Respiratory Artifacts Research Articles

Explainable AI for automated respiratory misalignment detection in PET/CT imaging

Purpose.Positron emission tomography (PET) image quality can be affected by artifacts emanating from PET, computed tomography (CT), or artifacts due to misalignment between PET and CT images. Automated detection of misalignment artifacts can be helpful both in data curation and in facilitating clinical workflow. This study aimed to develop an explainable machine learning approach to detect misalignment artifacts in PET/CT imaging.Approach.This study included 1216 PET/CT images. All images were visualized and images with respiratory misalignment artifact (RMA) detected. Using previously trained models, four organs including the lungs, liver, spleen, and heart were delineated on PET and CT images separately. Data were randomly split into cross-validation (80%) and test set (20%), then two segmentations performed on PET and CT images were compared and the comparison metrics used as predictors for a random forest framework in a 10-fold scheme on cross-validation data. The trained models were tested on 20% test set data. The model's performance was calculated in terms of specificity, sensitivity, F1-Score and area under the curve (AUC).Main results.Sensitivity, specificity, and AUC of 0.82, 0.85, and 0.91 were achieved in ten-fold data split. F1_score, sensitivity, specificity, and AUC of 84.5 vs 82.3, 83.9 vs 83.8, 87.7 vs 83.5, and 93.2 vs 90.1 were achieved for cross-validation vs test set, respectively. The liver and lung were the most important organs selected after feature selection.Significance.We developed an automated pipeline to segment four organs from PET and CT images separately and used the match between these segmentations to decide about the presence of misalignment artifact. This methodology may follow the same logic as a reader detecting misalignment through comparing the contours of organs on PET and CT images. The proposed method can be used to clean large datasets or integrated into a clinical scanner to indicate artifactual cases.

The effect on gastrointestinal peristalsis for magnetic resonance cholangiopancreatography during breath-holding methods.

The breath-hold (BH) 3D magnetic resonance cholangiopancreatography method has been reported to suppress "respiratory artifacts"; however, the influence of gastrointestinal peristalsis around the target organs has not been discussed. In contrast, the autonomic nervous system has been reported to affect gastrointestinal peristalsis and BH imaging has been reported to influence venous blood flow signal (BFS) through its involvement with the autonomic nervous system. We examined the impact of BH imaging on gastrointestinal peristalsis. Seven healthy volunteers participated. Three respiratory patterns-free breathing (FB), BH at maximum inspiration (Insp-BH), and BH at maximum expiration (Exp-BH)-were used. Gastrointestinal peristalsis was measured using cine MRI. Cine MRI data were analyzed using the normalized interframe difference method, focusing on the duodenum and gastric body. Hemodynamic changes resulting from BH methods were evaluated using 2D phase contrast, targeting the inferior vena cava (IVC). The BFS was examined for all phases of each respiratory pattern. Peristalsis variation in the duodenum showed no significant differences among FB, Exp-BH, and Insp-BH. In the gastric body, no significant differences were observed between FB and Exp-BH or between Exp-BH and Insp-BH. However, a significant difference emerged between FB and Insp-BH. Regarding BFS, in the IVC, significant differences were observed between Exp-BH and Insp-BH and between FB and Insp-BH (both, p < 0.01), with no significant difference between FB and Exp-BH. Insp-BH reduces venous blood flow and suppresses the influence of peristalsis variation.

Clinical application of prone position to suppress respiratory movement artifacts in supine position during magnetic resonance cholangiopancreatography/MRI.

To compare the image quality of magnetic resonance cholangiopancreatography (MRCP) in the supine position and prone position under the conditions of the same equipment, the same sequence (3D Navigator Triggered Sampling Perfection with Application-Optimized Contrast Using Different Flip-angle Evolutions, 3D-NT-SPACE) and the same patient, and to explore the clinical application value of prone position in MRCP examination to suppress respiratory motion artifacts. 53 participants who underwent MRCP in our hospital from April 2020 to August 2022 were prospectively collected. The 3D-NT-SPACE sequence was used in these patients. The visibility of the common bile duct, common hepatic duct, main pancreatic duct, and first- and second- and third-level branches of the intrahepatic bile duct and the comfort of the participants in two positions were subjective-evaluated. The Signal-to-noise ratio (SNR) and contrast-to-noise ratio were objective-evaluated. Statistical analysis was performed using Shapiro-Wilk, Levene's, Mann Whitney U test, Pearson chi-square test, and one-sample chi-square test. 53 patients (51.92years ± 2.02, 20 men) were evaluated. There were significant differences in the second- and third-level branches visibility score, the main pancreatic duct visibility score, the image quality score of the pancreaticobiliary tree, the blur and motion artifact score, the total image quality score, and SNR between the two positions (p < 0.05). The overall image quality of the prone position was better than that of the supine position. The prone position is a useful complement to the supine position.

