A preliminary study of super-resolution deep learning reconstruction with cardiac option for evaluation of endovascular-treated intracranial aneurysms.

OBJECTIVES: To investigate the usefulness of super-resolution deep learning reconstruction (SR-DLR) with cardiac option in the assessment of image quality in patients with stent-assisted coil embolization, coil embolization, and flow-diverting stent placement compared with other image reconstructions. METHODS: This single-center retrospective study included fifty patients (mean age, 59 years; range, 44-81 years; 13 men) who were treated with stent-assisted coil embolization, coil embolization, and flow-diverting stent placement between January and July 2023. The images were reconstructed using filtered back projection (FBP), hybrid iterative reconstruction (IR), and SR-DLR. The objective image analysis included image noise in the Hounsfield unit (HU), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and full width at half maximum (FWHM). Subjectively, two radiologists evaluated the overall image quality for the visualization of the flow-diverting stent, coil, and stent. RESULTS: The image noise in HU in SR-DLR was 6.99 ± 1.49, which was significantly lower than that in images reconstructed with FBP (12.32 ± 3.01) and hybrid IR (8.63 ± 2.12) (p < 0.001). Both the mean SNR and CNR were significantly higher in SR-DLR than in FBP and hybrid IR (p < 0.001 and p < 0.001). The FWHMs for the stent (p < 0.004), flow-diverting stent (p < 0.001), and coil (p < 0.001) were significantly lower in SR-DLR than in FBP and hybrid IR. The subjective visual scores were significantly higher in SR-DLR than in other image reconstructions (p < 0.001). CONCLUSIONS: SR-DLR with cardiac option is useful for follow-up imaging in stent-assisted coil embolization and flow-diverting stent placement in terms of lower image noise, higher SNR and CNR, superior subjective image analysis, and less blooming artifact than other image reconstructions. ADVANCES IN KNOWLEDGE: SR-DLR with cardiac option allow better visualization of the peripheral and smaller cerebral arteries. SR-DLR with cardiac option can be beneficial for CT imaging of stent-assisted coil embolization and flow-diverting stent.

Improved stent sharpness evaluation with super-resolution deep learning reconstruction in coronary CT angiography.

OBJECTIVES: This study aimed to assess the impact of super-resolution deep learning reconstruction (SR-DLR) on coronary CT angiography (CCTA) image quality and blooming artifacts from coronary artery stents in comparison to conventional methods, including hybrid iterative reconstruction (HIR) and deep learning-based reconstruction (DLR). METHODS: A retrospective analysis included 66 CCTA patients from July to November 2022. Major coronary arteries were evaluated for image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Stent sharpness was quantified using 10%-90% edge rise slope (ERS) and 10%-90% edge rise distance (ERD). Qualitative analysis employed a 5-point scoring system to assess overall image quality, image noise, vessel wall, and stent structure. RESULTS: SR-DLR demonstrated significantly lower image noise compared to HIR and DLR. SNR and CNR were notably higher in SR-DLR. Stent ERS was significantly improved in SR-DLR, with mean ERD values of 0.70 ± 0.20 mm for SR-DLR, 1.13 ± 0.28 mm for HIR, and 0.85 ± 0.26 mm for DLR. Qualitatively, SR-DLR scored higher in all categories. CONCLUSIONS: SR-DLR produces images with lower image noise, leading to improved overall image quality, compared with HIR and DLR. SR-DLR is a valuable image reconstruction algorithm for enhancing the spatial resolution and sharpness of coronary artery stents without being constrained by hardware limitations. ADVANCES IN KNOWLEDGE: The overall image quality was significantly higher in SR-DLR, resulting in sharper coronary artery stents compared to HIR and DLR.

Coronary artery calcium quantification: comparison between filtered-back projection, hybrid iterative reconstruction, and deep learning reconstruction techniques.

