Compressed sensing for body MRI

Acceleration of uterine 3D T2-weighted imaging by compressed SENSE-a multicentre study

OBJECTIVES

To find the optimal acceleration factor (AF) of the compressed SENSE (CS) technique for uterine isotropic high-resolution 3D T2-weighted imaging (3D-ISO-T2WI).

METHODS

A total of 91 female volunteers from the First Affiliated Hospital of Dalian Medical University, Chu Hsien-I Memorial Hospital and Tianjin Institute of Endocrinology, and The Fourth Hospital of Harbin were recruited. A total of 44 volunteers received uterus sagittal 3D-ISO-T2WI scans on 3.0T MRI device with different CS AFs (including SENSE3, CS3, CS4, CS5, CS6, and CS7), 51 received 3D-ISO-T2WI scans with different degrees of fat suppression (none, light, moderate, and severe), while 4 volunteers received both series of scans. Image quality was subjectively evaluated with a 3-point scoring system. Junction zone signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and myometrial SNR were also calculated. Intraclass correlation coefficients were used to analyse the consistency of the measurement results by 2 observers. Analysis of variance test or Friedman rank sum test was used to compare the differences in subjective scores, SNR, and CNR under different AFs/different degrees of fat suppression.

RESULTS

Images by AFs of CS3, CS4, and CS5 had the highest SNR and CNR. Among them, CS5 had the shortest scan time. CS5 also had one of the highest subjective scores. There was no significant difference in SNR and CNR among images acquired with different degrees of fat suppression. Also, images with moderate fat suppression had the highest subjective scores.

CONCLUSION

The CS5 combined with moderate fat suppression is recommended for routine female pelvic 3D-ISO-T2WI scan.

ADVANCES IN KNOWLEDGE

The CS5 has the highest image quality and has the shortest scan time, which is the best AF. Moderate fat suppression has the highest subjective scores. The CS5 and moderate fat suppression are the best combination for a female pelvic 3D-ISO-T2WI scan.

Deep learning reconstructed T2-weighted Dixon imaging of the spine: Impact on acquisition time and image quality

PURPOSE

To assess the image quality and impact on acquisition time of a novel deep learning based T2 Dixon sequence (T2DL) of the spine.

METHODS

This prospective, single center study included n = 44 consecutive patients with a clinical indication for lumbar MRI at our university radiology department between September 2022 and March 2023. MRI examinations were performed on 1.5-T and 3-T scanners (MAGNETOM Aera and Vida; Siemens Healthineers, Erlangen, Germany) using dedicated spine coils. The MR study protocol consisted of our standard clinical protocol, including a T2 weighted standard Dixon sequence (T2std) and an additional T2DL acquisition. The latter used a conventional sampling pattern with a higher parallel acceleration factor. The individual contrasts acquired for Dixon water-fat separation were then reconstructed using a dedicated research application. After reconstruction of the contrast images from k-space data, a conventional water-fat separation was performed to provide derived water images. Two readers with 6 and 4 years of experience in interpreting MSK imaging, respectively, analyzed the images in a randomized fashion. Regarding overall image quality, banding artifacts, artifacts, sharpness, noise, and diagnostic confidence were analyzed using a 5-point Likert scale (from 1 = non-diagnostic to 5 = excellent image quality). Statistical analyses included the Wilcoxon signed-rank test and weighted Cohen's kappa statistics.

RESULTS

Forty-four patients (mean age 53 years (±18), male sex: 39 %) were prospectively included. Thirty-one examinations were performed on 1.5 T and 13 examinations on 3 T scanners. A sequence was successfully acquired in all patients. The total acquisition time of T2DL was 93 s at 1.5-T and 86 s at 3-T, compared to 235 s, and 257 s, respectively for T2std (reduction of acquisition time: 60.4 % at 1.5-T, and 66.5 % at 3-T; p < 0.01). Overall image quality was rated equal for both sequences (median T2DL: 5[3 -5], and median T2std: 5 [2 -5]; p = 0.57). T2DL showed significantly reduced noise levels compared to T2std (5 [4 -5] versus 4 [3 -4]; p < 0.001). In addition, sharpness was rated to be significantly higher in T2DL (5 [4 -5] versus 4 [3 -5]; p < 0.001). Although T2DL displayed significantly more banding artifacts (5 [2 -5] versus 5 [4 -5]; p < 0.001), no significant impact on readers diagnostic confidence between sequences was noted (T2std: 5 [2 -5], and T2DL: 5 [3 -5]; p = 0.61). Substantial inter-reader and intrareader agreement was observed for T2DL overall image quality (κ: 0.77, and κ: 0.8, respectively).

CONCLUSION

T2DL is feasible, yields an image quality comparable to the reference standard while substantially reducing the acquisition time.

Dynamic contrast enhanced MRI of the head and neck region using a VIBE sequence with Cartesian undersampling and compressed sensing

OBJECTIVES

Compressed sensing allows for image reconstruction from sparsely sampled k-space data, which is particularly useful in dynamic contrast enhanced MRI (DCE-MRI). The aim of the study was to assess the diagnostic value of a volume-interpolated 3D T1-weighted spoiled gradient-echo sequence with variable density Cartesian undersampling and compressed sensing (CS) for head and neck MRI.

METHODS

Seventy-one patients with clinical indications for head and neck MRI were included in this study. DCE-MRI was performed at 3 Tesla magnet using CS-VIBE (variable density undersampling, temporal resolution 3.4 s, slice thickness 1 mm). Image quality was compared to standard Cartesian VIBE. Three experienced readers independently evaluated image quality and lesion conspicuity on a 5-point Likert scale and determined the DCE-derived time intensity curve (TIC) types.

RESULTS

CS-VIBE demonstrated higher image quality scores compared to standard VIBE with respect to overall image quality (4.3 ± 0.6 vs. 4.2 ± 0.7, p = 0.682), vessel contour (4.6 ± 0.4 vs. 4.4 ± 0.6, p < 0.001), muscle contour (4.4 ± 0.5 vs. 4.5 ± 0.6, p = 0.302), lesion conspicuity (4.5 ± 0.7 vs. 4.3 ± 0.9, p = 0.024) and showed improved fat saturation (4.8 ± 0.3 vs. 3.8 ± 0.4, p < 0.001) and movement artifacts were significantly reduced (4.6 ± 0.6 vs. 3.7 ± 0.7, p < 0.001). Standard VIBE outperformed CS-VIBE in the delineation of pharyngeal mucosa (4.2 ± 0.5 vs. 4.6 ± 0.6, p < 0.001). Lesion size in cases where a focal lesion was identified was similar for all readers for CS-VIBE and standard VIBE (p = 0.101). TIC curve assessment showed good interobserver agreement (k=0.717).

CONCLUSION

CS-VIBE with variable density Cartesian undersampling allows for DCE-MRI of the head and neck region with diagnostic, high image quality and high temporal resolution.

Compressed-sensing-inspired reconstruction algorithms in low-dose computed tomography: A review

BACKGROUND

Optimization of the dose the patient receives during scanning is an important problem in modern medical X-ray computed tomography (CT). One of the basic ways to its solution is to reduce the number of views. Compressed sensing theory helped promote the development of a new class of effective reconstruction algorithms for limited data CT. These compressed-sensing-inspired (CSI) algorithms optimize the Lp (0 ≤ p ≤ 1) norm of images and can accurately reconstruct CT tomograms from a very few views. The paper presents a review of the CSI algorithms and discusses prospects for their further use in commercial low-dose CT.

METHODS

Many literature references with the CSI algorithms have been were searched. To structure the material collected the author gives a classification framework within which he describes Lp regularization methods, the basic CSI algorithms that are used most often in few-view CT, and some of their derivatives. Lots of examples are provided to illustrate the use of the CSI algorithms in few-view and low-dose CT.

RESULTS

A list of the CSI algorithms is compiled from the literature search. For better demonstrativeness they are summarized in a table. The inference is done that already today some of the algorithms are capable of reconstruction from 20 to 30 views with acceptable quality and dose reduction by a factor of 10.

DISCUSSION

In conclusion the author discusses how soon the CSI reconstruction algorithms can be introduced in the practice of medical diagnosis and used in commercial CT scanners.

Highly accelerated parameter mapping using model-based alternating reconstruction coupling fitting

Objective.A model-based alternating reconstruction coupling fitting, termed Model-based Alternating Reconstruction COupling fitting (MARCO), is proposed for accurate and fast magnetic resonance parameter mapping.Approach.MARCO utilizes the signal model as a regularization by minimizing the bias between the image series and the signal produced by the suitable signal model based on iteratively updated parameter maps when reconstructing. The technique can incorporate prior knowledge of both image series and parameters by adding sparsity constraints. The optimization problem is decomposed into three subproblems and solved through three alternating steps involving reconstruction and nonlinear least-square fitting, which can produce both contrast-weighted images and parameter maps simultaneously.Main results.The algorithm is applied toT2mapping with extended phase graph algorithm integrated and validated on undersampled multi-echo spin-echo data from both phantom and in vivo sources. Compared with traditional compressed sensing and model-based methods, the proposed approach yields more accurateT2maps with more details at high acceleration factors.Significance.The proposed method provides a basic framework for quantitative MR relaxometry, theoretically applicable to all quantitative MR relaxometry. It has the potential to improve the diagnostic utility of quantitative imaging techniques.

T1-weighted fast fluid-attenuated inversion-recovery sequence (T1-FFLAIR) enables the visualization and quantification of fetal brain myelination in utero

OBJECTIVES

To investigate the advantage of T1-weighted fast fluid-attenuated inversion-recovery MRI sequence without (T1-FFLAIR) and with compressed sensing technology (T1-FFLAIR-CS), which shows improved T1-weighted contrast, over standard used T1-weighted fast field echo (T1-FFE) sequence for the assessment of fetal myelination.

MATERIALS AND METHODS

This retrospective single-center study included 115 consecutive fetal brain MRI examinations (63 axial and 76 coronal, mean gestational age (GA) 28.56 ± 5.23 weeks, range 19-39 weeks). Two raters, blinded to GA, qualitatively assessed a fetal myelin total score (MTS) on each T1-weighted sequence at five brain regions (medulla oblongata, pons, mesencephalon, thalamus, central region). One rater performed region-of-interest quantitative analysis (n = 61) at the same five brain regions. Pearson correlation analysis was applied for correlation of MTS and of the signal intensity ratios (relative to muscle) with GA on each T1-weighted sequence. Fetal MRI-based results were compared with myelination patterns of postmortem fetal human brains (n = 46; GA 18 to 42), processed by histological and immunohistochemical analysis.

RESULTS

MTS positively correlated with GA on all three sequences (all r between 0.802 and 0.908). The signal intensity ratios measured at the five brain regions correlated best with GA on T1-FFLAIR (r between 0.583 and 0.785). T1-FFLAIR demonstrated significantly better correlations with GA than T1-FFE for both qualitative and quantitative analysis (all p < 0.05). Furthermore, T1-FFLAIR enabled the best visualization of myelinated brain structures when compared to histology.

CONCLUSION

T1-FFLAIR outperforms the standard T1-FFE sequence in the visualization of fetal brain myelination, as demonstrated by qualitative and quantitative methods.

CLINICAL RELEVANCE STATEMENT

T1-weighted fast fluid-attenuated inversion-recovery sequence (T1-FFLAIR) provided best visualization and quantification of myelination in utero that, in addition to the relatively short acquisition time, makes feasible its routine application in fetal MRI for the assessment of brain myelination.