Leveraging Multi-Echo EPI to Enhance BOLD Sensitivity in Task-based Olfactory fMRI.

Functional magnetic resonance imaging (fMRI) using blood-oxygenation-level-dependent (BOLD) contrast relies on gradient echo echo-planar imaging (GE-EPI) to quantify dynamic susceptibility changes associated with the hemodynamic response to neural activity. However, acquiring BOLD fMRI in human olfactory regions is particularly challenging due to their proximity to the sinuses where large susceptibility gradients induce magnetic field distortions. BOLD fMRI of the human olfactory system is further complicated by respiratory artifacts that are highly correlated with event onsets in olfactory tasks. Multi-echo EPI (ME-EPI) acquires gradient echo data at multiple echo times (TEs) during a single acquisition and can leverage signal evolution over the multiple echo times to enhance BOLD sensitivity and reduce artifactual signal contributions. In the current study, we developed a ME-EPI acquisition protocol for olfactory task-based fMRI and demonstrated significant improvement in BOLD signal sensitivity over conventional single-echo EPI (1E-EPI). The observed improvement arose from both an increase in BOLD signal changes through a T 2 * -weighted echo combination and a reduction in non-BOLD artifacts through the application of the Multi-Echo Independent Components Analysis (ME-ICA) denoising method. This study represents one of the first direct comparisons between 1E-EPI and ME-EPI in high-susceptibility regions and provides compelling evidence in favor of using ME-EPI for future task-based fMRI studies.

Automatic semantic segmentation of EHG recordings by deep learning: An approach to a screening tool for use in clinical practice

Background and ObjectivePreterm delivery is an important factor in the disease burden of the newborn and infants worldwide. Electrohysterography (EHG) has become a promising technique for predicting this condition, thanks to its high degree of sensitivity. Despite the technological progress made in predicting preterm labor, its use in clinical practice is still limited, one of the main barriers being the lack of tools for automatic signal processing without expert supervision, i.e. automatic screening of motion and respiratory artifacts in EHG records. Our main objective was thus to design and validate an automatic system of segmenting and screening the physiological segments of uterine origin in EHG records for robust characterization of uterine myoelectric activity, predicting preterm labor and help to promote the transferability of the EHG technique to clinical practice. MethodsFor this, we combined 300 EHG recordings from the TPEHG DS database and 69 EHG recordings from our own database (Ci2B-La Fe) of women with singleton gestations. This dataset was used to train and evaluate U-Net, U-Net++, and U-Net 3+ for semantic segmentation of the physiological and artifacted segments of EHG signals. The model's predictions were then fine-tuned by post-processing. ResultsU-Net 3+ outperformed the other models, achieving an area under the ROC curve of 91.4 % and an average precision of 96.4 % in detecting physiological activity. Thresholds from 0.6 to 0.8 achieved precision from 93.7 % to 97.4 % and specificity from 81.7 % to 94.5 %, detecting high-quality physiological segments while maintaining a trade-off between recall and specificity. Post-processing improved the model's adaptability by fine-tuning both the physiological and corrupted segments, ensuring accurate artifact detection while maintaining physiological segment integrity in EHG signals. ConclusionsAs automatic segmentation proved to be as effective as double-blind manual segmentation in predicting preterm labor, this automatic segmentation tool fills a crucial gap in the existing preterm delivery prediction system workflow by eliminating the need for double-blind segmentation by experts and facilitates the practical clinical use of EHG. This work potentially contributes to the early detection of authentic preterm labor women and will allow clinicians to design individual patient strategies for maternal health surveillance systems and predict adverse pregnancy outcomes.