BACKGROUND: The reference protocol for the quantification of coronary artery calcium (CAC) should be updated to meet the standards of modern imaging techniques. PURPOSE: To assess the influence of filtered-back projection (FBP), hybrid iterative reconstruction (IR), and three levels of deep learning reconstruction (DLR) on CAC quantification on both in vitro and in vivo studies. MATERIAL AND METHODS: In vitro study was performed with a multipurpose anthropomorphic chest phantom and small pieces of bones. The real volume of each piece was measured using the water displacement method. In the in vivo study, 100 patients (84 men; mean age = 71.2 ± 8.7 years) underwent CAC scoring with a tube voltage of 120 kVp and image thickness of 3 mm. The image reconstruction was done with FBP, hybrid IR, and three levels of DLR including mild (DLRmild), standard (DLRstd), and strong (DLRstr). RESULTS: In the in vitro study, the calcium volume was equivalent (P = 0.949) among FBP, hybrid IR, DLRmild, DLRstd, and DLRstr. In the in vivo study, the image noise was significantly lower in images that used DLRstr-based reconstruction, when compared images other reconstructions (P < 0.001). There were no significant differences in the calcium volume (P = 0.987) and Agatston score (P = 0.991) among FBP, hybrid IR, DLRmild, DLRstd, and DLRstr. The highest overall agreement of Agatston scores was found in the DLR groups (98%) and hybrid IR (95%) when compared to standard FBP reconstruction. CONCLUSION: The DLRstr presented the lowest bias of agreement in the Agatston scores and is recommended for the accurate quantification of CAC.

The effectiveness of post-processing head and neck CT angiography using contrast enhancement boost technique.

BACKGROUND AND PURPOSE: This study aimed to investigate the potential of contrast enhancement (CE)-boost technique in the head and neck computed tomography (CT) angiography in terms of the objective and subjective image quality. MATERIALS AND METHODS: Consecutive patients who underwent head and neck CT angiography between May 2022 and July 2022 were included. The CE-boost images were generated by combining the subtracted iodinated image and contrast-enhanced image. The objective image analysis was compared for each image with and without CE-boost technique using the CT attenuation, image noise, signal-to-noise-ratio (SNR), contrast-to-noise-ratio (CNR), and image sharpness (full width at half width maximum, FWHM). The subjective image analysis was evaluated by two independent experienced radiologists in the following aspects: the overall image quality, motion artifact, vascular delineation, and vessel sharpness. RESULTS: A total of 65 patients (mean age, 59.48 ± 13.71 years; range, 24-87 years; 36 women) were included. The CT attenuation of the vertebrobasilar arteries was significantly (p < 0.001) higher in the images obtained using CE-boost technique than in conventional images. Image noise was significantly (p < 0.001) lower for CE-boost images (6.09 ± 1.93) than for conventional images (7.79 ± 1.73). Moreover, CE-boost technique yielded higher SNR (64.43 ± 17.17 vs. 121.37 ± 38.77, p < 0.001) and CNR (56.90 ± 18.79 vs. 116.65 ± 57.44, p < 0.001) than conventional images. CE-boost resulted in shorter FWHM than conventional images (p < 0.001). Higher subjective image quality scores were also demonstrated by the CE-boost than images without CE-boost technique. CONCLUSIONS: In both objective and subjective image analysis, the CE-boost technique provided higher image quality without increasing the flow rate and concentration of contrast media in the head and neck CT angiography. Furthermore, the vessel completeness and delineation were superior in CE-boost images than in conventional images.

Effects of Ground Slopes on Erector Spinae Muscle Activities and Characteristics of Golf Swing.

