (MRI) is a very innovative, but at the same time complex and technically demanding diagnostic method in radiology. It plays an increasing role in high-quality and efficient patient management. Quality assurance in MRI is of utmost importance to avoid patient risks due to errors before and during the examination and when reporting the results. Therefore, MRI requires higher physician qualification and expertise than any other diagnostic imaging technique in medicine. This holds true for indication, performance of the examination itself, and in particular for image evaluation and writing of the report. In Germany, the radiologist is the only specialist who is systematically educated in all aspects of MRI during medical specialty training and who must document a specified, high number of examinations during this training. However, also non-radiologist physicians are increasingly endeavoring to conduct and bill MRI examinations on their own.

METHOD

 In this position statement, the following aspects of quality assurance for MRI examinations and billing by radiologists and non-radiologist physician specialists are examined scientifically: Requirements for specialist physician training, MRI risks and contraindications, radiation protection in the case of non-ionizing radiation, application of MR contrast agents, requirements regarding image quality, significance of image artifacts and incidental findings, image evaluation and reporting, interdisciplinary communication and multiple-eyes principle, and impact on healthcare system costs.

CONCLUSION

 The German Roentgen Society, German Society of Neuroradiology, and Society of German-speaking Pediatric Radiologists are critical with regard to MRI performance by non-radiologists in the interest of quality standards, patient welfare, and healthcare payers. The 24-month additional qualification in MRI as defined by the physician specialization regulations (Weiterbildungsordnung) through the German state medical associations (Landesärztekammern) is the only competence-based and quality-assured training program for board-certified specialist physicians outside radiology. This has to be required as the minimum standard for performance and reporting of MRI exams. Exclusively unstructured MRI training outside the physician specialization regulations has to be strictly rejected for reasons of patient safety. The performance and reporting of MRI examinations must be reserved for adequately trained and continuously educated specialist physicians.

KEY POINTS

· MR imaging plays an increasing role due to its high diagnostic value and serves as the reference standard in many indications.. · MRI is a complex technique that implies patient risks in case of inappropriare application or lack of expertise.. · In Germany, the radiologist is the only specialist physician that has been systematically trained in all aspects of MRI such as indication, performance, and reporting of examinations in specified, high numbers.. · The only competence-based and quality-assured MRI training program for specialist physicians outside radiology is the 24-month additional qualification as defined by the regulations through the German state medical associations.. · In view of quality-assurance and patient safety, a finalized training program following the physician specialization regulations has to be required for the performance and reporting of MRI examinations..

CITATION FORMAT

· Hunold P, Bucher AM, Sandstede J et al. Statement of the German Roentgen Society, German Society of Neuroradiology, and Society of German-speaking Pediatric Radiologists on Requirements for the Performance and Reporting of MR Imaging Examinations Outside of Radiology. Fortschr Röntgenstr 2021; 193: 1050 - 1060.

Local excitation universal parallel transmit pulses at 9.4T

PURPOSE

To demonstrate that the concept of "universal pTx pulses" is applicable to local excitation applications.

METHODS

A database of B₀ / B 1 + maps from eight different subjects was acquired at 9.4T. Based on these maps, universal pulses that aim at local excitation of the visual cortex area in the human brain (with a flip angle of 90° or 7°) were calculated. The remaining brain regions should not experience any excitation. The pulses were designed with an extension of the "spatial domain method." A 2D and a 3D target excitation pattern were tested, respectively. The pulse performance was examined on non-database subjects by Bloch simulations and in vivo at 9.4T using a GRE anatomical MRI and a presaturated TurboFLASH B 1 + mapping sequence.

RESULTS

The calculated universal pulses show excellent performance in simulations and in vivo on subjects that were not contained in the design database. The visual cortex region is excited, while the desired non-excitation areas produce the only minimal signal. In simulations, the pulses with 3D target pattern show a lack of excitation uniformity in the visual cortex region; however, in vivo, this inhomogeneity can be deemed acceptable. A reduced field of view application of the universal pulse design concept was performed successfully.

CONCLUSIONS

The proposed design approach creates universal local excitation pulses for a flip angle of 7° and 90°, respectively. Providing universal pTx pulses for local excitation applications prospectively abandons the need for time-consuming subject-specific B₀ / B 1 + mapping and pTx-pulse calculation during the scan session.

A 20-gauge active needle design with thin-film printed circuitry for interventional MRI at 0.55T

PURPOSE

This work aims to fabricate RF antenna components on metallic needle surfaces using biocompatible polyester tubing and conductive ink to develop an active interventional MRI needle for clinical use at 0.55 Tesla.

METHODS

A custom computer numeric control-based conductive ink printing method was developed. Based on electromagnetic simulation results, thin-film RF antennas were printed with conductive ink and used to fabricate a medical grade, 20-gauge (0.87 mm outer diameter), 90-mm long active interventional MRI needle. The MRI visibility performance of the active needle prototype was tested in vitro in 1 gel phantom and in vivo in 1 swine. A nearly identical active needle constructed using a 44 American Wire Gauge insulated copper wire-wound RF receiver antenna was a comparator. The RF-induced heating risk was evaluated in a gel phantom per American Society for Testing and Materials (ASTM) 2182-19.