Comparative Performance Analysis of Filtering Methods for Removing Baseline Wander Noise from an ECG Signal

ECG signals play a vital role in the diagnosis of cardiovascular conditions. However, they often suffer from the effects of various noise sources, including baseline wandering, respiratory artifact noise, power line interference and electrode motion artifacts. To overcome these challenges, it is imperative to implement low-frequency signal noise reduction strategies. Such strategies aim to significantly improve the quality of ECG signals, thus promoting more accurate and reliable diagnosis of cardiovascular disorders. This paper conducts a comparative analysis to assess the effectiveness of commonly used filtering and wavelet techniques in reducing Baseline Wander (BW) noise within ECG signals generated by the influence of breathing or electrode movements. It is common to observe the selection and evaluation of only one particular technique in the existing literature. In contrast, this study aims to provide a comprehensive comparative analysis, providing insight into the performance and relative merits of different techniques. Our research uses both filtering and Discrete Wavelet Transform (DWT) techniques in baseline noise removal. In this context, a reference point is established utilizing noise-free signals and a meticulous investigation of the wavelet-based approach that most effectively eliminates the resulting noise is provided. Subsequently, we assess the reference input and output signal via Signal-to-Noise Ratio (SNR) and Kolmogorov–Smirnov statistical test measurements. The most important contribution of this work to the scientific community resides in the comprehensive examination of IIR/FIR-based and wavelet method-based filtering methods capable of yielding the highest SNR levels across various ECG signals with various types of BW noise. Additionally, the effectiveness of the Chebychev-II filter in BW noise removal is highlighted. Our study was conducted using the MATLAB platform and code command lines were shared to facilitate the reproduction of our study by other researchers. It is considered that this study will be an important reference in the selection of effective techniques for removing BW noise within ECG signals.

Rapid whole brain 3D T2 mapping respiratory-resolved Double-Echo Steady State (DESS) sequence with improved repeatability.

To propose a quantitative 3D double-echo steady-state (DESS) sequence that offers rapid and repeatable T2 mapping of the human brain using different encoding schemes that account for respiratory B0 variation. A retrospective self-gating module was firstly implemented into the standard DESS sequence in order to suppress the respiratory artifact via data binning. A compressed-sensing trajectory (CS-DESS) was then optimized to accelerate the acquisition. Finally, a spiral Cartesian encoding (SPICCS-DESS) was incorporated to further disrupt the coherent respiratory artifact. These different versions were compared to a standard DESS sequence (fully DESS) by assessing the T2 distribution and repeatability in different brain regions of eight volunteers at 3 T. The respiratory artifact correction was determined to be optimal when the data was binned into seven respiratory phases. Compared to the fully DESS, T2 distribution was improved for the CS-DESS and SPICCS-DESS with interquartile ranges reduced significantly by a factor ranging from 2 to 12 in the caudate, putamen, and thalamus regions. In the gray and white matter areas, average absolute test-retest T2 differences across all volunteers were respectively 3.5 ± 2% and 3.1 ± 2.1% for the SPICCS-DESS, 4.6 ± 4.6% and 4.9 ± 5.1% for the CS-DESS, and 15% ± 13% and 7.3 ± 5.6% for the fully DESS. The SPICCS-DESS sequence's acquisition time could be reduced by half (<4 min) while maintaining its efficient T2 mapping. The respiratory-resolved SPICCS-DESS sequence offers rapid, robust, and repeatable 3D T2 mapping of the human brain, which can be especially effective for longitudinal monitoring of cerebral pathologies.

Accuracy of oscillometric-based blood pressure monitoring devices: impact of pulse volume, arrhythmia, and respiratory artifact.

An oscillometric waveform (OMW) envelope-based blood pressure (BP) monitoring device is widely used to monitor blood pressure and prevent hypertension and adverse cardiovascular events. At present, all primary care physicians and clinicians widely recommend oscillometric-based BP devices. The consumer selects the device based on their own decision, without knowing whether the device is validated or not, resulting in over- or under-treatment of hypertension. It is imperative that each device must comply with international protocols. In this study, we have investigated the accuracy of inflation and deflation-based oscillometric BP monitoring devices in the case of sinus rhythm (SR). Since different health conditions of the patient affect the oscillometric waveform, which can affect the device's accuracy, in such cases, many BP monitors are skeptical of succeeding in the norms of international protocols. Therefore, this study also aims to calculate the accuracy of these devices in various health conditions and measure the effect of pulse volume, arrhythmia, and respiratory artifact on it using a non-invasive blood pressure (NIBP) simulator. We found that the oscillometric BP devices failed to measure the correct blood pressure in several clinical conditions.

