High resolution simulation and measurement demonstrate oscillatory spatiotemporal B0 fluctuations across the human cardiac cycle.

PURPOSE: Functional cardiac MRI scans employing balanced steady-state free precession sequences suffer from dark band artifacts in the myocardium due to B0 inhomogeneity. We recently introduced a novel method for the theoretical derivation of B0 distributions in the human heart. This study aims to simulate the B0 distributions in the heart across the cardiac cycle using structural MR images and validate the simulations via in vivo measured cardiac phase-specific B0 maps on the same subjects at 3T. METHODS: Cardiac phase-specific B0 field maps were acquired from eight healthy subjects at 3T. B0 conditions were simulated based on tissue masks created from the cardiac-phase specific structural images from the in vivo B0 map scan and anatomical images from a thoracic MRI scan, adopting our recently published approach. The simulations and in vivo measurements were compared by calculating the spatial correlation of their B0 distributions and temporal correlation of the derived spherical harmonic coefficients throughout the cardiac cycle. RESULTS: The spatial comparison of B0 maps between the simulation and in vivo measurement indicates an overall average correlation coefficient of 0.91 across the cardiac cycle in all subjects. Both groups show consistent high-level B0 patterns. Temporal variations of B0 conditions exhibit sinusoidal characteristics and are strongly correlated between simulation and in vivo. CONCLUSION: Theoretical simulations employing regional anatomical features were validated by direct in vivo B0 mapping in the same subjects. The spatial B0 condition throughout the cardiac cycle exhibits oscillatory characteristics due to structural distortions of cardiac motion.

Prospective motion correction for cervical spinal cord MRS.

PURPOSE: To develop prospective motion correction for single-voxel MRS in the human cervical spinal cord. METHODS: A motion MR navigator was implemented using reduced field-of-view 2D-selective RF excitation together with EPI readout. A short-echo semi-LASER sequence (TE = 30 ms) was updated to incorporate this real-time image-based motion navigator, as well as real-time shim and frequency navigators. Five healthy participants were studied at 3 T with a 64-channel head-neck receive coil. Single-voxel MRS data were measured in a voxel located at the C3-5 vertebrae level. The motion navigator was used to correct for translations in the X-Y plane and was validated by assessing spectral quality with and without prospective correction in the presence of subject motion. RESULTS: Without prospective correction, motion resulted in severe lipid contamination in the MR spectra. With prospective correction, the quality of spinal cord MR spectra in the presence of motion was similar to that obtained in the absence of motion, with comparable spectral signal-to-noise ratio and linewidth and no significant lipid contamination. CONCLUSION: Prospective motion and B0 correction allow acquisition of good-quality MR spectra in the human cervical spinal cord in the presence of motion. This new technique should facilitate reliable acquisition of spinal cord MR spectra in both research and clinical settings.

Speech production real-time MRI at 0.55 T.

PURPOSE: To demonstrate speech-production real-time MRI (RT-MRI) using a contemporary 0.55T system, and to identify opportunities for improved performance compared with conventional field strengths. METHODS: Experiments were performed on healthy adult volunteers using a 0.55T MRI system with high-performance gradients and a custom 8-channel upper airway coil. Imaging was performed using spiral-based balanced SSFP and gradient-recalled echo (GRE) pulse sequences using a temporal finite-difference constrained reconstruction. Speech-production RT-MRI was performed with three spiral readout durations (8.90, 5.58, and 3.48 ms) to determine trade-offs with respect to articulator contrast, blurring, banding artifacts, and overall image quality. RESULTS: Both spiral GRE and bSSFP captured tongue boundary dynamics during rapid consonant-vowel syllables. Although bSSFP provided substantially higher SNR in all vocal tract articulators than GRE, it suffered from banding artifacts at TR > 10.9 ms. Spiral bSSFP with the shortest readout duration (3.48 ms, TR = 5.30 ms) had the best image quality, with a 1.54-times boost in SNR compared with an equivalent GRE sequence. Longer readout durations led to increased SNR efficiency and blurring in both bSSFP and GRE. CONCLUSION: High-performance 0.55T MRI systems can be used for speech-production RT-MRI. Spiral bSSFP can be used without suffering from banding artifacts in vocal tract articulators, provide better SNR efficiency, and have better image quality than what is typically achieved at 1.5 T or 3 T.