RESULTS

The active needle prototype with printed RF antenna was clearly visible both in vitro and in vivo under MRI. The maximum RF-induced temperature rise of prototypes with printed RF antenna and insulated copper wire antenna after a 3.96 W/kg, 15 min. long scan were 1.64°C and 8.21°C, respectively. The increase in needle diameter was 98 µm and 264 µm for prototypes with printed RF antenna and copper wire-wound antenna, respectively.

CONCLUSION

The active needle prototype with conductive ink printed antenna provides distinct device visibility under MRI. Variations on the needle surface are mitigated compared to use of a 44 American Wire Gauge copper wire. RF-induced heating tests support device RF safety under MRI. The proposed method enables fabrication of small diameter active interventional MRI devices having complex geometries, something previously difficult using conventional methods.

Canadian Society of Thoracic Radiology/Canadian Association of Radiologists Clinical Practice Guidance for Non-Vascular Thoracic MRI

Historically thoracic MRI has been limited by the lower proton density of lung parenchyma, cardiac and respiratory motion artifacts and long acquisition times. Recent technological advancements in MR hardware systems and improvement in MR pulse sequences have helped overcome these limitations and expand clinical opportunities for non-vascular thoracic MRI. Non-vascular thoracic MRI has been established as a problem-solving imaging modality for characterization of thymic, mediastinal, pleural chest wall and superior sulcus tumors and for detection of endometriosis. It is increasingly recognized as a powerful imaging tool for detection and characterization of lung nodules and for assessment of lung cancer staging. The lack of ionizing radiation makes thoracic MRI an invaluable imaging modality for young patients, pregnancy and for frequent serial follow-up imaging. Lack of familiarity and exposure to non-vascular thoracic MRI and lack of consistency in existing MRI protocols have called for clinical practice guidance. The purpose of this guide, which was developed by the Canadian Society of Thoracic Radiology and endorsed by the Canadian Association of Radiologists, is to familiarize radiologists, other interested clinicians and MR technologists with common and less common clinical indications for non-vascular thoracic MRI, discuss the fundamental imaging findings and focus on basic and more advanced MRI sequences tailored to specific clinical questions.

Monitoring and Synchronization of Cardiac and Respiratory Traces in Magnetic Resonance Imaging: A Review

Synchronization of human vital signs, namely the cardiac cycle and respiratory excursions, is necessary during magnetic resonance imaging of the cardiovascular system and the abdominal cavity to achieve optimal image quality with minimized artifacts. This review summarizes techniques currently available in clinical practice, as well as methods under development, outlines the benefits and disadvantages of each approach, and offers some unique solutions for consideration.

Evaluation of MRI Artifact in some selected centers in Kano Metropolis, Nigeria

Background

Magnetic Resonance Imaging (MRI) artifacts can occur due to hardware or software related problems, human physiologic phenomenon or physical restrictions. Careful study design and scanning protocols can prevent certain artifacts from occurring, but some are unavoidable.

Study aims

The study aimed at evaluating MRI artifact in some selected centers in Kano metropolis, Nigeria.

Methodology

A descriptive cross-sectional study was conducted involving both prospective and retrospective phases across three centres in the Kano metropolis from March 2019 to August 2019. Using the purposive sampling method, 3 centers were selected. A data capture sheet was designed for data collection.

Results

Thirty five (50%) of the artifacts encountered were from the centreA, 28(40%) from the centre B, and 7(10%) from the centre C. Motion-induced artifact was the most frequently encountered artifact 26(37.1%), followed by wrap-around artifact 15(21.4%), and then frequency-induced artifact 13(18.6%). Thoracic spine MRI had the highest number of artifacts 28(40%), followed by brain 20(28.6%), and then lumbar spine 19(27.1%).

Conclusion

In Kano metropolis the most encountered MRI artifact was the motion-induced artifact and thoracic spine MRI had the highest number of artifacts. The artifacts had a negative effect on image quality.

Noninvasive imaging of congenital cardiovascular defects

Advances in the treatment have drastically increased the survival rate of congenital heart disease (CHD) patients. Therefore, the prevalence of these patients is growing. Imaging plays a crucial role in the diagnosis and management of this population as a key component of patient care at all stages, especially in those patients who survived into adulthood. Over the last decades, noninvasive imaging techniques, such as cardiac magnetic resonance (CMR) and cardiac computed tomography (CCT), progressively increased their clinical relevance, reaching stronger levels of accuracy and indications in the clinical surveillance of CHD. The current review highlights the main technical aspects and clinical applications of CMR and CCT in the setting of congenital cardiovascular abnormalities, aiming to address a state-of-the-art guidance to every physician and cardiac imager not routinely involved in the field.

