Deep Learning Super-Resolution Reconstruction for Fast and Motion-Robust T2-weighted Prostate MRI

Background Deep learning (DL) reconstructions can enhance image quality while decreasing MRI acquisition time. However, DL reconstruction methods combined with compressed sensing for prostate MRI have not been well studied. Purpose To use an industry-developed DL algorithm to reconstruct low-resolution T2-weighted turbo spin-echo (TSE) prostate MRI scans and compare these with standard sequences. Materials and Methods In this prospective study, participants with suspected prostate cancer underwent prostate MRI with a Cartesian standard-resolution T2-weighted TSE sequence (T2C) and non-Cartesian standard-resolution T2-weighted TSE sequence (T2NC) between August and November 2022. Additionally, a low-resolution Cartesian DL-reconstructed T2-weighted TSE sequence (T2DL) with compressed sensing DL denoising and resolution upscaling reconstruction was acquired. Image sharpness was assessed qualitatively by two readers using a five-point Likert scale (from 1 = nondiagnostic to 5 = excellent) and quantitatively by calculating edge rise distance. The Friedman test and one-way analysis of variance with post hoc Bonferroni and Tukey tests, respectively, were used for group comparisons. Prostate Imaging Reporting and Data System (PI-RADS) score agreement between sequences was compared by using Cohen κ. Results This study included 109 male participants (mean age, 68 years ± 8 [SD]). Acquisition time of T2DL was 36% and 29% lower compared with that of T2C and T2NC (mean duration, 164 seconds ± 20 vs 257 seconds ± 32 and 230 seconds ± 28; P < .001 for both). T2DL showed improved image sharpness compared with standard sequences using both qualitative (median score, 5 [IQR, 4-5] vs 4 [IQR, 3-4] for T2C and 4 [IQR, 3-4] for T2NC; P < .001 for both) and quantitative (mean edge rise distance, 0.75 mm ± 0.39 vs 1.15 mm ± 0.68 for T2C and 0.98 mm ± 0.65 for T2NC; P < .001 and P = .01) methods. PI-RADS score agreement between T2NC and T2DL was excellent (κ range, 0.92-0.94 [95% CI: 0.87, 0.98]). Conclusion DL reconstruction of low-resolution T2-weighted TSE sequences enabled accelerated acquisition times and improved image quality compared with standard acquisitions while showing excellent agreement with conventional sequences for PI-RADS ratings. Clinical trial registration no. NCT05820113 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Turkbey in this issue.

Non-contrast free-breathing 3D cardiovascular magnetic resonance angiography using REACT (relaxation-enhanced angiography without contrast) compared to contrast-enhanced steady-state magnetic resonance angiography in complex pediatric congenital heart disease at 3T

BACKGROUND

To evaluate the great vessels in young children with complex congenital heart disease (CHD) using non-contrast cardiovascular magnetic resonance angiography (CMRA) based on three-dimensional relaxation-enhanced angiography without contrast (REACT) in comparison to contrast-enhanced steady-state CMRA.

METHODS

In this retrospective study from April to July 2021, respiratory- and electrocardiogram-gated native REACT CMRA was compared to contrast-enhanced single-phase steady-state CMRA in children with CHD who underwent CMRA at 3T under deep sedation. Vascular assessment included image quality (1 = non-diagnostic, 5 = excellent), vessel diameter, and diagnostic findings. For statistical analysis, paired t-test, Pearson correlation, Bland-Altman analysis, Wilcoxon test, and intraclass correlation coefficients (ICC) were applied.

RESULTS

Thirty-six young children with complex CHD (median 4 years, interquartile range, 2-5; 20 males) were included. Native REACT CMRA was obtained successfully in all patients (mean scan time: 4:22 ± 1:44 min). For all vessels assessed, diameters correlated strongly between both methods (Pearson r = 0.99; bias = 0.04 ± 0.61 mm) with high interobserver reproducibility (ICC: 0.99 for both CMRAs). Native REACT CMRA demonstrated comparable overall image quality to contrast-enhanced CMRA (3.9 ± 1.0 vs. 3.8 ± 0.9, P = 0.018). With REACT CMRA, better image quality was obtained at the ascending aorta (4.8 ± 0.5 vs. 4.3 ± 0.8, P < 0.001), coronary roots (e.g., left: 4.1 ± 1.0 vs. 3.3 ± 1.1, P = 0.001), and inferior vena cava (4.6 ± 0.5 vs. 3.2 ± 0.8, P < 0.001). In all patients, additional vascular findings were assessed equally with native REACT CMRA and the contrast-enhanced reference standard (n = 6).