Eddy current-induced artifact correction in high b-value ex vivo human brain diffusion MRI with dynamic field monitoring.

PURPOSE: To investigate whether spatiotemporal magnetic field monitoring can correct pronounced eddy current-induced artifacts incurred by strong diffusion-sensitizing gradients up to 300 mT/m used in high b-value diffusion-weighted (DW) EPI. METHODS: A dynamic field camera equipped with 16 1 H NMR field probes was first used to characterize field perturbations caused by residual eddy currents from diffusion gradients waveforms in a 3D multi-shot EPI sequence on a 3T Connectom scanner for different gradient strengths (up to 300 mT/m), diffusion directions, and shots. The efficacy of dynamic field monitoring-based image reconstruction was demonstrated on high-gradient strength, submillimeter resolution whole-brain ex vivo diffusion MRI. A 3D multi-shot image reconstruction framework was developed that incorporated the nonlinear phase evolution measured with the dynamic field camera. RESULTS: Phase perturbations in the readout induced by residual eddy currents from strong diffusion gradients are highly nonlinear in space and time, vary among diffusion directions, and interfere significantly with the image encoding gradients, changing the k-space trajectory. During the readout, phase modulations between odd and even EPI echoes become non-static and diffusion encoding direction-dependent. Superior reduction of ghosting and geometric distortion was achieved with dynamic field monitoring compared to ghosting reduction approaches such as navigator- and structured low-rank-based methods or MUSE followed by image-based distortion correction with the FSL tool "eddy." CONCLUSION: Strong eddy current artifacts characteristic of high-gradient strength DW-EPI can be well corrected with dynamic field monitoring-based image reconstruction.

Characterization of concomitant gradient fields and their effects on image distortions using a low-field point-of-care Halbach-based MRI system.

PURPOSE: Concomitant gradient fields have been extensively studied at clinical field strengths. However, their effects have not yet been modeled for low-field point-of-care (POC) systems. The purpose of this work is to characterize the effects associated with concomitant fields for POC Halbach-array-based systems. METHODS: The concomitant fields associated with a cylindrical gradient coils designed for a transverse B 0 $$ {B}_0 $$ and a signal model including the tilting effect of the effective magnetic field are derived. The formalism is used to simulate and predict concomitant field related distortions. A 46-mT Halbach-array-based system with a maximum gradient strength of 15 mT/m is used to verify the model using two-dimensional spin-echo sequences. RESULTS: The simulations and experimental results are in good agreement with the derived equations. The fundamental characteristics of the concomitant field equations are different to conventional MRI systems: Image distortions occur primarily in the transverse directions and a cross-term only exists when applying transverse gradient pulses simultaneously. CONCLUSION: The level of image warping in the frequency encoding direction is insignificant for the POC systems discussed here. However, when trying to achieve short echo-times by using strong phase encoding and readout-dephasing gradients, the combination can result in image warping and blurring which should be accounted for in image interpretation.

Multi-echo-based fat artifact correction for CEST MRI at 7 T.

PURPOSE: CEST MRI is influenced by fat signal, which can reduce the apparent CEST contrast or lead to pseudo-CEST effects. Our goal was to develop a fat artifact correction based on multi-echo fat-water separation that functions stably for 7 T knee MRI data. METHODS: Our proposed algorithm utilizes the full complex data and a phase demodulation with an off-resonance map estimation based on the Z-spectra prior to fat-water separation to achieve stable fat artifact correction. Our method was validated and compared to multi-echo-based methods originally proposed for 3 T by Bloch-McConnell simulations and phantom measurements. Moreover, the method was applied to in vivo 7 T knee MRI examinations and compared to Gaussian fat saturation and a published single-echo Z-spectrum-based fat artifact correction method. RESULTS: Phase demodulation prior to fat-water separation reduced the occurrence of fat-water swaps. Utilizing the complex signal data led to more stable correction results than working with magnitude data, as was proposed for 3 T. Our approach reduced pseudo-nuclear Overhauser effects compared to the other correction methods. Thus, the mean asymmetry contrast at 3.5 ppm in cartilage over five volunteers increased from -9.2% (uncorrected) and -10.6% (Z-spectrum-based) to -1.5%. Results showed higher spatial stability than with the fat saturation pulse. CONCLUSION: Our work demonstrates the feasibility of multi-echo-based fat-water separation with an adaptive fat model for fat artifact correction for CEST MRI at 7 T. Our approach provided better fat artifact correction throughout the entire spectrum and image than the fat saturation pulse or Z-spectrum-based correction method for both phantom and knee imaging results.