KEY POINTS

• So far, the assessment of fetal myelination in utero was limited due to the insufficient contrast. • T1-weighted fast fluid-attenuated inversion-recovery sequence allows a qualitative and quantitative assessment of fetal brain myelination. • T1-weighted fast fluid-attenuated inversion-recovery sequence outperforms the standard used T1-weighted sequence for visualization and quantification of myelination in utero.

A systematic review of 4D magnetic resonance imaging techniques for abdominal radiotherapy treatment planning

Background and purpose

Four-dimensional magnetic resonance imaging (4DMRI) has gained interest as an alternative to the current standard for motion management four-dimensional tomography (4DCT) in abdominal radiotherapy treatment planning (RTP). This review aims to assess the 4DMRI literature in abdomen, focusing on technical considerations and the validity of using 4DMRI for patients within radiotherapy protocols.

Materials and methods

The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A comprehensive search was performed across the Medline, Embase, Scopus, and Web of Science databases, covering all years up to December 31, 2023. The studies were grouped into two categories: 4DMRI reconstructed from 3DMRI acquisition; and 4DMRI reconstructed from multi-slice 2DMRI acquisition.

Results

A total of 39 studies met the inclusion criteria and were analysed to provide key findings. Key findings were 4DMRI had the potential to improve abdominal RTP for patients by providing accurate tumour definition and motion assessment compared to 4DCT. 4DMRI reconstructed from 3DMRI acquisition showed promise as a feasible approach for motion management in abdominal RTP regarding spatial resolution. Currently,the slice thickness achieved on 4DMRI reconstructed from multi-slice 2DMRI acquisitions was unsuitable for clinical purposes. Lastly, the current barriers for clinical implementation of 4DMRI were the limited availability of validated commercial solutions and the lack of larger cohort comparative studies to 4DCT for target delineation and plan optimisation.

Conclusion

4DMRI showed potential improvements in abdominal RTP, but standards and guidelines for the use of 4DMRI in radiotherapy were required to demonstrate clinical benefits.

Compressed sensing 3D T2WI radiomics model: improving diagnostic performance in muscle invasion of bladder cancer

BACKGROUND

Preoperative discrimination between non-muscle-invasive bladder cancer (NMIBC) and the muscle invasive bladder cancer (MIBC) is a determinant of management. The purpose of this research is to employ radiomics to evaluate the diagnostic value in determining muscle invasiveness of compressed sensing (CS) accelerated 3D T2-weighted-SPACE sequence with high resolution and short acquisition time.

METHODS

This prospective study involved 108 participants who underwent preoperative 3D-CS-T2-weighted-SPACE, 3D-T2-weighted-SPACE and T2-weighted sequences. The cohort was divided into training and validation cohorts in a 7:3 ratio. In the training cohort, a Rad-score was constructed based on radiomic features selected by intraclass correlation coefficients, pearson correlation coefficient and least absolute shrinkage and selection operator . Multivariate logistic regression was used to develop a nomogram combined radiomics and clinical indices. In the validation cohort, the performances of the models were evaluated by ROC, calibration, and decision curves.

RESULTS

In the validation cohort, the area under ROC curve of 3D-CS-T2-weighted-SPACE, 3D-T2-weighted-SPACE and T2-weighted models were 0.87(95% confidence interval (CI):0.73-1.00), 0.79(95%CI:0.63-0.96) and 0.77(95%CI:0.60-0.93), respectively. The differences in signal-to-noise ratio and contrast-to-noise ratio between 3D-CS-T2-weighted-SPACE and 3D-T2-weighted-SPACE sequences were not statistically significant(p > 0.05). While the clinical model composed of three clinical indices was 0.74(95%CI:0.55-0.94) and the radiomics-clinical nomogram model was 0.88(95%CI:0.75-1.00). The calibration curves confirmed high goodness of fit, and the decision curve also showed that the radiomics model and combined nomogram model yielded higher net benefits than the clinical model.

CONCLUSION

The radiomics model based on compressed sensing 3D T2WI sequence, which was acquired within a shorter acquisition time, showed superior diagnostic efficacy in muscle invasion of bladder cancer. Additionally, the nomogram model could enhance the diagnostic performance.

Paired conditional generative adversarial network for highly accelerated liver 4D MRI

Purpose.4D MRI with high spatiotemporal resolution is desired for image-guided liver radiotherapy. Acquiring densely sampling k-space data is time-consuming. Accelerated acquisition with sparse samples is desirable but often causes degraded image quality or long reconstruction time. We propose the Reconstruct Paired Conditional Generative Adversarial Network (Re-Con-GAN) to shorten the 4D MRI reconstruction time while maintaining the reconstruction quality.Methods.Patients who underwent free-breathing liver 4D MRI were included in the study. Fully- and retrospectively under-sampled data at 3, 6 and 10 times (3×, 6× and 10×) were first reconstructed using the nuFFT algorithm. Re-Con-GAN then trained input and output in pairs. Three types of networks, ResNet9, UNet and reconstruction swin transformer (RST), were explored as generators. PatchGAN was selected as the discriminator. Re-Con-GAN processed the data (3D +t) as temporal slices (2D +t). A total of 48 patients with 12 332 temporal slices were split into training (37 patients with 10 721 slices) and test (11 patients with 1611 slices). Compressed sensing (CS) reconstruction with spatiotemporal sparsity constraint was used as a benchmark. Reconstructed image quality was further evaluated with a liver gross tumor volume (GTV) localization task using Mask-RCNN trained from a separate 3D static liver MRI dataset (70 patients; 103 GTV contours).Results.Re-Con-GAN consistently achieved comparable/better PSNR, SSIM, and RMSE scores compared to CS/UNet models. The inference time of Re-Con-GAN, UNet and CS are 0.15, 0.16, and 120 s. The GTV detection task showed that Re-Con-GAN and CS, compared to UNet, better improved the dice score (3× Re-Con-GAN 80.98%; 3× CS 80.74%; 3× UNet 79.88%) of unprocessed under-sampled images (3× 69.61%).Conclusion.A generative network with adversarial training is proposed with promising and efficient reconstruction results demonstrated on an in-house dataset. The rapid and qualitative reconstruction of 4D liver MR has the potential to facilitate online adaptive MR-guided radiotherapy for liver cancer.

Partial Acquisition of Spectral Projections Accelerates Four-dimensional Spectral-spatial EPR Imaging for Mouse Tumor Models: A Feasibility Study

PURPOSE

Our study aimed to accelerate the acquisition of four-dimensional (4D) spectral-spatial electron paramagnetic resonance (EPR) imaging for mouse tumor models. This advancement in EPR imaging should reduce the acquisition time of spectroscopic mapping while reducing quality degradation for mouse tumor models.

PROCEDURES

EPR spectra under magnetic field gradients, called spectral projections, were partially measured. Additional spectral projections were later computationally synthesized from the measured spectral projections. Four-dimensional spectral-spatial images were reconstructed from the post-processed spectral projections using the algebraic reconstruction technique (ART) and assessed in terms of their image qualities. We applied this approach to a sample solution and a mouse Hs766T xenograft model of human-derived pancreatic ductal adenocarcinoma cells to demonstrate the feasibility of our concept. The nitroxyl radical imaging agent 2H,15N-DCP was exogenously infused into the mouse xenograft model.

RESULTS

The computation code of 4D spectral-spatial imaging was tested with numerically generated spectral projections. In the linewidth mapping of the sample solution, we achieved a relative standard uncertainty (standard deviation/| mean |) of 0.76 μT/45.38 μT = 0.017 on the peak-to-peak first-derivative EPR linewidth. The qualities of the linewidth maps and the effect of computational synthesis of spectral projections were examined. Finally, we obtained the three-dimensional linewidth map of 2H,15N-DCP in a Hs766T tumor-bearing leg in vivo.

CONCLUSION

We achieved a 46.7% reduction in the acquisition time of 4D spectral-spatial EPR imaging without significantly degrading the image quality. A combination of ART and partial acquisition in three-dimensional raster magnetic field gradient settings in orthogonal coordinates is a novel approach. Our approach to 4D spectral-spatial EPR imaging can be applied to any subject, especially for samples with less variation in one direction.

Sampling pattern discrepancy in the application of compressed sensing hyperpolarized xenon-129 lung MRI

Although hyperpolarized (HP) 129Xe ventilation MRI can be carried out within a breath hold, it is still challenging for many sick patients. Compressed sensing (CS) is a viable alternative to accelerate this approach. However, undersampled images with identical sampling ratios differ from one another. Twenty subjects (n = 10 healthy and n = 10 patients with asthma) were scanned using a GE MR750 3 T scanner, acquiring fully sampled 2D multi-slice HP 129Xe lung ventilation images (10 s breath hold, 128 × 80 (FE × PE-frequency encoding × phase encoding) and 16 slices). Using fully sampled data, 500 variable-density Cartesian random undersampling patterns were generated, each at eight different sampling ratios from 10% to 80%. The parallel imaging and compressed sensing (PICS) command from BART was employed to reconstruct undersampled data. The signal to noise ratio (SNR), structural similarity index measurement (SSIM) and sidelobe to peak ratio of each were subsequently compared. There was a high degree of variation in both SNR and SSIM results from each of the 500 masks of each sampling rate. As the undersampling increases, there is more variation in the quantifying metrics, for both healthy and asthmatic individuals. Our study shows that random undersampling poses a significant challenge when applied at sampling ratios less than 60%, despite fulfilling CS's incoherency criteria. Such low sampling ratios will result in a large variety of undersampling patterns. Therefore, skipped segments of k-space cannot be allowed to happen randomly at low sampling rates. By optimizing the sampling pattern, CS will reach its full potential and be able to be applied to a highly undersampled 129Xe lung dataset.

Fast 5-minute shoulder MRI protocol with accelerated TSE-sequences and deep learning image reconstruction for the assessment of shoulder pain at 1.5 and 3 Tesla

Purpose

The objective of this study was to implement a 5-minute MRI protocol for the shoulder in routine clinical practice consisting of accelerated 2D turbo spin echo (TSE) sequences with deep learning (DL) reconstruction at 1.5 and 3 Tesla, and to compare the image quality and diagnostic performance to that of a standard 2D TSE protocol.

Methods

Patients undergoing shoulder MRI between October 2020 and June 2021 were prospectively enrolled. Each patient underwent two MRI examinations: first a standard, fully sampled TSE (TSES) protocol reconstructed with a standard reconstruction followed by a second fast, prospectively undersampled TSE protocol with a conventional parallel imaging undersampling pattern reconstructed with a DL reconstruction (TSEDL). Image quality and visualization of anatomic structures as well as diagnostic performance with respect to shoulder lesions were assessed using a 5-point Likert-scale (5 = best). Interchangeability analysis, Wilcoxon signed-rank test and kappa statistics were performed to compare the two protocols.

Results

A total of 30 participants was included (mean age 50±15 years; 15 men). Overall image quality was evaluated to be superior in TSEDL versus TSES (p<0.001). Noise and edge sharpness were evaluated to be significantly superior in TSEDL versus TSES (noise: p<0.001, edge sharpness: p<0.05). No difference was found concerning qualitative diagnostic confidence, assessability of anatomical structures (p>0.05), and quantitative diagnostic performance for shoulder lesions when comparing the two sequences.

Conclusions

A fast 5-minute TSEDL MRI protocol of the shoulder is feasible in routine clinical practice at 1.5 and 3 T, with interchangeable results concerning the diagnostic performance, allowing a reduction in scan time of more than 50% compared to the standard TSES protocol.