“Brain-Breath” Interactions: Respiration-Timing-Dependent Impact on Functional Brain Networks and Beyond

Breathing is a natural process that we cannot do without and is also a daily action that sensitively and intensely changes under various situations. What if this essential act of breathing can impact our overall well-being? Recent studies have demonstrated that breathing couples with higher brain functions, i.e., perception, motor actions, and cognition. In particular, the timing of breathing can be a key factor to modulate accuracy in cognitive tasks and changes activation in specific cortical regions. To determine possible respiratory roles in attentional and memory processes and functional brain networks, we discussed several issues of interactions between breathing and brain function: i) respiration-dependent modulation of cognition and mental health; ii) respiratory rhythm generation in the brainstem (e.g., the PreBötzinger complex); iii) interpretation of the blood-oxygen-level-dependent (BOLD) signal without respiratory artifacts using functional magnetic resonance imaging (fMRI); iv) respiration-timing-dependent effects on functional neural networks (e.g., the locus coeruleus, temporoparietal junction, ventral attention network, and cingulo-opercular salience network); and v) a potential application of breathing manipulation in mental health care. These outlines and considerations of “brain-breath” interactions lead to a better understanding of the interoceptive and cognitive mechanisms that underlie brain-body interactions in health conditions and in stress-related and neuropsychiatric disorders.

Lowest peak central venous pressure correlates with highest invasive arterial blood pressure as a method for optimising AV delay in post-surgical temporary pacing

Abstract Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): British Heart Foundation. Background Atrioventricular (AV) delay optimisation has been performed using a variety of methods, including doppler outflow and alternating blood pressure algorithms. Patients after cardiac surgery are usually invasively monitored with arterial and central venous pressure (CVP) lines. Purpose We aimed to see if the CVP line could be used to optimise AV delays in temporary pacing for situations where the arterial line is absent or non-functional. Methods 11 patients in sinus rhythm but with temporary pacemakers after cardiac surgery were studied. Each patient underwent alternating optimisation algorithms where they were subjected to 8 transitions between a reference AV delay of 120ms and a tested AV delay ranging from 40ms to 280 ms. Testing was terminated after the AV delay occurred when native conduction occurred i.e after they began AAI pacing. All patients were paced at 80 bpm. Arterial blood pressure (ABP) and CVP were recorded from radial arterial lines and central venous lines in the internal jugular vein during the transitions. The optimal point was defined as the AV delay generating the maximum systolic blood pressure. The CVP was measured in 3 ways: peak pressure, mean pressure, and area under the curve. Central venous pressure tracings were corrected for respiration using a "fit-a-curve" function. All analysis was performed in Python. Results Individual pressure readings. There was a negative correlation between individual ABP and Peak CVP pressure readings (R= -0.539, p=0&amp;lt;0.001). A representative example for a single patient is shown in Figure 1 and for all data in Figure 2. A similar relationship, albeit less strong, was seen between ABP and Mean CVP (R= -0.281, p=0.046). There was no significant relationship between ABP and CVP AUC (R = -0.281, p=0.130). Optimum pressure settings: There was a strong correlation between the optimum AV delay as defined by the highest ABP and the optimum AVD as defined by the lowest peak CVP (R = 0.672, p=0.03). There was no significant relationship between the optimum AVD delay as defined by peak ABP and the optimum AVD defined by either mean CVP nor CVP AUC (R=0.269, p=0.452 for both). Conclusions There is an inverse relationship between individual measurements of arterial blood pressure and both peak and mean central venous pressure. The optimal AVD as defined by the highest ABP correlates with the optimal AVD as defined by the lowest peak CVP measurement. However, this method does require correction for respiratory artefact.