CONCLUSION

In young children with complex CHD, REACT CMRA can provide gadolinium-free high image quality, accurate vascular measurements, and equivalent diagnostic quality compared to standard contrast-enhanced CMRA.

Fetal Cardiac Cine MRI with Doppler US Gating in Complex Congenital Heart Disease

Purpose

To apply Doppler US (DUS)-gated fetal cardiac cine MRI in clinical routine and investigate diagnostic performance in complex congenital heart disease (CHD) compared with that of fetal echocardiography.

Materials and Methods

In this prospective study (May 2021 to March 2022), women with fetuses with CHD underwent fetal echocardiography and DUS-gated fetal cardiac MRI on the same day. For MRI, balanced steady-state free precession cine images were acquired in the axial and optional sagittal and/or coronal orientations. Overall image quality was assessed on a four-point Likert scale (from 1 = nondiagnostic to 4 = good image quality). The presence of abnormalities in 20 fetal cardiovascular features was independently assessed by using both modalities. The reference standard was postnatal examination results. Differences in sensitivities and specificities were determined by using a random-effects model.

Results

The study included 23 participants (mean age, 32 years ± 5 [SD]; mean gestational age, 36 weeks ± 1). Fetal cardiac MRI was completed in all participants. The median overall image quality of DUS-gated cine images was 3 (IQR, 2.5-4). In 21 of 23 participants (91%), underlying CHD was correctly assessed by using fetal cardiac MRI. In one case, the correct diagnosis was made by using MRI only (situs inversus and congenitally corrected transposition of the great arteries). Sensitivities (91.8% [95% CI: 85.7, 95.1] vs 93.6% [95% CI: 88.8, 96.2]; P = .53) and specificities (99.9% [95% CI: 99.2, 100] vs 99.9% [95% CI: 99.5, 100]; P > .99) for the detection of abnormal cardiovascular features were comparable between MRI and echocardiography, respectively.

Conclusion

Using DUS-gated fetal cine cardiac MRI resulted in performance comparable with that of using fetal echocardiography for diagnosing complex fetal CHD.Keywords: Pediatrics, MR-Fetal (Fetal MRI), Cardiac, Heart, Congenital, Fetal Imaging, Cardiac MRI, Prenatal, Congenital Heart DiseaseClinical trial registration no. NCT05066399 Supplemental material is available for this article. © RSNA, 2023See also the commentary by Biko and Fogel in this issue.

Free-breathing non-contrast flow-independent cardiovascular magnetic resonance angiography using cardiac gated, magnetization-prepared 3D Dixon method: assessment of thoracic vasculature in congenital heart disease

BACKGROUND

To evaluate a non-contrast respiratory- and electrocardiogram-gated 3D cardiovascular magnetic resonance angiography (CMRA) based on magnetization-prepared Dixon method (relaxation-enhanced angiography without contrast and triggering, REACT) for the assessment of the thoracic vasculature in congenital heart disease (CHD) patients.

METHODS

70 patients with CHD (mean 28 years, range: 10-65 years) were retrospectively identified in this single-center study. REACT-CMRA was applied with respiratory- and cardiac-gating. Image quality (IQ) of REACT-CMRA was compared to standard non-gated multi-phase first-pass-CMRA and respiratory- and electrocardiogram-gated steady-state-CMRA. IQ of different vessels of interest (ascending aorta, left pulmonary artery, left superior pulmonary vein, right coronary ostium, coronary sinus) was independently assessed by two readers on a five-point Likert scale. Measurements of vessel diameters were performed in predefined anatomic landmarks (ascending aorta, left pulmonary artery, left superior pulmonary vein). Both readers assessed artifacts and vascular abnormalities. Friedman test, chi-squared test, and Bland-Altman method were used for statistical analysis.