(1) Background: 'Slope' refers to the position faced by golfers on the course. Research on the recruitment strategies of thoracolumbar erector spinae during golf swings on different slopes may help us to understand some underlying mechanisms of lower back pain. (2) Purpose: The purpose of the present study is to assess electromyography (EMG) patterns of the erector spinae muscles (ES) and the kinematics of the trunk and swing parameters while performing golf swings on three different ground slopes: (1) no slope where the ball is level with the feet (BLF), (2) a slope where the ball is above the feet (BAF), and (3) a slope where the ball is below the feet (BBF). Furthermore, the present study evaluates the effect of slope on the kinematics of the trunk, the X-factor angle, and the hitting parameters. (3) Methods: Eight right-handed recreational male golfers completed five swings using a seven-iron for each ground slope. Surface electromyograms from the left and right sides of the ES thoracolumbar region (T8 and L3 on the spinous process side) were evaluated. Each golf swing was divided into five phases. Kinematics of the shoulder, trunk, and spine were evaluated, and the ball speed, swing speed, carry, smash factor, launch angle, and apex were measured using Caddie SC300. (3) Results: The muscle activity of the BAF and BBF slopes was significantly lower than that of the BLF slope during the early follow-through phase of the thoracic ES on the lead side (i.e., left side) and during the acceleration and early follow-through phases of the lumbar ES on the lead side. The lead and trail side (i.e., right side) lumbar ES were more active during acceleration than the thoracic ES. Additionally, the trends of the lead and trail sides of the thoracolumbar regions on the three slopes were found to be the same across the five phases. Trunk angle and X-factor angles had no significant differences in address, top of backswing, or ball impact. The maximum separation angles of the X-factor appeared in the early phase of the downswing for all the three slopes. Regarding smash factor and launch angle, there were no significant differences between the three slopes. The ball speed, swing speed, carry, and apex were higher on BLF than on BAF and BBF slopes. (4) Conclusion: The findings suggest that amateur golfers face different slopes with altered muscle recruitment strategies. Specifically, during the acceleration phase of the golf swing, the BAF and the BBF slopes, compared with the BLF slope, significantly underactivated the lead side thoracolumbar erector spinae muscles, thereby increasing the risk of back injury. Changes in muscle activity during critical periods may affect neuromuscular deficits in high-handicap players and may have implications for the understanding and development of golf-related lower back pain. In addition, the X-factor angle was not affected by the slope, however, it can be found that the hitting parameters on the BLF slope are more dominant than on the other slopes.

Deep learning reconstruction allows for usage of contrast agent of lower concentration for coronary CTA than filtered back projection and hybrid iterative reconstruction.

BACKGROUND: The demand for homogeneous and higher vascular contrast enhancement is critical to provide an appropriate interpretation of abnormal vascular findings in coronary computed tomography angiography (CTA). PURPOSE: To evaluate the effect of various contrast media concentrations (Iohexol-370, Iohexol-300, Iohexol-240) and image reconstructions (filtered back projection [FBP], hybrid iterative reconstruction [IR], and deep learning reconstruction [DLR]) on coronary CTA. MATERIAL AND METHODS: A total of 63 patients referred for coronary CTA between July and October 2021 were enrolled in this prospective study, and they randomly received one of three contrast media. CTA images were reconstructed with FBP, hybrid IR, and DLR. The CT attenuation, image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were calculated for all three images. The images were subjectively evaluated by two radiologists in terms of overall image quality, artifacts, image noise, and vessel wall delineation on a 5-point Likert scale. RESULTS: The application of DLR resulted in significantly lower image noise; higher CT attenuation, SNR, and CNR; and better subjective analysis among the three different concentrations of contrast media groups (P < 0.001). There was no significant difference in the CT attenuation of the left ventricle (P = 0.089) and coronary arteries (P = 0.072) between hybrid IR at Iohexol-300 and DLR at Iohexol-240. Furthermore, application of DLR to the Iohexol-240 significantly improved SNR and CNR; it achieved higher subjective scores compared with hybrid IR at Iohexol-300 (P < 0.001). CONCLUSION: We suggest that using DLR with Iohexol-240 contrast media is preferable to hybrid IR with Iohexol-300 contrast media in coronary CTA.