Arterial spin labeled perfusion imaging with balanced steady-state free precession readout and radial sampling

PurposeTo develop an arterial spin labeling (ASL) perfusion imaging method with balanced steady-state free precession (bSSFP) readout and radial sampling for improved SNR and robustness to motion and off-resonance effects. MethodsAn ASL perfusion imaging method was developed with pseudo-continuous arterial spin labeling (pCASL) and bSSFP readout. Three-dimensional (3D) k-space data were collected in segmented acquisitions following a stack-of-stars sampling trajectory. Multiple phase-cycling technique was utilized to improve the robustness to off-resonance effects. Parallel imaging with sparsity-constrained image reconstruction was used to accelerate imaging or increase the spatial coverage. ResultsASL with bSSFP readout showed higher spatial and temporal SNRs of the gray matter perfusion signal compared to those from spoiled gradient-recalled acquisition (SPGR). Cartesian and radial sampling schemes showed similar spatial and temporal SNRs, regardless of the imaging readout. In case of severe B0 inhomogeneity, single-RF phase incremented bSSFP acquisitions showed banding artifacts. These artifacts were significantly reduced when multiple phase-cycling technique (N = 4) was employed. The perfusion-weighted images obtained by the Cartesian sampling scheme showed respiratory motion-related artifacts when a high segmentation number was used. The perfusion-weighted images obtained by the radial sampling scheme did not show these artifacts. Whole brain perfusion imaging was feasible in 1.15 min or 4.6 min for cases without and with phase-cycling (N = 4), respectively, using the proposed method with parallel imaging. ConclusionsThe developed method allows non-invasive perfusion imaging of the whole-brain with relatively high SNR and robustness to motion and off-resonance effects in a practically feasible imaging time.

An Evaluation of Non-Contact Photoplethysmography-Based Methods for Remote Respiratory Rate Estimation.

The respiration rate (RR) is one of the physiological signals deserving monitoring for assessing human health and emotional states. However, traditional devices, such as the respiration belt to be worn around the chest, are not always a feasible solution (e.g., telemedicine, device discomfort). Recently, novel approaches have been proposed aiming at estimating RR in a less invasive yet reliable way, requiring the acquisition and processing of contact or remote Photoplethysmography (contact reference and remote-PPG, respectively). The aim of this paper is to address the lack of systematic evaluation of proposed methods on publicly available datasets, which currently impedes a fair comparison among them. In particular, we evaluate two prominent families of PPG processing methods estimating Respiratory Induced Variations (RIVs): the first encompasses methods based on the direct extraction of morphological features concerning the RR; and the second group includes methods modeling respiratory artifacts adopting, in the most promising cases, single-channel blind source separation. Extensive experiments have been carried out on the public BP4D+ dataset, showing that the morphological estimation of RIVs is more reliable than those produced by a single-channel blind source separation method (both in contact and remote testing phases), as well as in comparison with a representative state-of-the-art Deep Learning-based approach for remote respiratory information estimation.

Compare image quality of T2-weighted imaging with different phase acceleration factors.

Previous studies demonstrated that adjusting the phase acceleration (PA) factors could influence image quality. To improve image quality and decrease respiratory artifacts of lesions in the liver on T2-weighted image by adjusting PA factor and number of excitation (NEX). Sixty consecutive patients with hepatic lesions were enrolled in this prospective research between May 2020 and June 2020. All patients had 3.0T magnetic resonance imaging with 4 sequences (combining PA factors and NEXs, the former was 2 and 3, the latter were 1.5 and 2, respectively, with the same other scanning parameters). Two readers used 5-point quality scales to assess image quality. The signal intensity was measured by drawing regions of interest in the liver, spleen, and background on the T2-weighted imaging. Artifacts, overall image impression, and vascular conspicuity were better when the PA factor was 3 than 2. Artifacts and vascular conspicuity were better when NEX was 2 than 1.5. PA factor 3 and NEX 2 got a higher score in 5-point quality scales and less scan time than the other 3 sequences. Meanwhile, the signal-to-noise ratio of PA factor 3 and NEX 2 was best among these 4 sequences. PA factor and NEX could influence the imaging quality and lesion-to-hepatic contrast in detecting hepatic lesions on T2-weighted images. PA factor 3 and NEX 2 may have a positive effect in the clinic, especially for those with irregular respiration, as it decreased artifacts and reduced scan time.

Deep learning for improving PET/CT attenuation correction by elastic registration of anatomical data.