Advanced MRI techniques in abdominal imaging

Magnetic resonance imaging (MRI) is a crucial modality for abdominal imaging evaluation of focal lesions and tissue properties. However, several obstacles, such as prolonged scan times, limitations in patients' breath-hold capacity, and contrast agent-associated artifacts, remain in abdominal MR images. Recent techniques, including parallel imaging, three-dimensional acquisition, compressed sensing, and deep learning, have been developed to reduce the scan time while ensuring acceptable image quality or to achieve higher resolution without extending the scan duration. Quantitative measurements using MRI techniques enable the noninvasive evaluation of specific materials. A comprehensive understanding of these advanced techniques is essential for accurate interpretation of MRI sequences. Herein, we therefore review advanced abdominal MRI techniques.

Effect of the Relationship between Respiratory Interval and Temporal Resolution on Image Quality in Free-breathing Abdominal MR Imaging

PURPOSE

To evaluate how the relationship between respiratory interval (RI) and temporal resolution (TR) impacts image quality in free-breathing abdominal MRI (FB-aMRI) using golden-angle radial sparse parallel (GRASP).

METHODS

Ten healthy volunteers (25.9 ± 2.5 years, four women) underwent 2 mins free-breathing fat-suppression T1-weighted imaging using GRASP at RIs of 3 and 5s (RI3 and RI5, respectively) and retrospectively reconstructed at TR of 1.8, 2.9, 4.8, and 7.7s (TR1.8, TR2.9, TR4.8, and TR7.7, respectively) in each patient. The standard deviation (SD) under the diaphragm was measured using SD maps showing the discrepancy for each horizontal section at all TRs. Two radiologists evaluated image quality (visualization of the right hepatic vein at the confluence of the inferior vena cava, posterior segment branch of portal vein, pancreas, left kidney, and artifacts) at all TRs using a 5-point scale.

RESULTS

The SD was significantly higher at TR1.8 compared to TR4.8 (P < 0.01) and TR7.7 (P < 0.001), as well as at TR2.9 compared to TR7.7 (P < 0.01) for both RIs. The SD between TR4.8 and TR7.7 did not differ for both RIs. For all visual assessment metrics, the TR1.8 scores were significantly lower than the TR4.8 and TR7.7 scores for both RIs. The pancreas and left kidney scores at TR2.9 were significantly lower than those at TR7.7 (P < 0.05) for RI5. Additionally, the left kidney score at TR1.8 was lower than that at TR2.9 (P < 0.05) for RI3. All scores at TR2.9, TR4.8, and TR7.7 were similar for RI3, while those at TR4.8 and TR7.7 were similar for RI5.

CONCLUSION

Prolonging the TRs compared to RIs enhances image quality in FB-aMRI using GRASP.

Speeding Up and Improving Image Quality in Glioblastoma MRI Protocol by Deep Learning Image Reconstruction

A fully diagnostic MRI glioma protocol is key to monitoring therapy assessment but is time-consuming and especially challenging in critically ill and uncooperative patients. Artificial intelligence demonstrated promise in reducing scan time and improving image quality simultaneously. The purpose of this study was to investigate the diagnostic performance, the impact on acquisition acceleration, and the image quality of a deep learning optimized glioma protocol of the brain. Thirty-three patients with histologically confirmed glioblastoma underwent standardized brain tumor imaging according to the glioma consensus recommendations on a 3-Tesla MRI scanner. Conventional and deep learning-reconstructed (DLR) fluid-attenuated inversion recovery, and T2- and T1-weighted contrast-enhanced Turbo spin echo images with an improved in-plane resolution, i.e., super-resolution, were acquired. Two experienced neuroradiologists independently evaluated the image datasets for subjective image quality, diagnostic confidence, tumor conspicuity, noise levels, artifacts, and sharpness. In addition, the tumor volume was measured in the image datasets according to Response Assessment in Neuro-Oncology (RANO) 2.0, as well as compared between both imaging techniques, and various clinical-pathological parameters were determined. The average time saving of DLR sequences was 30% per MRI sequence. Simultaneously, DLR sequences showed superior overall image quality (all p < 0.001), improved tumor conspicuity and image sharpness (all p < 0.001, respectively), and less image noise (all p < 0.001), while maintaining diagnostic confidence (all p > 0.05), compared to conventional images. Regarding RANO 2.0, the volume of non-enhancing non-target lesions (p = 0.963), enhancing target lesions (p = 0.993), and enhancing non-target lesions (p = 0.951) did not differ between reconstruction types. The feasibility of the deep learning-optimized glioma protocol was demonstrated with a 30% reduction in acquisition time on average and an increased in-plane resolution. The evaluated DLR sequences improved subjective image quality and maintained diagnostic accuracy in tumor detection and tumor classification according to RANO 2.0.

Free-Breathing Compressed Sensing Cine Cardiac MRI for Assessment of Left Ventricular Strain by Feature Tracking in Children

BACKGROUND

Cardiac MRI feature-tracking (FT) with breath-holding (BH) cine balanced steady state free precession (bSSFP) imaging is well established. It is unclear whether FT-strain measurements can be reliably derived from free-breathing (FB) compressed sensing (CS) bSSFP imaging.

PURPOSE

To compare left ventricular (LV) strain analysis and image quality of an FB CS bSSFP cine sequence with that of a conventional BH bSSFP sequence in children.

STUDY TYPE

Prospective.

SUBJECTS

40 children able to perform BHs (cohort 1 [12.1 ± 2.2 years]) and 17 children unable to perform BHs (cohort 2 [5.2 ± 1.8 years]).

FIELD STRENGTH/SEQUENCE

3T, bSSFP sequence with and without CS.

ASSESSMENT

Acquisition times and image quality were assessed. LV myocardial deformation parameters were compared between BH cine and FB CS cine studies in cohort 1. Strain indices and image quality of FB CS cine studies were also assessed in cohort 2. Intraobserver and interobserver variability of strain parameters was determined.

STATISTICAL TESTS

Paired t-test, Wilcoxon signed-rank test, intraclass correlation coefficient (ICC), and Bland-Altman analysis. A P-value <0.05 was considered statistically significant.

RESULTS

In cohort 1, the mean acquisition time of the FB CS cine study was significantly lower than for conventional BH cine study (15.6 s vs. 209.4 s). No significant difference were found in global circumferential strain rate (P = 0.089), global longitudinal strain rate (P = 0.366) and EuroCMR image quality scores (P = 0.128) between BH and FB sequences in cohort 1. The overall image quality score of FB CS cine in cohort 2 was 3.5 ± 0.5 with acquisition time of 14.7 ± 2.1 s. Interobserver and intraobserver variabilities were good to excellent (ICC = 0.810 to 0.943).

DATA CONCLUSION

FB CS cine imaging may be a promising alternative technique for strain assessment in pediatric patients with poor BH ability.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY: Stage 1.

Compressed sensing with deep learning reconstruction: Improving capability of gadolinium-EOB-enhanced 3D T1WI

PURPOSE

The purpose of this study was to determine the utility of compressed sensing (CS) with deep learning reconstruction (DLR) for improving spatial resolution, image quality and focal liver lesion detection on high-resolution contrast-enhanced T1-weighted imaging (HR-CE-T1WI) obtained by CS with DLR as compared with conventional CE-T1WI with parallel imaging (PI).

METHODS

Seventy-seven participants with focal liver lesions underwent conventional CE-T1WI with PI and HR-CE-T1WI, surgical resection, transarterial chemoembolization, and radiofrequency ablation, followed by histopathological or >2-year follow-up examinations in our hospital. Signal-to-noise ratios (SNRs) of liver, spleen and kidney were calculated for each patient, after which each SNR was compared by means of paired t-test. To compare focal lesion detection capabilities of the two methods, a 5-point visual scoring system was adopted for a per lesion basis analysis. Jackknife free-response receiver operating characteristic (JAFROC) analysis was then performed, while sensitivity and false positive rates (/data set) for consensus assessment of the two methods were also compared by using McNemar's test or the signed rank test.

RESULTS

Each SNR of HR-CE-T1WI was significantly higher than that of conventional CE-T1WI with PI (p < 0.05). Sensitivities for consensus assessment showed that HR-CE-MRI had significantly higher sensitivity than conventional CE-T1WI with PI (p = 0.004). Moreover, there were significantly fewer FP/cases for HR-CE-T1WI than for conventional CE-T1WI with PI (p = 0.04).

CONCLUSION

CS with DLR are useful for improving spatial resolution, image quality and focal liver lesion detection capability of Gd-EOB-DTPA enhanced 3D T1WI without any need for longer breath-holding time.

3D cine-magnetic resonance imaging using spatial and temporal implicit neural representation learning (STINR-MR)

Objective. 3D cine-magnetic resonance imaging (cine-MRI) can capture images of the human body volume with high spatial and temporal resolutions to study anatomical dynamics. However, the reconstruction of 3D cine-MRI is challenged by highly under-sampled k-space data in each dynamic (cine) frame, due to the slow speed of MR signal acquisition. We proposed a machine learning-based framework, spatial and temporal implicit neural representation learning (STINR-MR), for accurate 3D cine-MRI reconstruction from highly under-sampled data.Approach. STINR-MR used a joint reconstruction and deformable registration approach to achieve a high acceleration factor for cine volumetric imaging. It addressed the ill-posed spatiotemporal reconstruction problem by solving a reference-frame 3D MR image and a corresponding motion model that deforms the reference frame to each cine frame. The reference-frame 3D MR image was reconstructed as a spatial implicit neural representation (INR) network, which learns the mapping from input 3D spatial coordinates to corresponding MR values. The dynamic motion model was constructed via a temporal INR, as well as basis deformation vector fields (DVFs) extracted from prior/onboard 4D-MRIs using principal component analysis. The learned temporal INR encodes input time points and outputs corresponding weighting factors to combine the basis DVFs into time-resolved motion fields that represent cine-frame-specific dynamics. STINR-MR was evaluated using MR data simulated from the 4D extended cardiac-torso (XCAT) digital phantom, as well as two MR datasets acquired clinically from human subjects. Its reconstruction accuracy was also compared with that of the model-based non-rigid motion estimation method (MR-MOTUS) and a deep learning-based method (TEMPEST).Main results. STINR-MR can reconstruct 3D cine-MR images with high temporal (<100 ms) and spatial (3 mm) resolutions. Compared with MR-MOTUS and TEMPEST, STINR-MR consistently reconstructed images with better image quality and fewer artifacts and achieved superior tumor localization accuracy via the solved dynamic DVFs. For the XCAT study, STINR reconstructed the tumors to a mean ± SD center-of-mass error of 0.9 ± 0.4 mm, compared to 3.4 ± 1.0 mm of the MR-MOTUS method. The high-frame-rate reconstruction capability of STINR-MR allows different irregular motion patterns to be accurately captured.Significance. STINR-MR provides a lightweight and efficient framework for accurate 3D cine-MRI reconstruction. It is a 'one-shot' method that does not require external data for pre-training, allowing it to avoid generalizability issues typically encountered in deep learning-based methods.

Breath-hold High-resolution T1-weighted Gradient Echo Liver MR Imaging with Compressed Sensing Obtained during the Gadoxetic Acid-enhanced Hepatobiliary Phase: Image Quality and Lesion Visibility Compared with a Standard T1-weighted Sequence

PURPOSE

To evaluate the feasibility of breath-hold (BH) high-resolution (HR) T1-weighted gradient echo hepatobiliary phase (HBP) imaging using compressed sensing (CS) in gadoxetic acid-enhanced liver MRI in comparison with standard HBP imaging using parallel imaging (PI).