Improvement in Image Quality and Visibility of Coronary Arteries, Stents, and Valve Structures on CT Angiography by Deep Learning Reconstruction.

OBJECTIVE: This study aimed to investigate whether a deep learning reconstruction (DLR) method improves the image quality, stent evaluation, and visibility of the valve apparatus in coronary computed tomography angiography (CCTA) when compared with filtered back projection (FBP) and hybrid iterative reconstruction (IR) methods. MATERIALS AND METHODS: CCTA images of 51 patients (mean age ± standard deviation [SD], 63.9 ± 9.8 years, 36 male) who underwent examination at a single institution were reconstructed using DLR, FBP, and hybrid IR methods and reviewed. CT attenuation, image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and stent evaluation, including 10%-90% edge rise slope (ERS) and 10%-90% edge rise distance (ERD), were measured. Quantitative data are summarized as the mean ± SD. The subjective visual scores (1 for worst -5 for best) of the images were obtained for the following: overall image quality, image noise, and appearance of stent, vessel, and aortic and tricuspid valve apparatus (annulus, leaflets, papillary muscles, and chordae tendineae). These parameters were compared between the DLR, FBP, and hybrid IR methods. RESULTS: DLR provided higher Hounsfield unit (HU) values in the aorta and similar attenuation in the fat and muscle compared with FBP and hybrid IR. The image noise in HU was significantly lower in DLR (12.6 ± 2.2) than in hybrid IR (24.2 ± 3.0) and FBP (54.2 ± 9.5) (p < 0.001). The SNR and CNR were significantly higher in the DLR group than in the FBP and hybrid IR groups (p < 0.001). In the coronary stent, the mean value of ERS was significantly higher in DLR (1260.4 ± 242.5 HU/mm) than that of FBP (801.9 ± 170.7 HU/mm) and hybrid IR (641.9 ± 112.0 HU/mm). The mean value of ERD was measured as 0.8 ± 0.1 mm for DLR while it was 1.1 ± 0.2 mm for FBP and 1.1 ± 0.2 mm for hybrid IR. The subjective visual scores were higher in the DLR than in the images reconstructed with FBP and hybrid IR. CONCLUSION: DLR reconstruction provided better images than FBP and hybrid IR reconstruction.

A Novel Computed Tomography Image Reconstruction for Improving Visualization of Pulmonary Vasculature: Comparison Between Preprocessing and Postprocessing Images Using a Contrast Enhancement Boost Technique.

OBJECTIVE: This study aimed to evaluate chest computed tomography (CT) angiography image quality using the contrast enhancement (CE)-boost technique compared with conventional images. METHODS: Forty patients who underwent contrast-enhanced chest CT were included. Combined CT angiography images of the iodinated image obtained from the subtraction of nonenhanced CT images and CT angiography images were used to generate CE-boost images. Computed tomography attenuation, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) for the right and left pulmonary arteries as the central and subsegmental arteries as peripheral vessels were assessed. Subjective image quality was rated on a 5-point scale by 2 radiologists. Image quality was assessed using a paired t test. RESULTS: Computed tomography attenuation in the main pulmonary artery was significantly higher for the CE-boost images (311.05 ± 91.94) than for the conventional images (221.25 ± 61.21, P < 0.001). Similarly, the CE-boost images resulted in significantly higher CT attenuation in the subsegmental arteries (right, 305.34 ± 90.13; left, 313.05 ± 97.21) than in the conventional images (right, 218.45 ± 63.16; left, 223.89 ± 74.27). The CE-boost technique demonstrated marked improvement in the visualization of the peripheral pulmonary artery without the administration of a higher iodine delivery rate. The mean SNR and CNR were also significantly higher in the central and peripheral vessels in the CE-boost images than in the conventional images (P < 0.001). In the subjective analysis, the image contrast and vascular contrast edge were significantly higher for the CE-boost images than for conventional images (P < 0.001). CONCLUSIONS: The CE-boost technique increases not only the visualization of peripheral arteries by improving vascular attenuation but also the SNR and CNR.