RESULTS

Overall IQ score of REACT-CMRA was higher compared to first-pass-CMRA (3.5 ± 0.4 vs. 2.7 ± 0.4, P < 0.001) and did not differ from steady-state-CMRA (3.5 ± 0.4 vs. 3.5 ± 0.6, P = 0.99). Non-diagnostic IQ of the defined vessels of interest was observed less frequently on REACT-CMRA (1.7 %) compared to steady-state- (4.3 %, P = 0.046) or first-pass-CMRA (20.9 %, P < 0.001). Close agreements in vessel diameter measurements were observed between REACT-CMRA and steady-state-CMRA (e.g. ascending aorta, bias: 0.38 ± 1.0 mm, 95 % limits of agreement (LOA): - 1.62-2.38 mm). REACT-CMRA showed high intra- (bias: 0.04 ± 1.0 mm, 95 % LOA: - 1.9-2.0 mm) and interobserver (bias: 0.20 ± 1.1 mm, 95 % LOA: - 2.0-2.4 mm) agreements regarding vessel diameter measurements. Fat-water separation artifacts were observed in 11/70 (16 %) patients on REACT-CMRA but did not limit diagnostic utility. Six vascular abnormalities were detected on REACT-CMRA that were not seen on standard contrast-enhanced CMRA.

CONCLUSIONS

Non-contrast-enhanced cardiac-gated REACT-CMRA offers a high diagnostic quality for assessment of the thoracic vasculature in CHD patients.

Qualitative and Quantitative Comparison of Respiratory Triggered Reduced Field-of-View (FOV) Versus Full FOV Diffusion Weighted Imaging (DWI) in Pancreatic Pathologies

RATIONALE AND OBJECTIVES

To investigate the effects of a reduced field-of-view (rFOV) acquisition in diffusion-weighted magnetic resonance imaging of the pancreas.

MATERIALS AND METHODS

We enrolled 153 patients who underwent routine clinical MRI work-up including respiratory-triggered diffusion-weighted single-shot echo-planar imaging (DWI) with full field-of-view (fFOV, 3 × 3 × 4 mm³ voxel size) and reduced field-of-view (rFOV, 2.5 × 2.5 × 3 mm³ voxel size) for suspected pancreatic pathology. Two experienced radiologists were asked to subjectively rate (Likert Scale 1-4) image quality (overall image quality, lesion conspicuity, anatomical detail, artifacts). In addition, quantitative image parameters were assessed (apparent diffusion coefficient, apparent signal to noise ratio, apparent contrast to noise ratio [CNR]).

RESULTS

All subjective metrics of image quality were rated in favor of rFOV DWI images compared to fFOV DWI images with substantial-to-high inter-rater reliability. Calculated ADC values of normal pancreas, pancreatic pathologies and reference tissues revealed no differences between both sequences. Whereas the apparent signal to noise ratio was higher in fFOV images, apparent CNR was higher in rFOV images.

CONCLUSION

rFOV DWI provides higher image quality and apparent CNR values, favorable in the analysis of pancreatic pathologies.

T2 Turbo Spin Echo With Compressed Sensing and Propeller Acquisition (Sampling k-Space by Utilizing Rotating Blades) for Fast and Motion Robust Prostate MRI: Comparison With Conventional Acquisition

OBJECTIVES

The aim of this study was to compare a new compressed sensing (CS) method for T2-weighted propeller acquisitions (T2 CS ) with conventional T2-weighted propeller sequences (T2 conv ) in terms of achieving a higher image quality, while reducing the acquisition time.

MATERIALS AND METHODS

Male participants with a clinical suspicion of prostate cancer were prospectively enrolled and underwent prostate magnetic resonance imaging at 3 T. Axial and sagittal images of the T2 conv sequence and the T2 CS sequence were acquired. Sequences were qualitatively assessed by 2 blinded radiologists concerning artifacts, image-sharpness, lesion conspicuity, capsule delineation, and overall image quality using 5-point Likert items ranging from 1 (nondiagnostic) to 5 (excellent). The apparent signal-to-noise ratio and apparent contrast-to-noise ratio were evaluated. PI-RADS scores were assessed for both sequences. Statistical analysis was performed by using Wilcoxon signed rank test and paired samples t test. Intrarater and interrater reliability of qualitative image evaluation was assessed using intraclass correlation coefficient (ICC) estimates.