METHODS

The study included 122 patients with liver tumors with hypointensity in the HBP who underwent both HR HBP imaging with CS and standard HBP imaging with PI. Two radiologists evaluated the liver edge sharpness, hepatic vessel conspicuity, bile duct conspicuity, image noise, and overall image quality, as well as the lesion conspicuity on HR and standard HBP imaging and the contrast-enhanced (CE) MR cholangiography (MRC) image quality reconstructed from HBP images. As a quantitative analysis, the SNR of the liver and the liver to lesion signal intensity ratio (LLSIR) were also determined.

RESULTS

The liver edge sharpness, hepatic vessel conspicuity, bile duct conspicuity, and overall image quality as well as the lesion conspicuity and the LLSIR on HR HBP imaging with CS were significantly higher than those on standard HBP imaging (all of P < 0.001). The image quality of CE-MRC reconstructed from HR HBP imaging with CS was also significantly higher than that from standard HBP imaging (P < 0.001). Conversely, the SNR of liver in standard HBP was significantly higher than that in HR HBP with CS (P < 0.001).

CONCLUSION

BH HR HBP imaging with CS provided an improved overall image quality, lesion conspicuity, and CE-MRC visualization when compared with standard HBP imaging without extending the acquisition time.

Hepatobiliary phase imaging in cirrhotic patients using compressed sensing and controlled aliasing in parallel imaging results in higher acceleration

OBJECTIVE

We aimed to compare the image quality and focal lesion detection ability of hepatobiliary phase (HBP) images obtained using compressed sensing (CS) and controlled aliasing in parallel imaging results in higher acceleration (CAIPIRINHA) in patients with liver cirrhosis.

MATERIALS AND METHODS

We retrospectively included 244 gadoxetic acid-enhanced liver MRI from 244 patients with cirrhosis obtained by two HBP images using CS and CAIPIRINHA from July 2020 to December 2020. The optimized resolution and scan time for CS-HBP and CAIPIRINHA-HBP were 0.9 × 0.9 × 1.5 mm3 and 15 s and 1.3 × 1.3 × 3 mm3 and 16 s, respectively. We compared the image quality between the two sets of images in 244 patients and focal lesion (n = 294) analyses for 112 patients.

RESULTS

CS-HBP showed comparable overall image quality (3.7 ± 0.9 vs. 3.6 ± 0.8, p = 0.680), superior liver edge sharpness (3.9 ± 0.6 vs. 3.6 ± 0.5, p < 0.001), and fewer respiratory motion artifacts (4.0 ± 0.7 vs. 3.8 ± 0.5, p < 0.001), but higher non-respiratory artifacts (3.4 ± 0.7 vs. 3.6 ± 0.6, p < 0.001) and subjective image noise (3.5 ± 0.8 vs. 3.6 ± 0.7, p = 0.014) than CAIPIRINHA-HBP. CS-HBP showed a higher signal-to-noise ratio in the liver than CAIPIRINHA-HBP (20.9 ± 9.0 vs. 18.9 ± 7.1, p = 0.008). The pooled sensitivity, specificity, and AUC were 90.0%, 77.5%, and 0.84 for CS-HBP and 73.5%, 82.4%, and 0.78 for CAIPIRINHA-HBP, respectively.

CONCLUSIONS

CS-HBP showed better focal lesion detection ability, comparable overall image quality, and fewer respiratory motion artifacts, but higher non-respiratory artifacts and noise compared to CAIPIRINHA-HBP. Thus, CS-HBP could be recommended for liver MRI in patients with cirrhosis to improve diagnostic performance.

CLINICAL RELEVANCE STATEMENT

Thin-slice CS-HBP may be useful for detecting sub-centimeter hepatocellular carcinoma in cirrhotic patients with Child-Pugh classification A while maintaining comparable subjective image quality.

KEY POINTS

• Compared with controlled aliasing in parallel imaging results in higher acceleration, compressed sensing hepatobiliary phase yielded thinner slices and shorter scan time at a higher accelerating factor. • Compressed sensing hepatobiliary phase showed comparable overall image quality, superior liver edge sharpness, and fewer respiratory motion artifacts, but higher non-respiratory artifacts and subjective image noise than controlled aliasing in parallel imaging results in higher acceleration-hepatobiliary phase. • Compressed sensing hepatobiliary phase can detect sub-centimeter hepatocellular carcinoma in cirrhotic patients with Child-Pugh classification A.

Enhancing gadoxetic acid-enhanced liver MRI: a synergistic approach with deep learning CAIPIRINHA-VIBE and optimized fat suppression techniques

OBJECTIVE

To investigate whether a deep learning (DL) controlled aliasing in parallel imaging results in higher acceleration (CAIPIRINHA)-volumetric interpolated breath-hold examination (VIBE) technique can improve image quality, lesion conspicuity, and lesion detection compared to a standard CAIPIRINHA-VIBE technique in gadoxetic acid-enhanced liver MRI.

METHODS

This retrospective single-center study included 168 patients who underwent gadoxetic acid-enhanced liver MRI at 3 T using both standard CAIPIRINHA-VIBE and DL CAIPIRINHA-VIBE techniques on pre-contrast and hepatobiliary phase (HBP) images. Additionally, high-resolution (HR) DL CAIPIRINHA-VIBE was obtained with 1-mm slice thickness on the HBP. Three abdominal radiologists independently assessed the image quality and lesion conspicuity of pre-contrast and HBP images. Statistical analyses involved the Wilcoxon signed-rank test for image quality assessment and the generalized estimation equation for lesion conspicuity and detection evaluation.

RESULTS

DL and HR-DL CAIPIRINHA-VIBE demonstrated significantly improved overall image quality and reduced artifacts on pre-contrast and HBP images compared to standard CAIPIRINHA-VIBE (p < 0.001), with a shorter acquisition time (DL vs standard, 11 s vs 17 s). However, the former presented a more synthetic appearance (both p < 0.05). HR-DL CAIPIRINHA-VIBE showed superior lesion conspicuity to standard and DL CAIPIRINHA-VIBE on HBP images (p < 0.001). Moreover, HR-DL CAIPIRINHA-VIBE exhibited a significantly higher detection rate of small (< 2 cm) solid focal liver lesions (FLLs) on HBP images compared to standard CAIPIRINHA-VIBE (92.5% vs 87.4%; odds ratio = 1.83; p = 0.036).

CONCLUSION

DL and HR-DL CAIPIRINHA-VIBE achieved superior image quality compared to standard CAIPIRINHA-VIBE. Additionally, HR-DL CAIPIRINHA-VIBE improved the lesion conspicuity and detection of small solid FLLs. DL and HR-DL CAIPIRINHA-VIBE hold the potential clinical utility for gadoxetic acid-enhanced liver MRI.

CLINICAL RELEVANCE STATEMENT

DL and HR-DL CAIPIRINHA-VIBE hold promise as potential alternatives to standard CAIPIRINHA-VIBE in routine clinical liver MRI, improving the image quality and lesion conspicuity, enhancing the detection of small (< 2 cm) solid focal liver lesions, and reducing the acquisition time.

KEY POINTS

• DL and HR-DL CAIPIRINHA-VIBE demonstrated improved overall image quality and reduced artifacts on pre-contrast and HBP images compared to standard CAIPIRINHA-VIBE, in addition to a shorter acquisition time. • DL and HR-DL CAIPIRINHA-VIBE yielded a more synthetic appearance than standard CAIPIRINHA-VIBE. • HR-DL CAIPIRINHA-VIBE showed improved lesion conspicuity than standard CAIPIRINHA-VIBE on HBP images, with a higher detection of small (< 2 cm) solid focal liver lesions.

Deep learning-accelerated image reconstruction in back pain-MRI imaging: reduction of acquisition time and improvement of image quality

INTRODUCTION

Low back pain is a global health issue causing disability and missed work days. Commonly used MRI scans including T1-weighted and T2-weighted images provide detailed information of the spine and surrounding tissues. Artificial intelligence showed promise in improving image quality and simultaneously reducing scan time. This study evaluates the performance of deep learning (DL)-based T2 turbo spin-echo (TSE, T2DLR) and T1 TSE (T1DLR) in lumbar spine imaging regarding acquisition time, image quality, artifact resistance, and diagnostic confidence.

MATERIAL AND METHODS

This retrospective monocentric study included 60 patients with lower back pain who underwent lumbar spinal MRI between February and April 2023. MRI parameters and DL reconstruction (DLR) techniques were utilized to acquire images. Two neuroradiologists independently evaluated image datasets based on various parameters using a 4-point Likert scale.

RESULTS

Accelerated imaging showed significantly less image noise and artifacts, as well as better image sharpness, compared to standard imaging. Overall image quality and diagnostic confidence were higher in accelerated imaging. Relevant disk herniations and spinal fractures were detected in both DLR and conventional images. Both readers favored accelerated imaging in the majority of examinations. The lumbar spine examination time was cut by 61% in accelerated imaging compared to standard imaging.

CONCLUSION

In conclusion, the utilization of deep learning-based image reconstruction techniques in lumbar spinal imaging resulted in significant time savings of up to 61% compared to standard imaging, while also improving image quality and diagnostic confidence. These findings highlight the potential of these techniques to enhance efficiency and accuracy in clinical practice for patients with lower back pain.

Fever of unknown origin in pediatrics: role of nuclear medicine

Fever of unknown origin (FUO) is a debated issue in numerous scientific studies in adult patients with a not jet-defined workflow in a clinical and diagnostic setting. Few works are published about pediatric patients even if FUO represents a challenging, not infrequent scenario in hospital and outpatient recovery. The fever might be the onset symptom of a transient mild infection or the beginning of a more difficult-to-diagnose and serious pathological condition. In the adult workflow 18FDG PET-CT is nowadays playing a relevant role, considering the limited spread of conventional 99mTc-HMPAO-White Blood Cells scintigraphy. It represents a robust tool for diagnosing the eventual site of infection, but it is limited by procedural complexity and long duration, up to 24 hours. The WBC-scintigraphy is also not suitable for children, only for young adults or adolescents, considering the relevant blood sample entity and the procedural risk for sensitive subjects. The most assessed clinical and diagnostic know-how on Pediatric FUO are summarized and a synthetic flow-chard is presented to support the clinical management and to choose the best diagnostic pathway.

Deep learning-accelerated image reconstruction in MRI of the orbit to shorten acquisition time and enhance image quality

BACKGROUND AND PURPOSE

This study explores the use of deep learning (DL) techniques in MRI of the orbit to enhance imaging. Standard protocols, although detailed, have lengthy acquisition times. We investigate DL-based methods for T2-weighted and T1-weighted, fat-saturated, contrast-enhanced turbo spin echo (TSE) sequences, aiming to improve image quality, reduce acquisition time, minimize artifacts, and enhance diagnostic confidence in orbital imaging.

METHODS

In a 3-Tesla MRI study of 50 patients evaluating orbital diseases from March to July 2023, conventional (TSES ) and DL TSE sequences (TSEDL ) were used. Two neuroradiologists independently assessed the image datasets for image quality, diagnostic confidence, noise levels, artifacts, and image sharpness using a randomized and blinded 4-point Likert scale.

RESULTS

TSEDL significantly reduced image noise and artifacts, enhanced image sharpness, and decreased scan time, outperforming TSES (p < .05). TSEDL showed superior overall image quality and diagnostic confidence, with relevant findings effectively detected in both DL-based and conventional images. In 94% of cases, readers preferred accelerated imaging.