An equal-TE ultrafast 3D gradient-echo imaging method with high tolerance to magnetic susceptibility artifacts: Application to BOLD functional MRI.

PURPOSE: To develop an ultrafast 3D gradient echo-based MRI method with constant TE and high tolerance to B0 inhomogeneity, dubbed ERASE (equal-TE rapid acquisition with sequential excitation), and to introduce its use in BOLD functional MRI (fMRI). THEORY AND METHODS: Essential features of ERASE, including spin behavior, were characterized, and a comparison study was conducted with conventional EPI. To demonstrate high tolerance to B0 inhomogeneity, in vivo imaging of the mouse brain with a fiber-optic implant was performed at 9.4 T, and human brain imaging (including the orbitofrontal cortex) was performed at 3 T and 7 T. To evaluate the performance of ERASE in BOLD-fMRI, the characteristics of SNR and temporal SNR were analyzed for in vivo rat brains at 9.4 T in comparison with multislice gradient-echo EPI. Percent signal changes and t-scores are also presented. RESULTS: For both mouse brain and human brain imaging, ERASE exhibited a high tolerance to magnetic susceptibility artifacts, showing much lower distortion and signal dropout, especially in the regions involving large magnetic susceptibility effects. For BOLD-fMRI, ERASE provided higher temporal SNR and t-scores than EPI, but exhibited similar percent signal changes in in vivo rat brains at 9.4 T. CONCLUSION: When compared with conventional EPI, ERASE is much less sensitive, not only to EPI-related artifacts such as Nyquist ghosting, but also to B0 inhomogeneity including magnetic susceptibility effects. It is promising for use in BOLD-fMRI, providing higher temporal SNR and t-scores with constant TE when compared with EPI, although further optimization is needed for human fMRI.

Improvement of depiction of the intracranial arteries on brain CT angiography using deep learning reconstruction.

To evaluate the ability of a commercialized deep learning reconstruction technique to depict intracranial vessels on the brain computed tomography angiography and compare the image quality with filtered-back-projection and hybrid iterative reconstruction in terms of objective and subjective measures. Forty-three patients underwent brain computed tomography angiography, and images were reconstructed using three algorithms: filtered-back-projection, hybrid iterative reconstruction, and deep learning reconstruction. The image noise, computed tomography attenuation value, signal-to-noise ratio, and contrast-to-noise ratio were measured in the bilateral cavernous segment of the internal carotid artery, vertebral artery, basilar apex, horizontal segment of the middle cerebral artery and used for the objective assessment of the image quality among the three different reconstructions. The subjective image quality score was significantly higher for the deep learning reconstruction than hybrid iterative reconstruction and filtered-back-projection images. The deep learning reconstruction markedly improved the reduction of blooming artifacts in surgical clips and coiled aneurysms. The deep learning reconstruction method generally improves the image quality of brain computed tomography angiography in terms of objective measurement and subjective grading compared with filtered-back-projection and hybrid iterative reconstruction. Especially, deep learning reconstruction is deemed advantageous for better depiction of small vessels compared to filtered-back projection and hybrid iterative reconstruction.

k-Space deep learning for reference-free EPI ghost correction.