Controlled mechanical ventilation to detect regional lymph node metastases in esophageal cancer using USPIO-enhanced MRI; comparison of image quality

BACKGROUND

Artifacts caused by respiratory motion or ventilation-induced chest movements are a major problem for thoracic MRI, as they can obscure important anatomical structures such as lymph node metastases. We compared image quality of routine breathhold with intermittent apnea during controlled mechanical ventilation of patients under general anesthesia as the ideal situation without respiratory motion in the detection and characterization of regional lymph nodes in esophageal cancer.

METHODS

In this prospective study, 10 patients treated for esophageal cancer underwent ultrasmall superparamagnetic iron oxide (USPIO) enhanced MRI scans. Before neoadjuvant therapy, MRI scans were acquired with a routine breathhold technique. After neoadjuvant therapy, patients were scanned under general anesthesia immediately prior to surgery with controlled mechanical ventilation. The image quality was compared using a Likert scale questionnaire based on visibility of anatomical structures and image artifacts.

RESULTS

MRI with controlled mechanical ventilation and prolonged controlled apnea of 4 min was safe and feasible. All cardio-respiratory monitoring parameters remained stable during the apnea phases. Mediastinal and upper abdominal lymph nodes down to 2 mm in size could be visualized with all sequences. All image quality criteria, including visibility of thoracic structures and regional lymph nodes were scored higher using the controlled ventilation sequences compared to the routine breathhold phase.

CONCLUSION

USPIO-enhanced MRI with controlled mechanical ventilation is superior to routine breathhold MRI in visualizing lymph nodes, which warrants new motion reduction techniques to use MRI for the detection of lymph node metastases in patients with esophageal cancer.

New Advances in Magnetic Resonance Techniques in Abdomen and Pelvis

This article explores new acquisition methods in magnetic resonance (MR) imaging to provide high spatial and temporal resolution imaging for a wide spectrum of clinical applications in the abdomen and pelvis. We present an overview of some of these advanced MR techniques, such as non-cartesian image acquisition, fast sampling and compressed sensing, diffusion quantification and quantitative MR that can improve data sampling, enhance image quality, yield quantitative measurements, and/or optimize diagnostic performance in the body.

MRI restoration using edge-guided adversarial learning

Magnetic resonance imaging (MRI) images acquired as multislice two-dimensional (2D) images present challenges when reformatted in orthogonal planes due to sparser sampling in the through-plane direction. Restoring the "missing" through-plane slices, or regions of an MRI image damaged by acquisition artifacts can be modeled as an image imputation task. In this work, we consider the damaged image data or missing through-plane slices as image masks and proposed an edge-guided generative adversarial network to restore brain MRI images. Inspired by the procedure of image inpainting, our proposed method decouples image repair into two stages: edge connection and contrast completion, both of which used general adversarial networks (GAN). We trained and tested on a dataset from the Human Connectome Project to test the application of our method for thick slice imputation, while we tested the artifact correction on clinical data and simulated datasets. Our Edge-Guided GAN had superior PSNR, SSIM, conspicuity and signal texture compared to traditional imputation tools, the Context Encoder and the Densely Connected Super Resolution Network with GAN (DCSRN-GAN). The proposed network may improve utilization of clinical 2D scans for 3D atlas generation and big-data comparative studies of brain morphometry.

Magnetic Resonance Angiography of the Thoracic Vasculature: Technique and Applications

Magnetic resonance angiography (MRA) is a powerful clinical tool for evaluation of the thoracic vasculature. MRA can be performed on nearly any magnetic resonance imaging (MRI) scanner, and provides images of high diagnostic quality without the use of ionizing radiation. While computed tomographic angiography (CTA) is preferred in the evaluation of hemodynamically unstable patients, MRA represents an important tool for evaluation of the thoracic vasculature in stable patients. Contrast-enhanced MRA is generally performed unless there is a specific contraindication, as it shortens the duration of the exam and provides images of higher diagnostic quality than noncontrast MRA. However, intravenous contrast is often not required to obtain a diagnostic evaluation for most clinical indications. Indeed, a variety of noncontrast MRA techniques are used for thoracic imaging, often in conjunction with contrast-enhanced MRA, each of which has a differing degree of reliance on flowing blood to produce the desired vascular signal. In this article we review contrast-enhanced MRA, with a focus on contrast agents, methods of bolus timing, and considerations in imaging acquisition. Next, we cover the mechanism of contrast, strengths, and weaknesses of various noncontrast MRA techniques. Finally, we present an approach to protocol development and review representative protocols used at our institution for a variety of thoracic applications. Further attention will be devoted to additional techniques employed to address specific clinical questions, such as delayed contrast-enhanced imaging, provocative maneuvers, electrocardiogram and respiratory gating, and phase-contrast imaging. The purpose of this article is to review basic techniques and methodology in thoracic MRA, discuss an approach to protocol development, and illustrate commonly encountered pathology on thoracic MRA examinations. Level of Evidence 5 Technical Efficacy Stage 3.

EDUCATIONAL SERIES IN CONGENITAL HEART DISEASE: Cardiovascular MRI and CT in congenital heart disease

Cardiovascular MRI and CT are useful imaging modalities complimentary to echocardiography. This review article describes the common indications and consideration for the use of MRI and CT in the management of congenital heart disease.