CONCLUSION

The study proved that using DL for MRI image reconstruction in orbital scans significantly cut acquisition time by 69%. This approach also enhanced image quality, reduced image noise, sharpened images, and boosted diagnostic confidence.

Advanced Abdominal MRI Techniques and Problem-Solving Strategies

MRI plays an important role in abdominal imaging because of its ability to detect and characterize focal lesions. However, MRI examinations have several challenges, such as comparatively long scan times and motion management through breath-holding maneuvers. Techniques for reducing scan time with acceptable image quality, such as parallel imaging, compressed sensing, and cutting-edge deep learning techniques, have been developed to enable problem-solving strategies. Additionally, free-breathing techniques for dynamic contrast-enhanced imaging, such as extra-dimensional-volumetric interpolated breath-hold examination, golden-angle radial sparse parallel, and liver acceleration volume acquisition Star, can help patients with severe dyspnea or those under sedation to undergo abdominal MRI. We aimed to present various advanced abdominal MRI techniques for reducing the scan time while maintaining image quality and free-breathing techniques for dynamic imaging and illustrate cases using the techniques mentioned above. A review of these advanced techniques can assist in the appropriate interpretation of sequences.

Accelerated 3D MR neurography of the brachial plexus using deep learning-constrained compressed sensing

OBJECTIVES

To explore the use of deep learning-constrained compressed sensing (DLCS) in improving image quality and acquisition time for 3D MRI of the brachial plexus.

METHODS

Fifty-four participants who underwent contrast-enhanced imaging and forty-one participants who underwent unenhanced imaging were included. Sensitivity encoding with an acceleration of 2 × 2 (SENSE4x), CS with an acceleration of 4 (CS4x), and DLCS with acceleration of 4 (DLCS4x) and 8 (DLCS8x) were used for MRI of the brachial plexus. Apparent signal-to-noise ratios (aSNRs), apparent contrast-to-noise ratios (aCNRs), and qualitative scores on a 4-point scale were evaluated and compared by ANOVA and the Friedman test. Interobserver agreement was evaluated by calculating the intraclass correlation coefficients.

RESULTS

DLCS4x achieved higher aSNR and aCNR than SENSE4x, CS4x, and DLCS8x (all p < 0.05). For the root segment of the brachial plexus, no statistically significant differences in the qualitative scores were found among the four sequences. For the trunk segment, DLCS4x had higher scores than SENSE4x (p = 0.04) in the contrast-enhanced group and had higher scores than SENSE4x and DLCS8x in the unenhanced group (all p < 0.05). For the divisions, cords, and branches, DLCS4x had higher scores than SENSE4x, CS4x, and DLCS8x (all p ≤ 0.01). No overt difference was found among SENSE4x, CS4x, and DLCS8x in any segment of the brachial plexus (all p > 0.05).

CONCLUSIONS

In three-dimensional MRI for the brachial plexus, DLCS4x can improve image quality compared with SENSE4x and CS4x, and DLCS8x can maintain the image quality compared to SENSE4x and CS4x.

CLINICAL RELEVANCE STATEMENT

Deep learning-constrained compressed sensing can improve the image quality or accelerate acquisition of 3D MRI of the brachial plexus, which should be benefit in evaluating the brachial plexus and its branches in clinical practice.

KEY POINTS

•Deep learning-constrained compressed sensing showed higher aSNR, aCNR, and qualitative scores for the brachial plexus than SENSE and CS at the same acceleration factor with similar scanning time. •Deep learning-constrained compressed sensing at acceleration factor of 8 had comparable aSNR, aCNR, and qualitative scores to SENSE4x and CS4x with approximately half the examination time. •Deep learning-constrained compressed sensing may be helpful in clinical practice for improving image quality and acquisition time in three-dimensional MRI of the brachial plexus.

Amide proton transfer-weighted MRI for renal tumors: Comparison with diffusion-weighted imaging

OBJECTIVE

To investigate the potential of amide proton transfer-weighted (APTw) MRI in identifying benign and malignant renal tumors and to evaluate whether APTw MRI can add diagnostic value to diffusion-weighted imaging (DWI).

MATERIALS AND METHODS

Participants with renal tumor underwent preoperative multiparametric MRI, including APTw MRI and DWI. The APTw and apparent diffusion coefficient (ADC) of malignant tumors and benign tumors were calculated independently by two radiologists and compared. The value of the mean APTw and the mean ADC for differentiating malignant and benign tumors was evaluated by receiver operating characteristic analysis.

RESULTS

In total, 65 participants (mean age, 59 years ±14; 41 men) were evaluated: 54 with malignant and 11 with benign renal tumors. Malignant renal tumors showed higher mean APTw values [2.03% (1.63) vs 1.00% (1.60); P < 0.01] and lower mean ADC values (1.22 × 10-3 mm2/s ± 0.37 vs 1.51 × 10-3 mm2/s ± 0.37; P < 0.05) than benign renal tumors. The area under the receiver operating characteristic curve (AUC) of APTw, ADC and the combination of them for the identification of benign and malignant renal tumors was 0.78(95% CI: 0.66, 0.87; P < 0.001),0.70(95% CI: 0.54, 0.86; P < 0.05) and 0.79 (95% CI: 0.67, 0.88; P < 0.001). The optimal cutoff value for mean APTw was 2.14% (sensitivity, 74%; specificity, 73%). There was no difference between these three parameters for differentiating malignant from benign renal tumors (P > 0.05).

CONCLUSION

The APTw MRI has the potential use as an imaging biomarker for renal malignant and benign tumors.

Compressed sensing magnetic resonance imaging (CS-MRI) diagnosis of rotator cuff tears

OBJECTIVE

The present prospective study was performed to evaluate the diagnostic efficiency of compressed sensing magnetic resonance imaging (CS-MRI) for rotator cuff tears.

METHODS

Between December 1, 2021 and April 1, 2022, 62 patients with suspected rotator cuff tears were admitted to Affiliated Hospital of Jinggangshan University and received CS-MRI and arthroscopy to determine the diagnosis and the disease type of tears. Their medical data were obtained and analyzed to evaluate the clinical feasibility of CS-MRI in diagnosing rotator cuff tears.

RESULTS

Of the 62 cases of suspected rotator cuff tears, 45 were confirmed by arthroscopy, including 31 cases of total tears and 14 partial tears. Using arthroscopic findings as the gold standard for the diagnosis of rotator cuff tears, the sensitivity of clinical signs to diagnose rotator cuff tears was 66.67%, the specificity was 70.59%, and the accuracy was 67.74%, while the sensitivity of CS-MRI in diagnosing rotator cuff tears was 84.44%, the specificity was 88.24%, and the accuracy was 81.54%. The accuracy of CS-MRI was significantly higher than that of clinical signs as determined by chi-square test within groups (P=0.019).

CONCLUSION

CS-MRI provides high resolution for muscles, tendons, and soft tissues, significantly contributing to the diagnosis of soft tissue injuries. Although there were no significant differences in the sensitivity and specificity of CS-MRI for the clinical diagnosis of rotator cuff tears compared to the clinical signs, CS-MRI significantly improved the diagnostic accuracy.

Deep Learning Accelerated Image Reconstruction of Fluid-Attenuated Inversion Recovery Sequence in Brain Imaging: Reduction of Acquisition Time and Improvement of Image Quality

RATIONALE AND OBJECTIVES

Fluid-attenuated inversion recovery (FLAIR) imaging is playing an increasingly significant role in the detection of brain metastases with a concomitant increase in the number of magnetic resonance imaging (MRI) examinations. Therefore, the purpose of this study was to investigate the impact on image quality and diagnostic confidence of an innovative deep learning-based accelerated FLAIR (FLAIRDLR) sequence of the brain compared to conventional (standard) FLAIR (FLAIRS) imaging.

MATERIALS AND METHODS

Seventy consecutive patients with staging cerebral MRIs were retrospectively enrolled in this single-center study. The FLAIRDLR was conducted using the same MRI acquisition parameters as the FLAIRS sequence, except for a higher acceleration factor for parallel imaging (from 2 to 4), which resulted in a shorter acquisition time of 1:39 minute instead of 2:40 minutes (-38%). Two specialized neuroradiologists evaluated the imaging datasets using a Likert scale that ranged from 1 to 4, with 4 indicating the best score for the following parameters: sharpness, lesion demarcation, artifacts, overall image quality, and diagnostic confidence. Additionally, the image preference of the readers and the interreader agreement were assessed.

RESULTS

The average age of the patients was 63 ± 11years. FLAIRDLR exhibited significantly less image noise than FLAIRS, with P-values of< .001 and< .05, respectively. The sharpness of the images and the ability to detect lesions were rated higher in FLAIRDLR, with a median score of 4 compared to a median score of 3 in FLAIRS (P-values of<.001 for both readers). In terms of overall image quality, FLAIRDLR was rated superior to FLAIRS, with a median score of 4 vs 3 (P-values of<.001 for both readers). Both readers preferred FLAIRDLR in 68/70 cases.

CONCLUSION

The feasibility of deep learning FLAIR brain imaging was shown with additional 38% reduction in examination time compared to standard FLAIR imaging. Furthermore, this technique has shown improvement in image quality, noise reduction, and lesion demarcation.

Accelerated Musculoskeletal Magnetic Resonance Imaging

With a substantial growth in the use of musculoskeletal MRI, there has been a growing need to improve MRI workflow, and faster imaging has been suggested as one of the solutions for a more efficient examination process. Consequently, there have been considerable advances in accelerated MRI scanning methods. This article aims to review the basic principles and applications of accelerated musculoskeletal MRI techniques including widely used conventional acceleration methods, more advanced deep learning-based techniques, and new approaches to reduce scan time. Specifically, conventional accelerated MRI techniques, including parallel imaging, compressed sensing, and simultaneous multislice imaging, and deep learning-based accelerated MRI techniques, including undersampled MR image reconstruction, super-resolution imaging, artifact correction, and generation of unacquired contrast images, are discussed. Finally, new approaches to reduce scan time, including synthetic MRI, novel sequences, and new coil setups and designs, are also reviewed. We believe that a deep understanding of these fast MRI techniques and proper use of combined acceleration methods will synergistically improve scan time and MRI workflow in daily practice. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 1.

A Deep Learning Approach to Using Wearable Seismocardiography (SCG) for Diagnosing Aortic Valve Stenosis and Predicting Aortic Hemodynamics Obtained by 4D Flow MRI

In this paper, we explored the use of deep learning for the prediction of aortic flow metrics obtained using 4-dimensional (4D) flow magnetic resonance imaging (MRI) using wearable seismocardiography (SCG) devices. 4D flow MRI provides a comprehensive assessment of cardiovascular hemodynamics, but it is costly and time-consuming. We hypothesized that deep learning could be used to identify pathological changes in blood flow, such as elevated peak systolic velocity ([Formula: see text]) in patients with heart valve diseases, from SCG signals. We also investigated the ability of this deep learning technique to differentiate between patients diagnosed with aortic valve stenosis (AS), non-AS patients with a bicuspid aortic valve (BAV), non-AS patients with a mechanical aortic valve (MAV), and healthy subjects with a normal tricuspid aortic valve (TAV). In a study of 77 subjects who underwent same-day 4D flow MRI and SCG, we found that the [Formula: see text] values obtained using deep learning and SCGs were in good agreement with those obtained by 4D flow MRI. Additionally, subjects with non-AS TAV, non-AS BAV, non-AS MAV, and AS could be classified with ROC-AUC (area under the receiver operating characteristic curves) values of 92%, 95%, 81%, and 83%, respectively. This suggests that SCG obtained using low-cost wearable electronics may be used as a supplement to 4D flow MRI exams or as a screening tool for aortic valve disease.