PURPOSE: Nyquist ghost artifacts in echo planar imaging (EPI) are originated from phase mismatch between the even and odd echoes. However, conventional correction methods using reference scans often produce erroneous results especially in high-field MRI due to the nonlinear and time-varying local magnetic field changes. Recently, it was shown that the problem of ghost correction can be reformulated as k-space interpolation problem that can be solved using structured low-rank Hankel matrix approaches. Another recent work showed that data driven Hankel matrix decomposition can be reformulated to exhibit similar structures as deep convolutional neural network. By synergistically combining these findings, we propose a k-space deep learning approach that immediately corrects the phase mismatch without a reference scan in both accelerated and non-accelerated EPI acquisitions. THEORY AND METHODS: To take advantage of the even and odd-phase directional redundancy, the k-space data are divided into 2 channels configured with even and odd phase encodings. The redundancies between coils are also exploited by stacking the multi-coil k-space data into additional input channels. Then, our k-space ghost correction network is trained to learn the interpolation kernel to estimate the missing virtual k-space data. For the accelerated EPI data, the same neural network is trained to directly estimate the interpolation kernels for missing k-space data from both ghost and subsampling. RESULTS: Reconstruction results using 3T and 7T in vivo data showed that the proposed method outperformed the image quality compared to the existing methods, and the computing time is much faster. CONCLUSIONS: The proposed k-space deep learning for EPI ghost correction is highly robust and fast, and can be combined with acceleration, so that it can be used as a promising correction tool for high-field MRI without changing the current acquisition protocol.

A new ultrafast 3D gradient echo-based imaging method using quadratic-phase encoding.

PURPOSE: To propose a novel 3D ultrafast gradient echo-based MRI method, dubbed RASE, using quadratic-phase encoding. THEORY AND METHODS: Several characteristics of RASE, including spin behaviors, spatial resolution, SNR, and reduction of susceptibility-induced signal loss, were analytically described. A way of compensating for TE variation was suggested in the quadratic phase-encoding direction. Lemon, in vivo rat and mouse images were demonstrated at 9.4T, including a feasibility study for DCE-MRI as one of promising applications. RESULTS: RASE was successfully demonstrated by lemon and in vivo rat brain imaging, showing a good robustness to field inhomogeneity. Contribution of the quadratic phase to signal enhancement in a range of magnetic susceptibilities was also evaluated by simulation. Taking a geometric mean of 2 phantom data acquired with opposite gradient polarities effectively compensated for the effect of TE variation. Preliminary DCE-MRI results were also presented, showing that RASE could more accurately estimate Gd concentration than FLASH. CONCLUSION: RASE offers a shorter effective TE, having less sensitivity to field inhomogeneity and T2* effects, much less Nyquist ghosting or chemical-shift artifacts than gradient echo EPI (GE-EPI). We highly anticipate that RASE can be an alternative to GE-EPI in many applications, particularly those requiring high spatial and temporal resolutions in a broad volume coverage.

Inter-vender and test-retest reliabilities of resting-state functional magnetic resonance imaging: Implications for multi-center imaging studies.

This prospective multi-center study aimed to evaluate the inter-vendor and test-retest reliabilities of resting-state functional magnetic resonance imaging (RS-fMRI) by assessing the temporal signal-to-noise ratio (tSNR) and functional connectivity. Study included 10 healthy subjects and each subject was scanned using three 3T MR scanners (GE Signa HDxt, Siemens Skyra, and Philips Achieva) in two sessions. The tSNR was calculated from the time course data. Inter-vendor and test-retest reliabilities were assessed with intra-class correlation coefficients (ICCs) derived from variant component analysis. Independent component analysis was performed to identify the connectivity of the default-mode network (DMN). In result, the tSNR for the DMN was not significantly different among the GE, Philips, and Siemens scanners (P=0.638). In terms of vendor differences, the inter-vendor reliability was good (ICC=0.774). Regarding the test-retest reliability, the GE scanner showed excellent correlation (ICC=0.961), while the Philips (ICC=0.671) and Siemens (ICC=0.726) scanners showed relatively good correlation. The DMN pattern of the subjects between the two sessions for each scanner and between three scanners showed the identical patterns of functional connectivity. The inter-vendor and test-retest reliabilities of RS-fMRI using different 3T MR scanners are good. Thus, we suggest that RS-fMRI could be used in multicenter imaging studies as a reliable imaging marker.