FD-Net: An unsupervised deep forward-distortion model for susceptibility artifact correction in EPI.

PURPOSE: To introduce an unsupervised deep-learning method for fast and effective correction of susceptibility artifacts in reversed phase-encode (PE) image pairs acquired with echo planar imaging (EPI). METHODS: Recent learning-based correction approaches in EPI estimate a displacement field, unwarp the reversed-PE image pair with the estimated field, and average the unwarped pair to yield a corrected image. Unsupervised learning in these unwarping-based methods is commonly attained via a similarity constraint between the unwarped images in reversed-PE directions, neglecting consistency to the acquired EPI images. This work introduces a novel unsupervised deep Forward-Distortion Network (FD-Net) that predicts both the susceptibility-induced displacement field and the underlying anatomically correct image. Unlike previous methods, FD-Net enforces the forward-distortions of the correct image in both PE directions to be consistent with the acquired reversed-PE image pair. FD-Net further leverages a multiresolution architecture to maintain high local and global performance. RESULTS: FD-Net performs competitively with a gold-standard reference method (TOPUP) in image quality, while enabling a leap in computational efficiency. Furthermore, FD-Net outperforms recent unwarping-based methods for unsupervised correction in terms of both image and field quality. CONCLUSION: The unsupervised FD-Net method introduces a deep forward-distortion approach to enable fast, high-fidelity correction of susceptibility artifacts in EPI by maintaining consistency to measured data. Therefore, it holds great promise for improving the anatomical accuracy of EPI imaging.

Translatome Profiling of Tissue-Resident Macrophages Using the RiboTag Approach.

Global gene expression profiling has provided valuable insights into the specific contributions of different cell types to various physiological processes. Notably though, both bulk and single-cell transcriptomics require the prior retrieval of the cells from their tissue context to be analyzed. Isolation protocols for tissue macrophages are, however, notoriously inefficient and, moreover, prone to introduce considerable bias and artifacts. Here, we will discuss a valuable alternative, originally introduced by Amieux and colleagues. This so-called RiboTag approach allows, in combination with respective macrophage-specific Cre transgenic lines, to retrieve macrophage translatomes from crude tissue extracts. We will review our experience with this ingenious method, focusing on the study of brain macrophages, including microglia and border-associated cells. We will elaborate on the advantages of the RiboTag approach that render it a valuable complement to standard cell sorting-based profiling strategies, especially for the investigation of tissue macrophages.

Images: Polysomnographic artifact in a patient with Tourette syndrome.

Patients with Tourette syndrome frequently have sleep disturbances that may require polysomnographic testing. The use of deep brain stimulators is increasing with expanding indications including children with medically intractable Tourette syndrome. It is important to understand the effect the stimulator can have on polysomnographic monitoring. Herein we present an interesting case of an adolescent with medically intractable Tourette syndrome with a deep brain stimulator implant who underwent a polysomnogram demonstrating rhythmic, monomorphic artifact. CITATION: Bindra T, Ingram DG. Images: Polysomnographic artifact in a patient with Tourette syndrome. J Clin Sleep Med. 2023;19(12):2149-2151.

[Effects of metal materials for oral fixation and restoration on magnetic resonance imaging artifacts and the health of tissues around dental implants].