Utility of the New Faster Compressed SENSE MRCP at 3 Tesla MRI in Children with Pancreatitis

OBJECTIVE

To compare the acquisition time, diagnostic efficacy, and image quality of the newer compressed SENSE 3D MRCP (CS-3D MRCP) with conventional 3D MRCP (C-3D MRCP) in children with pancreatitis.

METHODS

A total of 24 children (2-17 y) diagnosed with pancreatitis were included in this study. The children underwent CS-3D MRCP and C-3D MRCP sequences. C-3D MRCP and CS-3D MRCP images were evaluated for the acquisition time duration, visualization of the pancreaticobiliary ducts, background suppression, image quality degradation by artifacts, and overall image quality by the two radiologists independently. Paired sample t-test was used to compare the acquisition time, the McNemar test for the image quality features, and the kappa coefficient was used for interobserver agreement.

RESULTS

A two-fold decrease in the acquisition time of CS-3D MRCP (~148 ± 61 s) was seen, compared to C-3D MRCP (~310 ± 98 s), p < 0.001. The median scores for overall image quality on CS-3D MRCP and C-3D MRCP, respectively, were 2.05 ± 0.52 and 2.21 ± 0.53 (p = 0.18) for both radiologists. No significant difference was seen for the visibility of ducts, background suppression, and artifacts between the two radiologists, with substantial to almost perfect agreement seen for the different findings.

CONCLUSION

The application of compressed SENSE 3D MRCP in children with pancreatitis results in a two-fold reduction in acquisition time with acceptable image quality. This may help in reducing the need for long sedation in children requiring anesthesia support for the MRCP and potentially help in reducing motion artifacts.

AI-assisted compressed sensing and parallel imaging sequences for MRI of patients with nasopharyngeal carcinoma: comparison of their capabilities in terms of examination time and image quality

OBJECTIVE

To compare examination time and image quality between artificial intelligence (AI)-assisted compressed sensing (ACS) technique and parallel imaging (PI) technique in MRI of patients with nasopharyngeal carcinoma (NPC).

METHODS

Sixty-six patients with pathologically confirmed NPC underwent nasopharynx and neck examination using a 3.0-T MRI system. Transverse T2-weighted fast spin-echo (FSE) sequence, transverse T1-weighted FSE sequence, post-contrast transverse T1-weighted FSE sequence, and post-contrast coronal T1-weighted FSE were obtained by both ACS and PI techniques, respectively. The signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and duration of scanning of both sets of images analyzed by ACS and PI techniques were compared. The images from the ACS and PI techniques were scored for lesion detection, margin sharpness of lesions, artifacts, and overall image quality using the 5-point Likert scale.

RESULTS

The examination time with ACS technique was significantly shorter than that with PI technique (p < 0.0001). The comparison of SNR and CNR showed that ACS technique was significantly superior with PI technique (p < 0.005). Qualitative image analysis showed that the scores of lesion detection, margin sharpness of lesions, artifacts, and overall image quality were higher in the ACS sequences than those in the PI sequences (p < 0.0001). Inter-observer agreement was evaluated for all qualitative indicators for each method, in which the results showed satisfactory-to-excellent agreement (p < 0.0001).

CONCLUSION

Compared with the PI technique, the ACS technique for MR examination of NPC can not only shorten scanning time but also improve image quality.

CLINICAL RELEVANCE STATEMENT

The artificial intelligence (AI)-assisted compressed sensing (ACS) technique shortens examination time for patients with nasopharyngeal carcinoma, while improving the image quality and examination success rate, which will benefit more patients.

KEY POINTS

• Compared with the parallel imaging (PI) technique, the artificial intelligence (AI)-assisted compressed sensing (ACS) technique not only reduced examination time, but also improved image quality. • Artificial intelligence (AI)-assisted compressed sensing (ACS) pulls the state-of-the-art deep learning technique into the reconstruction procedure and helps find an optimal balance of imaging speed and image quality.

Noise2Recon: Enabling SNR-robust MRI reconstruction with semi-supervised and self-supervised learning

PURPOSE

To develop a method for building MRI reconstruction neural networks robust to changes in signal-to-noise ratio (SNR) and trainable with a limited number of fully sampled scans.

METHODS

We propose Noise2Recon, a consistency training method for SNR-robust accelerated MRI reconstruction that can use both fully sampled (labeled) and undersampled (unlabeled) scans. Noise2Recon uses unlabeled data by enforcing consistency between model reconstructions of undersampled scans and their noise-augmented counterparts. Noise2Recon was compared to compressed sensing and both supervised and self-supervised deep learning baselines. Experiments were conducted using retrospectively accelerated data from the mridata three-dimensional fast-spin-echo knee and two-dimensional fastMRI brain datasets. All methods were evaluated in label-limited settings and among out-of-distribution (OOD) shifts, including changes in SNR, acceleration factors, and datasets. An extensive ablation study was conducted to characterize the sensitivity of Noise2Recon to hyperparameter choices.

RESULTS

In label-limited settings, Noise2Recon achieved better structural similarity, peak signal-to-noise ratio, and normalized-RMS error than all baselines and matched performance of supervised models, which were trained with14 × $$ 14\times $$ more fully sampled scans. Noise2Recon outperformed all baselines, including state-of-the-art fine-tuning and augmentation techniques, among low-SNR scans and when generalizing to OOD acceleration factors. Augmentation extent and loss weighting hyperparameters had negligible impact on Noise2Recon compared to supervised methods, which may indicate increased training stability.

CONCLUSION

Noise2Recon is a label-efficient reconstruction method that is robust to distribution shifts, such as changes in SNR, acceleration factors, and others, with limited or no fully sampled training data.

Deep Learning-Based Acceleration of Compressed Sensing for Noncontrast-Enhanced Coronary Magnetic Resonance Angiography in Patients With Suspected Coronary Artery Disease

BACKGROUND

The clinical application of coronary MR angiography (MRA) remains limited due to its long acquisition time and often unsatisfactory image quality. A compressed sensing artificial intelligence (CSAI) framework was recently introduced to overcome these limitations, but its feasibility in coronary MRA is unknown.

PURPOSE

To evaluate the diagnostic performance of noncontrast-enhanced coronary MRA with CSAI in patients with suspected coronary artery disease (CAD).

STUDY TYPE

Prospective observational study.

POPULATION

A total of 64 consecutive patients (mean age ± standard deviation [SD]: 59 ± 10 years, 48.4% females) with suspected CAD.

FIELD STRENGTH/SEQUENCE

A 3.0-T, balanced steady-state free precession sequence.

ASSESSMENT

Three observers evaluated the image quality for 15 coronary segments of the right and left coronary arteries using a 5-point scoring system (1 = not visible; 5 = excellent). Image scores ≥3 were considered diagnostic. Furthermore, the detection of CAD with ≥50% stenosis was evaluated in comparison to reference standard coronary computed tomography angiography (CTA). Mean acquisition times for CSAI-based coronary MRA were measured.

STATISTICAL TESTS

For each patient, vessel and segment, sensitivity, specificity, and diagnostic accuracy of CSAI-based coronary MRA for detecting CAD with ≥50% stenosis according to coronary CTA were calculated. Intraclass correlation coefficients (ICCs) were used to assess the interobserver agreement.

RESULTS

The mean MR acquisition time ± SD was 8.1 ± 2.4 minutes. Twenty-five (39.1%) patients had CAD with ≥50% stenosis on coronary CTA and 29 (45.3%) patients on MRA. A total of 885 segments on the CTA images and 818/885 (92.4%) coronary MRA segments were diagnostic (image score ≥3). The sensitivity, specificity, and diagnostic accuracy were as follows: per patient (92.0%, 84.6%, and 87.5%), per vessel (82.9%, 93.4%, and 91.1%), and per segment (77.6%, 98.2%, and 96.6%), respectively. The ICCs for image quality and stenosis assessment were 0.76-0.99 and 0.66-1.00, respectively.

DATA CONCLUSION

The image quality and diagnostic performance of coronary MRA with CSAI may show good results in comparison to coronary CTA in patients with suspected CAD.

EVIDENCE LEVEL

1.

TECHNICAL EFFICACY

2.

Optimal Temporal Resolution to Achieve Good Image Quality and Perform Pharmacokinetic Analysis in Free-breathing Dynamic Contrast-enhanced MR Imaging of the Pancreas

PURPOSE

The optimal temporal resolution for free-breathing dynamic contrast-enhanced MRI (FBDCE-MRI) of the pancreas has not been determined. This study aimed to evaluate the appropriate temporal resolution to achieve good image quality and to perform pharmacokinetic analysis in FBDCE-MRI of the pancreas using golden-angle radial sparse parallel (GRASP).

METHODS

Sixteen participants (53 ± 15 years, eight females) undergoing FBDCE-MRI were included in this prospective study. Images were retrospectively reconstructed at four temporal resolutions (1.8, 3.0, 4.8, and 7.8s). Two radiologists (5 years of experience) evaluated the image quality of each reconstructed image by assessing the visualization of the celiac artery (CEA), the common hepatic artery, the splenic artery, each area of the pancreas, and artifacts using a 5-point scale. Using Tissue-4D, pharmacokinetic parameters were calculated for each area in the reconstructed images at each temporal resolution for 16 examinations, excluding two with errors in the pharmacokinetic modeling analysis. Friedman and Bonferroni tests were used for analysis. A P value < 0.05 was considered statistically significant.

RESULTS

During vascular assessment, only scores for the CEA at 7.8s were significantly lower than the other temporal resolutions. Scores of all pancreatic regions and artifacts were significantly lower at 1.8s than at 4.8s and 7.8s. In the pharmacokinetic analysis, all volume transfer coefficients (Ktrans), rate constants (Kep), and the initial area under the concentration curve (iAUC) in the pancreatic head and tail were significantly lower at 4.8s and 7.8s than at 1.8s. iAUC in the pancreatic body and extracellular extravascular volume fraction (Ve) in the pancreatic head were significantly lower at 7.8s than at 1.8s.

CONCLUSION

A temporal resolution of 3.0s is appropriate to achieve image quality and perform pharmacokinetic analysis in FBDCE-MRI of the pancreas using GRASP.

Comparison of a Deep Learning-Accelerated vs. Conventional T2-Weighted Sequence in Biparametric MRI of the Prostate

BACKGROUND

Demand for prostate MRI is increasing, but scan times remain long even in abbreviated biparametric MRIs (bpMRI). Deep learning can be leveraged to accelerate T2-weighted imaging (T2WI).

PURPOSE

To compare conventional bpMRIs (CL-bpMRI) with bpMRIs including a deep learning-accelerated T2WI (DL-bpMRI) in diagnosing prostate cancer.

STUDY TYPE

Retrospective.

POPULATION

Eighty consecutive men, mean age 66 years (47-84) with suspected prostate cancer or prostate cancer on active surveillance who had a prostate MRI from December 28, 2020 to April 28, 2021 were included. Follow-up included prostate biopsy or stability of prostate-specific antigen (PSA) for 1 year.

FIELD STRENGTH AND SEQUENCES

A 3 T MRI. Conventional axial and coronal T2 turbo spin echo (CL-T2), 3-fold deep learning-accelerated axial and coronal T2-weighted sequence (DL-T2), diffusion weighted imaging (DWI) with b = 50 sec/mm2 , 1000 sec/mm2 , calculated b = 1500 sec/mm2 .