RESULTS

A total of 29 male participants were included (mean age, 66 ± 8 years). The acquisition time of the T2 CS sequence was respectively 26% (axial plane) and 24% (sagittal plane) shorter compared with the T2 conv sequence (eg, axial: 171 vs 232 seconds; P < 0.001). In the axial plane, the T2 CS sequence had fewer artifacts (4 [4-4.5] vs 4 [3-4]; P < 0.001), better image-sharpness (4 [4-4.5] vs 3 [3-3.5]; P < 0.001), better capsule delineation (4 [3-4] vs 3 [3-3.5]; P < 0.001), and better overall image quality (4 [4-4] vs 4 [3-4]; P < 0.001) compared with the T2 conv sequence. The ratings of lesion conspicuity were similar (4 [4-4] vs 4 [3-4]; P = 0.166). In the sagittal plane, the T2 CS sequence outperformed the T2 conv sequence in the categories artifacts (4 [4-4] vs 3 [3-4]; P < 0.001), image sharpness (4 [4-5] vs 4 [3-4]; P < 0.001), lesion conspicuity (4 [4-4] vs 4 [3-4]; P = 0.002), and overall image quality (4 [4-4] vs 4 [3-4]; P = 0.002). Capsule delineation was similar between both sequences (3 [3-4] vs 3 [3-3]; P = 0.07). Intraobserver and interobserver reliability for qualitative scoring were good (ICC intra: 0.92; ICC inter: 0.86). Quantitative analysis revealed a higher apparent signal-to-noise ratio (eg, axial: 52.2 ± 9.7 vs 22.8 ± 3.6; P < 0.001) and a higher apparent contrast-to-noise ratio (eg, axial: 44.0 ± 9.6 vs 18.6 ± 3.7; P ≤ 0.001) of the T2 CS sequence. PI-RADS scores were the same for both sequences in all participants.

CONCLUSIONS

CS-accelerated T2-weighted propeller acquisition had a superior image quality compared with conventional T2-weighted propeller sequences while significantly reducing the acquisition time.

Acceleration of chemical shift encoding-based water fat MRI for liver proton density fat fraction and T2* mapping using compressed sensing

Objectives

To evaluate proton density fat fraction (PDFF) and T2* measurements of the liver with combined parallel imaging (sensitivity encoding, SENSE) and compressed sensing (CS) accelerated chemical shift encoding-based water-fat separation.

Methods

Six-echo Dixon imaging was performed in the liver of 89 subjects. The first acquisition variant used acceleration based on SENSE with a total acceleration factor equal to 2.64 (acquisition labeled as SENSE). The second acquisition variant used acceleration based on a combination of CS with SENSE with a total acceleration factor equal to 4 (acquisition labeled as CS+SENSE). Acquisition times were compared between acquisitions and proton density fat fraction (PDFF) and T2*-values were measured and compared separately for each liver segment.

Results

Total scan duration was 14.5 sec for the SENSE accelerated image acquisition and 9.3 sec for the CS+SENSE accelerated image acquisition. PDFF and T2* values did not differ significantly between the two acquisitions (paired Mann-Whitney and paired t-test P>0.05 in all cases). CS+SENSE accelerated acquisition showed reduced motion artifacts (1.1%) compared to SENSE acquisition (12.3%).

Conclusion

CS+SENSE accelerates liver PDFF and T2*mapping while retaining the same quantitative values as an acquisition using only SENSE and reduces motion artifacts.

Free-breathing high resolution modified Dixon steady-state angiography with compressed sensing for the assessment of the thoracic vasculature in pediatric patients with congenital heart disease

BACKGROUND

Cardiovascular magnetic resonance angiography (CMRA) is a non-invasive imaging modality of choice in pediatric patients with congenital heart disease (CHD). This study was aimed to evaluate the diagnostic utility of a respiratory- and electrocardiogram-gated steady-state CMRA with modified Dixon (mDixon) fat suppression technique and compressed sensing in comparison to standard first-pass CMRA in pediatric patients with CHD at 3 T.

METHODS

In this retrospective single center study, pediatric CHD patients who underwent CMR with first-pass CMRA followed by mDixon steady-state CMRA at 3 T were analyzed. Image quality using a Likert scale from 5 (excellent) to 1 (non-diagnostic) and quality of fat suppression were assessed in consensus by two readers. Blood-to-tissue contrast and quantitative measurements of the thoracic vasculature were assessed separately by two readers. CMRA images were reevaluated by two readers for additional findings, which could be identified only on either one of the CMRA types. Paired Student t test, Wilcoxon test, and intraclass correlation coefficients (ICCs) were used for statistical analysis.