PURPOSE: To investigate the effects of metal materials for oral fixation and restoration on magnetic resonance imaging artifacts and the health of tissues around dental implants. METHODS: A total of 153 patients undergoing fixed oral restoration were selected from May 2018 to June 2020. They were divided according to the random number table method into group A (cobalt-chromium alloy, n=31), group B (nickel-chromium alloy, n=32), group C (titanium alloy, n=28), group D (pure titanium, n=29) and group E (gold alloy, n=33). The largest area of metal crown artifacts and the number of layers of the 5 groups were compared. The probing depth(PD), modified plaque index(mPLI), modified sulcus bleeding index(mSBI) and papilla index(PI) 6 months after restoration were evaluated.The data were statistically analyzed with SPSS 22.0 software package. RESULTS: One-way ANOVA showed that the largest area of metal crown artifacts and the number of layers involved in the 5 groups had significant differences(P＜0.05). Pairwise comparison showed that the largest area of metal crown artifacts, and the number of involved layers in group E were significantly lower than those in groups A, B, C, and D(P＜0.05). One-way ANOVA showed that there was no significant difference in PD, mPLI, mSBI and PI among 5 groups (P＞0.05). Pairwise comparison showed that there was no significant difference in PD, mPLI, mSBI and PI between group A and group B,C,D and E (P＞0.05). CONCLUSIONS: The artifacts produced by metal materials for oral fixation and restoration are closely related to the types of metal materials. Among them, cobalt-chromium alloys produce the largest artifacts, and gold alloys produce the smallest artifacts. The use of metal materials for oral fixation and restoration will not affect the health of tissues around dental implants.

Artifact Correction in Retinal Nerve Fiber Layer Thickness Maps Using Deep Learning and Its Clinical Utility in Glaucoma.

Purpose: Correcting retinal nerve fiber layer thickness (RNFLT) artifacts in glaucoma with deep learning and evaluate its clinical usefulness. Methods: We included 24,257 patients with optical coherence tomography and reliable visual field (VF) measurements within 30 days and 3,233 patients with reliable VF series of at least five measurements over ≥4 years. The artifacts are defined as RNFLT less than the known floor value of 50 µm. We selected 27,319 high-quality RNFLT maps with an artifact ratio (AR) of <2% as the ground truth. We created pseudo-artifacts from 21,722 low-quality RNFLT maps with AR of >5% and superimposed them on high-quality RNFLT maps to predict the artifact-free ground truth. We evaluated the impact of artifact correction on the structure-function relationship and progression forecasting. Results: The mean absolute error and Pearson correlation of the artifact correction were 9.89 µm and 0.90 (P < 0.001), respectively. Artifact correction improved R2 for VF prediction in RNFLT maps with AR of >10% and AR of >20% up to 0.03 and 0.04 (P < 0.001), respectively. Artifact correction improved (P < 0.05) the AUC for progression prediction in RNFLT maps with AR of ≤10%, >10%, and >20%: (1) total deviation pointwise progression: 0.68 to 0.69, 0.62 to 0.63, and 0.62 to 0.64; and (2) mean deviation fast progression: 0.67 to 0.68, 0.54 to 0.60, and 0.45 to 0.56. Conclusions: Artifact correction for RNFLTs improves VF and progression prediction in glaucoma. Translational Relevance: Our model improves clinical usability of RNFLT maps with artifacts.

VoxMore: technological artifact to assist voice acoustic evaluation in the teaching-learning process and clinical practice. / VoxMore: artefato tecnológico para auxiliar a avaliação acústica da voz no processo ensino-aprendizagem e prática clínica.