ASSESSMENT

CL-bpMRI and DL-bpMRI including the same conventional diffusion-weighted imaging (DWI) were presented to three radiologists (blinded to acquisition method) and to a deep learning computer-assisted detection algorithm (DL-CAD). The readers evaluated image quality using a 4-point Likert scale (1 = nondiagnostic, 4 = excellent) and graded lesions using Prostate Imaging Reporting and Data System (PI-RADS) v2.1. DL-CAD identified and assigned lesions of PI-RADS 3 or greater.

STATISTICAL TESTS

Quality metrics were compared using Wilcoxon signed rank test, and area under the receiver operating characteristic curve (AUC) were compared using Delong's test.

SIGNIFICANCE

P = 0.05.

RESULTS

Eighty men were included (age: 66 ± 9 years; 17/80 clinically significant prostate cancer). Overall image quality results by the three readers (CL-T2, DL-T2) are reader 1: 3.72 ± 0.53, 3.89 ± 0.39 (P = 0.99); reader 2: 3.33 ± 0.82, 3.31 ± 0.74 (P = 0.49); reader 3: 3.67 ± 0.63, 3.51 ± 0.62. In the patient-based analysis, the reader results of AUC are (CL-bpMRI, DL-bpMRI): reader 1: 0.77, 0.78 (P = 0.98), reader 2: 0.65, 0.66 (P = 0.99), reader 3: 0.57, 0.60 (P = 0.52). Diagnostic statistics from DL-CAD (CL-bpMRI, DL-bpMRI) are sensitivity (0.71, 0.71, P = 1.00), specificity (0.59, 0.44, P = 0.05), positive predictive value (0.23, 0.24, P = 0.25), negative predictive value (0.88, 0.88, P = 0.48).

CONCLUSION

Deep learning-accelerated T2-weighted imaging may potentially be used to decrease acquisition time for bpMRI.

EVIDENCE LEVEL

3.

TECHNICAL EFFICACY

Stage 2.

Evaluation of late gadolinium enhancement cardiac MRI using deep learning reconstruction

BACKGROUND

Deep learning (DL)-based methods have been used to improve the imaging quality of magnetic resonance imaging (MRI) by denoising.

PURPOSE

To assess the effects of DL-based MR reconstruction (DLR) method on late gadolinium enhancement (LGE) image quality.

MATERIAL AND METHODS

A total of 85 patients who underwent cardiovascular magnetic resonance (CMR) examination, including LGE imaging using conventional construction and DLR with varying levels of noise reduction (NR) levels, were included. Both magnitude LGE (MLGE) and phase-sensitive LGE (PSLGE) images were reviewed independently by double-blinded observers who used a 5-point Likert scale for multiple measures regarding image quality. Meanwhile, the signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and edge sharpness of images were calculated and compared between conventional LGE imaging and DLR LGE imaging.

RESULTS

Both MLGE and PSLGE with DLR at 50% and 75% noise reduction levels received significantly higher scores than conventional imaging for overall imaging quality (all P < 0.01). In addition, the SNR, CNR, and edge sharpness of all DLR LGE imaging are higher than conventional imaging (all P < 0.01). The highest subjective score and best image quality is obtained when the DLR noise reduction level is at 75%.

CONCLUSION

DLR reduced image noise while improving image contrast and sharpness in the cardiovascular LGE imaging.

3D cine-magnetic resonance imaging using spatial and temporal implicit neural representation learning (STINR-MR)

Objective

3D cine-magnetic resonance imaging (cine-MRI) can capture images of the human body volume with high spatial and temporal resolutions to study the anatomical dynamics. However, the reconstruction of 3D cine-MRI is challenged by highly undersampled k-space data in each dynamic (cine) frame, due to the slow speed of MR signal acquisition. We proposed a machine learning-based framework, spatial and temporal implicit neural representation learning (STINR-MR), for accurate 3D cine-MRI reconstruction from highly undersampled data.

Approach

STINR-MR used a joint reconstruction and deformable registration approach to achieve a high acceleration factor for cine volumetric imaging. It addressed the ill-posed spatiotemporal reconstruction problem by solving a reference-frame 3D MR image and a corresponding motion model which deforms the reference frame to each cine frame. The reference-frame 3D MR image was reconstructed as a spatial implicit neural representation (INR) network, which learns the mapping from input 3D spatial coordinates to corresponding MR values. The dynamic motion model was constructed via a temporal INR, as well as basis deformation vector fields (DVFs) extracted from prior/onboard 4D-MRIs using principal component analysis (PCA). The learned temporal INR encodes input time points and outputs corresponding weighting factors to combine the basis DVFs into time-resolved motion fields that represent cine-frame-specific dynamics. STINR-MR was evaluated using MR data simulated from the 4D extended cardiac-torso (XCAT) digital phantom, as well as MR data acquired clinically from a healthy human subject. Its reconstruction accuracy was also compared with that of the model-based non-rigid motion estimation method (MR-MOTUS).

Main results

STINR-MR can reconstruct 3D cine-MR images with high temporal (<100 ms) and spatial (3 mm) resolutions. Compared with MR-MOTUS, STINR-MR consistently reconstructed images with better image quality and fewer artifacts and achieved superior tumor localization accuracy via the solved dynamic DVFs. For the XCAT study, STINR reconstructed the tumors to a mean±S.D. center-of-mass error of 1.0±0.4 mm, compared to 3.4±1.0 mm of the MR-MOTUS method. The high-frame-rate reconstruction capability of STINR-MR allows different irregular motion patterns to be accurately captured.

Significance

STINR-MR provides a lightweight and efficient framework for accurate 3D cine-MRI reconstruction. It is a 'one-shot' method that does not require external data for pre-training, allowing it to avoid generalizability issues typically encountered in deep learning-based methods.

Multi-parametric MRI for radiotherapy simulation

Magnetic resonance imaging (MRI) has become an important imaging modality in the field of radiotherapy (RT) in the past decade, especially with the development of various novel MRI and image-guidance techniques. In this review article, we will describe recent developments and discuss the applications of multi-parametric MRI (mpMRI) in RT simulation. In this review, mpMRI refers to a general and loose definition which includes various multi-contrast MRI techniques. Specifically, we will focus on the implementation, challenges, and future directions of mpMRI techniques for RT simulation.

Feasibility and clinical usefulness of deep learning-accelerated MRI for acute painful fracture patients wearing a splint: A prospective comparative study

OBJECTIVE

To evaluate the feasibility and clinical usefulness of deep learning (DL)-accelerated turbo spin echo (TSEDL) sequences relative to standard TSE sequences (TSES) for acute radius fracture patients wearing a splint.

METHODS

This prospective consecutive study investigated 50 patients' preoperative wrist MRI scans acquired between July 2021 and January 2022. Examinations were performed at 3 Tesla MRI with body array coils due to the wrist splint. Besides TSES obtained according to the routine protocol, TSEDL sequences for axial T2-, coronal T1-, and coronal PD-weighted TSE sequences were scanned for comparison. For quantitative assessment, the relative signal-to-noise ratio (rSNR), the relative contrast-to-noise ratio (rCNR), and the relative contrast ratio (rCR) were measured. For qualitative assessment, all images were assessed by two independent musculoskeletal radiologists in terms of perceived SNR, image contrast, image sharpness, artifacts disturbing evaluation, overall image quality and diagnostic confidence for injuries using a four- or five-point Likert scale.

RESULTS

The scan time was shortened approximately by a factor of two for TSEDL compared to TSES. TSEDL images showed significantly better rSNR, rCNR, and rCR values for all sequences, and scored significantly better in terms of both image quality and diagnostic confidence for both readers than TSES images (all p < .05). Interrater reliabilities were in almost perfect agreement.

CONCLUSION

The DL-accelerated technique proved to be very helpful not only to reduce scan time but also to improve image quality for acute painful fracture patients wearing a splint despite using body array coils instead of a wrist-specific coil. Based on our study, the DL-accelerated technique can be very useful for MRI of any part of the extremities in trauma settings just with body array coils.

A convergence analysis for projected fast iterative soft-thresholding algorithm under radial sampling MRI

Radial sampling is a fast magnetic resonance imaging technique. Further imaging acceleration can be achieved with undersampling but how to reconstruct a clear image with fast algorithm is still challenging. Previous work has shown the advantage of removing undersampling image artifacts using the tight-frame sparse reconstruction model. This model was further solved with a projected fast iterative soft-thresholding algorithm (pFISTA). However, the convergence of this algorithm under radial sampling has not been clearly set up. In this work, the authors derived a theoretical convergence condition for this algorithm. This condition was approximated by estimating the maximal eigenvalue of reconstruction operators through the power iteration. Based on the condition, an optimal step size was further suggested to allow the fastest convergence. Verifications were made on the prospective in vivo data of static brain imaging and dynamic contrast-enhanced liver imaging, demonstrating that the recommended parameter allowed fast convergence in radial MRI.

Adaptive model-based Magnetic Resonance

PURPOSE

Conventional sequences are static in nature, fixing measurement parameters in advance in anticipation of a wide range of expected tissue parameter values. We set out to design and benchmark a new, personalized approach-termed adaptive MR-in which incoming subject data is used to update and fine-tune the pulse sequence parameters in real time.

METHODS

We implemented an adaptive, real-time multi-echo (MTE) experiment for estimating T₂ s. Our approach combined a Bayesian framework with model-based reconstruction. It maintained and continuously updated a prior distribution of the desired tissue parameters, including T₂ , which was used to guide the selection of sequence parameters in real time.

RESULTS

Computer simulations predicted accelerations between 1.7- and 3.3-fold for adaptive multi-echo sequences relative to static ones. These predictions were corroborated in phantom experiments. In healthy volunteers, our adaptive framework accelerated the measurement of T₂ for n-acetyl-aspartate by a factor of 2.5.

CONCLUSION

Adaptive pulse sequences that alter their excitations in real time could provide substantial reductions in acquisition times. Given the generality of our proposed framework, our results motivate further research into other adaptive model-based approaches to MRI and MRS.

Accelerating GRAPPA reconstruction using SoC design for real-time cardiac MRI

Real-time cardiac MRI is a rapidly developing area of research that has the potential to improve the diagnosis and treatment of cardiovascular diseases. However, the acquisition of high-quality real-time cardiac MR (CMR) images is challenging as it requires a high frame rate and temporal resolution. To overcome this challenge, there have been recent efforts on several approaches including hardware-based improvements and image reconstruction techniques such as compressed sensing and parallel MRI. The use of parallel MRI techniques such as GRAPPA (Generalized Autocalibrating Partial Parallel Acquisition) is a promising approach for improving the temporal resolution of MRI and expanding its applications in clinical practice. However, the GRAPPA algorithm involves a significant amount of computation, particularly for high acceleration factors and large datasets. This can result in long reconstruction times, which can limit the ability to achieve real-time imaging or high frame rates. One solution to this challenge is to use specialized hardware i.e. field-programmable gate arrays (FPGAs). In this work, a novel 32-bit floating-point FPGA-based GRAPPA accelerator is proposed with an aim to reconstruct high-quality cardiac MR images at higher frame rates, making it well suited for real-time clinical applications. The proposed FPGA-based accelerator consists of custom-designed data processing units named as dedicated computational engines (DCEs) that allow for a continuous flow of data between the calibration and synthesis stages of GRAPPA reconstruction process. This greatly increases the throughput and reduces the latency of the overall proposed system. Moreover, a high-speed memory module (DDR4-SDRAM) is integrated with the proposed architecture to store the multi-coil MR data. An on-chip quad-core ARM Cortex-A53 processor is used to manage access control information required for data transfer between the DCEs and DDR4-SDRAM. The proposed accelerator is implemented on Xilinx Zynq UltraScale + MPSoC using high-level synthesis (HLS) and hardware descriptive language (HDL) with an aim to explore the trade-offs between the reconstruction time, resource utilization and design effort. Several experiments have been performed using in-vivo cardiac datasets i.e. 18-receiver coil and 30-receiver coil to evaluate the performance of the proposed accelerator. A comparison is performed with the contemporary CPU and GPU-based GRAPPA reconstruction methods in terms of reconstruction time, frames-per-second and reconstruction accuracy (RMSE and SNR). The results show that the proposed accelerator achieves speed-up factors up to 121× and 9× as compared to the contemporary CPU-based and GPU-based GRAPPA reconstruction methods, respectively. Moreover, it has been demonstrated that the proposed accelerator can achieve reconstruction rates of up to ∼27 frames-per-second while maintaining the visual quality of the reconstructed images.