For PET/CT, the CT transmission data are used to correct the PET emission data for attenuation. However, subject motion between the consecutive scans can cause problems for the PET reconstruction. A method to match the CT to the PET would reduce resulting artifacts in the reconstructed images. This work presents a deep learning technique for inter-modality, elastic registration of PET/CT images for improving PET attenuation correction (AC). The feasibility of the technique is demonstrated for two applications: general whole-body (WB) imaging and cardiac myocardial perfusion imaging (MPI), with a specific focus on respiratory and gross voluntary motion. A convolutional neural network (CNN) was developed and trained for the registration task, comprising two distinct modules: a feature extractor and a displacement vector field (DVF) regressor. It took as input a non-attenuation-corrected PET/CT image pair and returned the relative DVF between them-it was trained in a supervised fashion using simulated inter-image motion. The 3D motion fields produced by the network were used to resample the CT image volumes, elastically warping them to spatially match the corresponding PET distributions. Performance of the algorithm was evaluated in different independent sets of WB clinical subject data: for recovering deliberate misregistrations imposed in motion-free PET/CT pairs and for improving reconstruction artifacts in cases with actual subject motion. The efficacy of this technique is also demonstrated for improving PET AC in cardiac MPI applications. A single registration network was found to be capable of handling a variety of PET tracers. It demonstrated state-of-the-art performance in the PET/CT registration task and was able to significantly reduce the effects of simulated motion imposed in motion-free, clinical data. Registering the CT to the PET distribution was also found to reduce various types of AC artifacts in the reconstructed PET images of subjects with actual motion. In particular, liver uniformity was improved in the subjects with significant observable respiratory motion. For MPI, the proposed approach yielded advantages for correcting artifacts in myocardial activity quantification and potentially for reducing the rate of the associated diagnostic errors. This study demonstrated the feasibility of using deep learning for registering the anatomical image to improve AC in clinical PET/CT reconstruction. Most notably, this improved common respiratory artifacts occurring near the lung/liver border, misalignment artifacts due to gross voluntary motion, and quantification errors in cardiac PET imaging.

Hitting the Target of Image-Guided Psychiatry?

Hitting the Target of Image-Guided Psychiatry?

Endoscopic Ultrasound Guided Shear Wave Elastography Is Safe With High Feasibility and Reproducibility When Used in the Pancreas: Findings From a Prospective Cohort.

The aim of this study was to assess the safety, feasibility, and reproducibility of endoscopic ultrasound shear wave elastography (EUS-SWE) in the pancreas. This is a prospective registry of consecutive patients undergoing clinically indicated EUS. Ten readings of SWE velocities (Vs [distance/time, m/s]) were obtained in the head (HOP), body, and tail of pancreas to quantify tissue stiffness. Each Vs score was accompanied by a reliability measurement VsN (%) with VsN >50% considered reliable. Safety was evaluated by perioperative complications rate. Feasibility was determined by technical success of obtaining measurements. Reproducibility was evaluated using intraclass correlation coefficient analysis. Total of 3320 EUS-SWE measurements were performed on 117 patients without perioperative complications. Measurement success rate was 100% across all locations. Reliable measurements were more common in the HOP (953/1120 [85.1%]) followed by body (853/1130 [75.5%]) and tail of pancreas (687/1070 [64.2%]) (P < 0.001). The analysis showed good reproducibility in all locations (intraclass correlation coefficient range, 0.80-0.89). Endoscopic ultrasound-SWE is safe, has 100% technical success rate, and is highly reproducible when used in the pancreas. Our study suggests that SWE measurements in the HOP offer the highest reliability, likely because of large study area and less respiratory artifact.

4D Free-Breathing Sequence For The Study Of Pancreatic Lesions In MRI 3 Tesla

Pancreatic cancer is the fourth leading cause of cancer death in both the United States and Europe. A fundamental role in the characterization, early diagnosis, and staging of pancreatic cancer is played by Magnetic Resonance. An innovative and recently implemented sequence, the 4D Free-Breathing sequence, is demonstrating remarkable efficiency in the characterization of pancreatic lesions, as it allows to obtain images with high temporal resolution on the arterial phase, maintaining high spatial and temporal resolution, with the patient free breathing and with compensation of respiratory movement artifacts. The aim of this study was to analyze the 4D Free-Breathing sequence technique and to evaluate its advantages in terms of image quality and diagnostic value in the characterization of pancreatic lesions. The 4D Free Breathing sequence replaces the acquisition of the classic arterial post-contrast phase obtained with the 3D-THRIVE sequence: after a first acquisition of the k-space data in the non-contrast phase (lasting 58 seconds), multiple arterial subphases, each one lasting about 5 seconds, will be acquired with a complete coverage of the post-contrast phase of about 90 seconds. This sequence exploits the k-space sampling technique called "Stack of Stars", based on a radial sampling in the XY plane. In detail, along the slice phase-encoding direction (kz), uniform Cartesian-grid sampling is maintained. Within each kz-encoded plane, radial data is collected with consecutive views (1 per sequence repetition time TR) rotated by a golden-angle of 111.25°, allowing the sampling of a complete circle, also determining a considerably reduced presence of breath artifacts.