PURPOSE: to present a technological artifact, the VoxMore plugin, to assist the academic teaching of voice acoustic assessment, as well as to optimize the speech therapy intervention in the practice of vocal clinics. METHODS: this is a multidisciplinary methodological study for the development of a technological artifact, a plugin, to be used in the Praat software. This tool performs vocal acoustic analysis and generates a report, with information and images referring to the domains of time, frequency, time-frequency, and que-frequency, as well as values of acoustic measures related to fundamental frequency (f0), period measures, disturbance measures of the period of f0, f0 amplitude perturbation measurements, spectral measurements, glottal noise measurements and cepstral measurements. RESULTS: in the VoxMore acoustic report, four files are generated with the following information: oscillograms of the voice signal and traces of f0 and intensity; images related to the frequency domain, Fourier spectrum and LPC spectrum, and to the time-frequency domain, spectrogram; information on cepstral and cepstrogram analysis; the values of all acoustic measurements, in numerical results format and in vertical bar graphs. CONCLUSION: VoxMore can contribute both to the teaching-learning process, acting as an auxiliary tool with a formative character in the undergraduate and graduate courses in Speech-Language Pathology, as well as to the clinical practice process, making the use of acoustic analysis in the vocal clinic feasible and supporting decision-making by speech-language pathologist.

OBJETIVO: apresentar um artefato tecnológico, o plugin VoxMore, para auxiliar o ensino acadêmico da avaliação acústica da voz, bem como otimizar a intervenção fonoaudiológica na prática da clínica vocal. MÉTODO: trata-se de um estudo metodológico de caráter multidisciplinar para o desenvolvimento de um artefato tecnológico, plugin, a ser utilizado no software Praat. Essa ferramenta realiza análise acústica vocal e gera um relatório, com informações e imagens referentes aos domínios do tempo, frequência, tempo-frequência, e quefrência, bem como valores de medidas acústicas relacionadas a frequência fundamental (f0), medidas de período, medidas de perturbação do período da f0, medidas de perturbação de amplitude da f0, medidas espectrais, medidas de ruído glotal e medidas cepstrais. RESULTADOS: no relatório acústico do VoxMore são gerados quatro arquivos com as seguintes informações: oscilogramas do sinal de voz e traçados da f0 e intensidade; imagens relacionadas ao domínio da frequência, espectro de Fourier e espectro de LPC, e ao domínio do tempo-frequência, espectrograma; informações sobre a análise cepstral e cepstrograma; valores de todas as medidas acústicas, no formato de resultados numéricos e em gráficos de barras verticais. CONCLUSÃO: o VoxMore pode contribuir tanto com o processo de ensino-aprendizagem, atuando como ferramenta auxiliar com caráter formativo nas disciplinas de graduação e pós-graduação em Fonoaudiologia, quanto com o processo da prática clínica, tornando viável a utilização da análise acústica na clínica vocal e apoiando a tomada de decisão dos fonoaudiólogos.

Accurate exclusion of kidney regions affected by susceptibility artifact in blood oxygenation level-dependent (BOLD) images using deep-learning-based segmentation.

Susceptibility artifact (SA) is common in renal blood oxygenation level-dependent (BOLD) images, and including the SA-affected region could induce much error in renal oxygenation quantification. In this paper, we propose to exclude kidney regions affected by SA in gradient echo images with different echo times (TE), based on a deep-learning segmentation approach. For kidney segmentation, a ResUNet was trained with 4000 CT images and then tuned with 60 BOLD images. Verified by a Monte Carlo simulation, the presence of SA leads to a bilinear pattern for the segmented area of kidney as function of TE, and the segmented kidney in the image of turning point's TE would exclude SA-affected regions. To evaluate the accuracy of excluding SA-affected regions, we compared the SA-free segmentations by the proposed method against manual segmentation by an experienced user for BOLD images of 35 subjects, and found DICE of 93.9% ± 3.4%. For 10 kidneys with severe SA, the DICE was 94.5% ± 1.7%, for 14 with moderate SA, 92.8% ± 4.7%, and for 46 with mild or no SA, 94.3% ± 3.8%. For the three sub-groups of kidneys, correction of SA led to a decrease of R2* of 8.5 ± 2.8, 4.7 ± 1.8, and 1.6 ± 0.9 s-1, respectively. In conclusion, the proposed method is capable of segmenting kidneys in BOLD images and at the same time excluding SA-affected region in a fully automatic way, therefore can potentially improve both speed and accuracy of the quantification procedure of renal BOLD data.

Exploring the impact of mobility and selection on stone tool recycling behaviors through agent-based simulation.