AI in MRI: Computational Frameworks for a Faster, Optimized, and Automated Imaging Workflow

Over the last decade, artificial intelligence (AI) has made an enormous impact on a wide range of fields, including science, engineering, informatics, finance, and transportation [...].

Rapid 3D breath-hold MR cholangiopancreatography using deep learning-constrained compressed sensing reconstruction

OBJECTIVES

To compare the image quality of three-dimensional breath-hold magnetic resonance cholangiopancreatography with deep learning-based compressed sensing reconstruction (3D DL-CS-MRCP) to those of 3D breath-hold MRCP with compressed sensing (3D CS-MRCP), 3D breath-hold MRCP with gradient and spin-echo (3D GRASE-MRCP) and conventional 2D single-shot breath-hold MRCP (2D MRCP).

METHODS

In total, 102 consecutive patients who underwent MRCP at 3.0 T, including 2D MRCP, 3D GRASE-MRCP, 3D CS-MRCP, and 3D DL-CS-MRCP, were prospectively included. Two radiologists independently analyzed the overall image quality, background suppression, artifacts, and visualization of pancreaticobiliary ducts using a five-point scale. The signal-to-noise ratio (SNR) of the common bile duct (CBD), contrast-to-noise ratio (CNR) of the CBD and liver, and contrast ratio between the periductal tissue and CBD were measured. The Friedman test was performed to compare the four protocols.

RESULTS

3D DL-CS-MRCP resulted in improved SNR and CNR values compared with those in the other three protocols, and better contrast ratio compared with that in 3D CS-MRCP and 3D GRASE-MRCP (all, p < 0.05). Qualitative image analysis showed that 3D DL-CS-MRCP had better performance for second-level intrahepatic ducts and distal main pancreatic ducts compared with 3D CS-MRCP (all, p < 0.05). Compared with 2D MRCP, 3D DL-CS-MRCP demonstrated better performance for the second-order left intrahepatic duct but was inferior in assessing the main pancreatic duct (all, p < 0.05). Moreover, the image quality was significantly higher in 3D DL-CS-MRCP than in 3D GRASE-MRCP.

CONCLUSION

3D DL-CS-MRCP has superior performance compared with that of 3D CS-MRCP or 3D GRASE-MRCP. Deep learning reconstruction also provides a comparable image quality but with inferior main pancreatic duct compared with that revealed by 2D MRCP.

KEY POINTS

• 3D breath-hold MRCP with deep learning reconstruction (3D DL-CS-MRCP) demonstrated improved image quality compared with that of 3D MRCP with compressed sensing or GRASE. • Compared with 2D MRCP, 3D DL-CS-MRCP had superior performance in SNR and CNR, better visualization of the left second-level intrahepatic bile ducts, and comparable overall image quality, but an inferior main pancreatic duct.

Kz-accelerated variable-density stack-of-stars MRI

This work aimed to develop a modified stack-of-stars golden-angle radial sampling scheme with variable-density acceleration along the slice (kz) dimension (referred to as VD-stack-of-stars) and to test this new sampling trajectory with multi-coil compressed sensing reconstruction for rapid motion-robust 3D liver MRI. VD-stack-of-stars sampling implements additional variable-density undersampling along the kz dimension, so that slice resolution (or volumetric coverage) can be increased without prolonging scan time. The new sampling trajectory (with increased slice resolution) was compared with standard stack-of-stars sampling with fully sampled kz (with standard slice resolution) in both non-contrast-enhanced free-breathing liver MRI and dynamic contrast-enhanced MRI (DCE-MRI) of the liver in volunteers. For both sampling trajectories, respiratory motion was extracted from the acquired radial data, and images were reconstructed using motion-compensated (respiratory-resolved or respiratory-weighted) dynamic radial compressed sensing reconstruction techniques. Qualitative image quality assessment (visual assessment by experienced radiologists) and quantitative analysis (as a metric of image sharpness) were performed to compare images acquired using the new and standard stack-of-stars sampling trajectories. Compared to standard stack-of-stars sampling, both non-contrast-enhanced and DCE liver MR images acquired with VD-stack-of-stars sampling presented improved overall image quality, sharper liver edges and increased hepatic vessel clarity in all image planes. The results have suggested that the proposed VD-stack-of-stars sampling scheme can achieve improved performance (increased slice resolution or volumetric coverage with better image quality) over standard stack-of-stars sampling in free-breathing DCE-MRI without increasing scan time. The reformatted coronal and sagittal images with better slice resolution may provide added clinical value.

Characterization of Effects of Compressed Sensing on High Spectral and Spatial Resolution (HiSS) MRI with Comparison to SENSE

High Spectral and Spatial resolution (HiSS) MRI shows high diagnostic performance in the breast. Acceleration methods based on k-space undersampling could allow stronger T2*-based image contrast and/or higher spectral resolution, potentially increasing diagnostic performance. An agar/oil phantom was prepared with water-fat boundaries perpendicular to the readout and phase encoding directions in a breast coil. HiSS MRI was acquired at 3T, at sensitivity encoding (SENSE) acceleration factors R of up to 10, and the R = 1 dataset was used to simulate corresponding compressed sensing (CS) accelerations. Image quality was evaluated by quantifying noise and artifact levels. Effective spatial resolution was determined via modulation transfer function analysis. Dispersion vs. absorption (DISPA) analysis and full width at half maximum (FWHM) quantified spectral lineshape changes. Noise levels remained constant with R for CS but amplified with SENSE. SENSE preserved the spatial resolution of HiSS MRI, while CS reduced it in the phase encoding direction. SENSE showed no effect on FWHM or DISPA markers, while CS increased FWHM. Thus, CS might perform better in noise-limited or geometrically constrained applications, but in geometric configurations specific to breast MRI, spectral analysis might be compromised, decreasing the diagnostic performance of HiSS MRI.

Evaluating prostate cancer bone metastasis using accelerated whole-body isotropic 3D T1-weighted Dixon MRI with compressed SENSE: a feasibility study

OBJECTIVES

The study aimed to assess the efficiency of whole-body high-resolution compressed sensing-sensitivity encoding isotropic T1-Weighted Dixon (CSI-T1W-Dixon) scans in evaluating bone metastasis.

METHODS

Forty-five high-risk prostate cancer patients with bone metastases were enrolled prospectively and underwent whole-body MRI sequences, which included the following: pre- and post-contrast CSI-T1W-Dixon and conventional multi-planar T1-Weighted Dixon (CMP-T1W-Dixon) (coronal, sagittal, and axial scans), short tau inversion recovery (STIR), and DWI. Comparison between the CMP-T1W-Dixon and CSI-T1W-Dixon images was done for the subjective image quality, the quantitative contrast-to-noise ratio (CNR), and signal-to-noise ratio (SNR). Furthermore, the diagnostic performance based on per-lesion and per-patient basis utilizing non-contrast T1-weighted (T1)/T1+ contrasted T1-weighted (T1C)/T1 + T1C + STIR + DWI sequences was compared between the CSI-T1W-Dixon and CMP-T1W-Dixon methods using reference standards (combining biopsy data and 6-month imaging follow-up).

RESULT

The CSI-T1W-Dixon images produced fewer image artifacts in the axial and coronal planes compared to the CMP-T1W-Dixon images. Also, the CSI-T1W-Dixon images provided better a CNR in fat-only images of all three planes and water-only images of the axial plane (p < 0.05). The CSI-T1W-Dixon showed a higher sensitivity than the CMP-T1W-Dixon techniques in analyzing T1-only images on a per-lesion basis (82.7% vs. 53.8% for sensitivity, p = 0.03). On a per-patient basis, no difference was found in the diagnostic capacity between the CSI-T1W-Dixon and CMP-T1W-Dixon sequences either alone or in combinations (p = 0.57-1).

CONCLUSION

High-resolution CSI-T1W-Dixon with higher image quality and diagnostic capacity can replace the CMP-T1W-Dixon method in evaluating bone metastasis in clinical practice.

KEY POINTS

• Compressed sensing isotropic acquisition for 3D T1-weighted Dixon images can improve the image quality with fewer artifacts compared to the anisotropic multiplanar acquisition. • Compressed sensing isotropic acquisition can save 67% of scanning time compared to anisotropic multiplanar acquisition. • Compressed sensing isotropic 3D T1-weighted Dixon images can offer better diagnostic performance with higher sensitivity compared to anisotropic multiplanar images.

Dark blood T2-weighted imaging of the human heart with AI-assisted compressed sensing: a patient cohort study

Background

Dark blood T2-weighted (DB-T2W) imaging is widely used to evaluate myocardial edema in myocarditis and inflammatory cardiomyopathy. However, this technique is sensitive to arrhythmia, tachycardia, and cardiac and respiratory motion due to the long scan time with multiple breath-holds. The application of artificial intelligence (AI)-assisted compressed sensing (ACS) has facilitated significant progress in accelerating medical imaging. However, the effect of DB-T2W imaging on ACS has not been elucidated. This study aimed to examine the effects of ACS on the image quality of single-shot and multi-shot DB-T2W imaging of edema.

Methods

Thirty-three patients were included in this study and received DB-T2W imaging with ACS, including single-shot acquisition (SS-ACS) and multi-shot acquisition (MS-ACS). The resulting images were compared with those of the conventional multi-shot DB-T2W imaging with parallel imaging (MS-PI). Quantitative assessments of the signal-to-noise ratio (SNR), tissue contrast ratio (CR), and contrast-to-noise ratio (CNR) were performed. Three radiologists independently evaluated the overall image quality, blood nulling, free wall of the left ventricle, free wall of the right ventricle, and interventricular septum using a 5-point Likert scale.

Results

The total scan time of the DB-T2W imaging with ACS was significantly reduced compared to the conventional parallel imaging [number of heartbeats (SS-ACS:MS-ACS:MS-PI) =19:63:99; P<0.001]. The SNR_myocardium and CNR_{blood-myocardium} of MS-ACS and SS-ACS were higher than those of MS-PI (all P values <0.01). Furthermore, the CR_{blood-myocardium} of SS-ACS was also higher than that of MS-PI (P<0.01). There were significant differences in overall image quality, blood nulling, left ventricle free wall visibility, and septum visibility between the MS-PI, MS-ACS, and SS-ACS protocols (all P values <0.05). Moreover, blood in the heart was better nulled using SS-ACS (P<0.01).

Conclusions

The ACS method shortens the scan time of DB-T2W imaging and achieves comparable or even better image quality compared to the PI method. Moreover, DB-T2W imaging using the ACS method can reduce the number of breath-holds to 1 with single-shot acquisition.