4D Free-Breathing Sequence For The Study Of Pancreatic Lesions In MRI 3 Tesla

Pancreatic cancer is the fourth leading cause of cancer death in both the United States and Europe. A fundamental rolein the characterization, early diagnosis, and staging of pancreatic cancer is played by Magnetic Resonance. An innovative and recently implemented sequence, the 4D Free-Breathing sequence, is demonstrating remarkable efficiencyin the characterization of pancreatic lesions, as it allows to obtain images with high temporal resolution on the arterial phase, maintaining high spatial and temporal resolution, with the patient free breathing and with compensationof respiratory movement artifacts. The aim of this study was to analyze the 4D Free-Breathing sequence techniqueand to evaluate its advantages in terms of image quality and diagnostic value in the characterization of pancreaticlesions. The 4D Free Breathing sequence replaces the acquisition of the classic arterial post-contrast phase obtainedwith the 3D-THRIVE sequence: after a first acquisition of the k-space data in the non-contrast phase (lasting 58seconds), multiple arterial subphases, each one lasting about 5 seconds, will be acquired with a complete coverageof the post-contrast phase of about 90 seconds. This sequence exploits the k-space sampling technique called “Stackof Stars”, based on a radial sampling in the XY plane. In detail, along the slice phase-encoding direction (kz), uniform Cartesian-grid sampling is maintained. Within each kz-encoded plane, radial data is collected with consecutiveviews (1 per sequence repetition time TR) rotated by a golden-angle of 111.25°, allowing the sampling of a completecircle, also determining a considerably reduced presence of breath artifacts. The inclusion of the 4D Free-Breathingsequence in the MRI study protocol of the pancreas, through the rapid and consequential acquisitions of 18 arterialphases, allows to improve the diagnostic information contained in the arterial phase, with free breathing, also innon-compliant patients and with correction of breath artifacts

Brachial Plexus Magnetic Resonance Neurography: Technical Challenges and Solutions.

Magnetic resonance neurography of the brachial plexus (BP) is challenging owing to its complex anatomy and technical obstacles around this anatomic region. Magnetic resonance techniques to improve image quality center around increasing nerve-to-background contrast ratio and mitigating imaging artifacts. General considerations include unilateral imaging of the BP at 3.0 T, appropriate selection and placement of surface coils, and optimization of pulse sequences. Technical considerations to improve nerve conspicuity include fat, vascular, and respiratory artifact suppression techniques; metal artifact reduction techniques; and 3-dimensional sequences. Specific optimization of these techniques for BP magnetic resonance neurography greatly improves image quality and diagnostic confidence to help guide nonoperative and operative management.

Non-Contact Heartbeat Detection Based on Ballistocardiogram Using UNet and Bidirectional Long Short-Term Memory.

Benefiting from non-invasive sensing tech- nologies, heartbeat detection from ballistocardiogram (BCG) signals is of great significance for home-care applications, such as risk prediction of cardiovascular disease (CVD) and sleep staging, etc. In this paper, we propose an effective deep learning model for automatic heartbeat detection from BCG signals based on UNet and bidirectional long short-term memory (Bi-LSTM). The developed deep learning model provides an effective solution to the existing challenges in BCG-aided heartbeat detection, especially for BCG in low signal-to-noise ratio, in which the waveforms in BCG signals are irregular due to measured postures, rhythm and artifact motion. For validations, performance of the proposed detection is evaluated by BCG recordings from 43 subjects with different measured postures and heart rate ranges. The accuracy of the detected heartbeat intervals measured in different postures and signal qualities, in comparison with the R-R interval of ECG, is promising in terms of mean absolute error and mean relative error, respectively, which is superior to the state-of-the-art methods. Numerical results demonstrate that the proposed UNet-BiLSTM model performs robust to noise and perturbations (e.g. respiratory effort and artifact motion) in BCG signals, and provides a reliable solution to long term heart rate monitoring.