Recycling behaviors are becoming increasingly recognized as important parts of the production and use of stone tools in the Paleolithic. Yet, there are still no well-defined expectations for how recycling affects the appearance of the archaeological record across landscapes. Using an agent-based model of recycling in surface contexts, this study looks how the archaeological record changes under different conditions of recycling frequency, occupational intensity, mobility, and artifact selection. The simulations also show that while an increased number of recycled artifacts across a landscape does indicate the occurrence of more scavenging and recycling behaviors generally, the location of large numbers of recycled artifacts is not necessarily where the scavenging itself happened. This is particularly true when mobility patterns mean each foraging group spend more time moving around the landscape. The results of the simulations also demonstrate that recycled artifacts are typically those that have been exposed longer in surface contexts, confirming hypothesized relationships between recycling and exposure. In addition to these findings, the recycling simulation shows how archaeological record formation due to recycling behaviors is affected by mobility strategies and selection preferences. While only a simplified model of recycling behaviors, the results of this simulations give us insight into how to better interpret recycling behaviors from the archaeological record, specifically demonstrating the importance of contextualizing the occurrence of recycled artifacts on a wider landscape-level scale.

Influence of demographic factors on the occurrence of motion artefacts in HR-pQCT.

The study shows a high incidence of motion artefacts in a central European population and a significant increase of those artefacts with higher age. These findings may impact on the design and conduct of future in vivo HR-pQCT studies or at least help to estimate the potential number of drop outs due to unusable image quality. PURPOSE: Motion artefacts in high-resolution peripheral quantitative computed tomography (HR-pQCT) are challenging, as they introduce error into the resulting measurement data. The aim of this study was to assess the general occurrence of motion artefacts in healthy distal radius and to evaluate the influence of demographic factors. METHODS: The retrospective study is based on 525 distal radius second-generation HR-pQCT scans of 95 patients. All stacks were evaluated by two experienced observers and graded according to the visual grading scale recommended by the manufacturer, ranging from grade 1 (no visible motion artefacts) to grade 5 (severe motion artefacts). Correlations between demographic factors and image quality were evaluated using a linear mixed effects model analysis. RESULTS: The average visual grading was 2.7 (SD ± 0.7). Age and severity of motion artefacts significantly correlated (p = 0.026). Patients aged 65 years or above had an average image quality between grades 1 and 3 in 72.7% of cases, while patients younger than 65 had an average image quality between grades 1 and 3 in 91.9% of cases. Gender, smoking behaviour, and handedness had no significant influence on motion artefacts. CONCLUSION: This study showed a high incidence of motion artefacts in a representative central European population, but also a significant increase of motion artefacts with higher age. This could impact further study designs by planning for a sufficiently large and if possible a more selective study population to gain a representative amount of high-quality image data.

A Lightweight Deep Learning Framework for Automatic MRI Data Sorting and Artifacts Detection.

The purpose of this study is to develop a lightweight and easily deployable deep learning system for fully automated content-based brain MRI sorting and artifacts detection. 22092 MRI volumes from 4076 patients between 2017 and 2021 were involved in this retrospective study. The dataset mainly contains 4 common contrast (T1-weighted (T1w), contrast-enhanced T1-weighted (T1c), T2-weighted (T2w), fluid-attenuated inversion recovery (FLAIR)) in three perspectives (axial, coronal, and sagittal), and magnetic resonance angiography (MRA), as well as three typical artifacts (motion, aliasing, and metal artifacts). In the proposed architecture, a pre-trained EfficientNetB0 with the fully connected layers removed was used as the feature extractor and a multilayer perceptron (MLP) module with four hidden layers was used as the classifier. Precision, recall, F1_Score, accuracy, the number of trainable parameters, and float-point of operations (FLOPs) were calculated to evaluate the performance of the proposed model. The proposed model was also compared with four other existing CNN-based models in terms of classification performance and model size. The overall precision, recall, F1_Score, and accuracy of the proposed model were 0.983, 0.926, 0.950, and 0.991, respectively. The performance of the proposed model was outperformed the other four CNN-based models. The number of trainable parameters and FLOPs were the smallest among the investigated models. Our proposed model can accurately sort head MRI scans and identify artifacts with minimum computational resources and can be used as a tool to support big medical imaging data research and facilitate large-scale database management.

A pathological lesion or a postmortem artefact? An interdisciplinary approach to deal with an interesting early medieval case.

OBJECTIVE: This study evaluates a case of pseudopathology and the effects that postmortem taphonomic changes and environmental influences can have on bone. MATERIAL: A skeleton of a young male from the early medieval site Staré Mesto, dated to the 9th-10th century CE. METHODS: The skeletal remains were subjected to detailed macroscopic and X-ray examination, and then a CT scan and XRF analysis were performed. RESULTS: X-ray examination of the mandible revealed unusually dense structures, whose appearance was not consistent with any known pathology. Based on the results of CT scanning, it was hypothesized that these were cavities filled with alluvial sediment. X-ray fluorescence spectrometry (XRF), focusing on the determination of the silica content, revealed a high intensity of silica in the samples of the affected area of the bone. CONCLUSION: The hypothesis that the inclusions were composed of waterborne sediment was supported. SIGNIFICANCE: Although it is well known that soil can infiltrate bones buried in the ground, its appearance on plain radiographs is not that commonly known. The case illustrates the usefulness of differentiating true pathologies from postmortem alterations to avoid inappropriate interpretations. LIMITATIONS: No similar cases have been described. SUGGESTION FOR FURTHER RESEARCH: In palaeopathological evaluation, the use of multiple imaging and evaluative techniques should be implemented to differentiate pathological lesions from pseudopathology.

A dual-stage partially interpretable neural network for joint suppression of bSSFP banding and flow artifacts in non-phase-cycled cine imaging.

PURPOSE: To develop a partially interpretable neural network for joint suppression of banding and flow artifacts in non-phase-cycled bSSFP cine imaging. METHODS: A dual-stage neural network consisting of a voxel-identification (VI) sub-network and artifact-suppression (AS) sub-network is proposed. The VI sub-network provides identification of artifacts, which guides artifact suppression and improves interpretability. The AS sub-network reduces banding and flow artifacts. Short-axis cine images of 12 frequency offsets from 28 healthy subjects were used to train and test the dual-stage network. An additional 77 patients were retrospectively enrolled to evaluate its clinical generalizability. For healthy subjects, artifact suppression performance was analyzed by comparison with traditional phase cycling. The partial interpretability provided by the VI sub-network was analyzed via correlation analysis. Generalizability was evaluated for cine obtained with different sequence parameters and scanners. For patients, artifact suppression performance and partial interpretability of the network were qualitatively evaluated by 3 clinicians. Cardiac function before and after artifact suppression was assessed via left ventricular ejection fraction (LVEF). RESULTS: For the healthy subjects, visual inspection and quantitative analysis found a considerable reduction of banding and flow artifacts by the proposed network. Compared with traditional phase cycling, the proposed network improved flow artifact scores (4.57 ± 0.23 vs 3.40 ± 0.38, P = 0.002) and overall image quality (4.33 ± 0.22 vs 3.60 ± 0.38, P = 0.002). The VI sub-network well identified the location of banding and flow artifacts in the original movie and significantly correlated with the change of signal intensities in these regions. Changes of imaging parameters or the scanner did not cause a significant change of overall image quality relative to the baseline dataset, suggesting a good generalizability. For the patients, qualitative analysis showed a significant improvement of banding artifacts (4.01 ± 0.50 vs 2.77 ± 0.40, P < 0.001), flow artifacts (4.22 ± 0.38 vs 2.97 ± 0.57, P < 0.001), and image quality (3.91 ± 0.45 vs 2.60 ± 0.43, P < 0.001) relative to the original cine. The artifact suppression slightly reduced the LVEF (mean bias = -1.25%, P = 0.01). CONCLUSIONS: The dual-stage network simultaneously reduces banding and flow artifacts in bSSFP cine imaging with a partial interpretability, sparing the need for sequence modification. The method can be easily deployed in a clinical setting to identify artifacts and improve cine image quality.