RESULTS

32 patients with CHD (3.3 ± 1.7 years, 13 female) were included. Overall image quality of steady-state mDixon CMRA was higher compared to first-pass CMRA (4.5 ± 0.5 vs. 3.3 ± 0.5; P < 0.001). Blood-to-tissue contrast ratio of steady-state mDixon CMRA was comparable to first-pass CMRA (7.85 ± 4.75 vs. 6.35 ± 2.23; P = 0.133). Fat suppression of steady-state mDixon CMRA was perfect in 30/32 (94%) cases. Vessel diameters were greater in first-pass CMRA compared to steady-state mDixon CMRA with the greatest differences at the level of pulmonary arteries and veins (e.g., right pulmonary artery for reader 1: 10.4 ± 2.4 vs. 9.9 ± 2.3 mm, P < 0.001). Interobserver agreement was higher for steady-state mDixon CMRA for all measurements compared to first-pass CMRA (ICCs > 0.92). In 9/32 (28%) patients, 10 additional findings were identified on mDixon steady-state CMRA (e.g., partial anomalous venous return, abnormalities of coronary arteries, subclavian artery stenosis), which were not depicted using first-pass CMRA.

CONCLUSIONS

Steady-state mDixon CMRA offers a robust fat suppression, a high image quality, and diagnostic utility for the assessment of the thoracic vasculature in pediatric CHD patients.

Free-breathing pseudo-golden-angle bSSFP cine cardiac MRI for biventricular functional assessment in congenital heart disease

PURPOSE

To compare standard breath-hold (BH) cine imaging to a radial pseudo-golden-angle free-breathing (FB) technique in congenital heart disease (CHD).

METHODS

In this prospective study, short-axis and 4-chamber BH and FB cardiac MRI sequences of 25 participants with CHD acquired at 1.5 Tesla, were quantitatively compared regarding ventricular volumes, function, interventricular septum thickness (IVSD), apparent signal to noise ratio (aSNR), and estimated contrast to noise ratio (eCNR). For qualitative comparison, three image quality criteria (contrast, endocardial edge definition, and artefacts) were rated on a 5-point Likert scale (5: excellent, 1: non-diagnostic). Paired t-Test was used for group comparisons, Bland-Altman analysis for agreement between techniques. Inter-reader agreement was compared using intraclass correlation coefficient.

RESULTS

IVSD (BH 7.4 ± 2.1 mm vs FB 7.4 ± 1.9 mm, p =.71), biventricular ejection fraction (left ventricle [LV]: 56.4 ± 10.8% vs 56.1 ± 9.3%, p =.83; right ventricle [RV]: 49.5 ± 8.6% vs 49.7 ± 10.1%, p =.83), and biventricular end diastolic volume (LV: 176.3 ± 63.9 ml vs 173.9 ± 64.9 ml, p =.90; RV: 185.4 ± 63.8 ml vs 189.6 ± 66.6 ml, p =.34) were comparable. Mean measurement time for FB short-axis sequences was 8.1 ± 1.3 compared to 4.4 ± 1.3 min for BH (p <.001). Subjective image quality between sequences was deemed comparable, (4.6 ± 0.6 vs 4.5 ± 0.6, p =.26, for 4-chamber views) with a significant difference regarding short-axis views (4.9 ± 0.3 vs 4.5 ± 0.6, p =.008). aSNR was similar (BH 25.8 ± 11.2 vs FB 22.2 ± 9.5, p =.24), while eCNR was higher for BH (89.1 ± 36.1 vs 68.5 ± 32.1, p =.03).

CONCLUSION

FB sequences yielded comparable results to BH regarding image quality, biventricular volumetry, and function, though measurement times were longer. The FB sequence described might be clinically valuable when BHs are insufficiently performed.

Fast 3D Isotropic Proton Density-Weighted Fat-Saturated MRI of the Knee at 1.5 T with Compressed Sensing: Comparison with Conventional Multiplanar 2D Sequences

PURPOSE

 Compressed sensing (CS) is a method to accelerate MRI acquisition by acquiring less data through undersampling of k-space. In this prospective study we aimed to evaluate whether a three-dimensional (3D) isotropic proton density-weighted fat saturated sequence (PDwFS) with CS can replace conventional multidirectional two-dimensional (2D) sequences at 1.5 Tesla.

MATERIALS AND METHODS

 20 patients (45.2 ± 20.2 years; 10 women) with suspected internal knee damage received a 3D PDwFS with CS acceleration factor 8 (acquisition time: 4:11 min) in addition to standard three-plane 2D PDwFS sequences (acquisition time: 4:05 min + 3:03 min + 4:46 min = 11:54 min) at 1.5 Tesla. Scores for homogeneity of fat saturation, image sharpness, and artifacts were rated by two board-certified radiologists on the basis of 5-point Likert scales. Based on these ratings, an overall image quality score was generated. Additionally, quantitative contrast ratios for the menisci (MEN), the anterior (ACL) and the posterior cruciate ligament (PCL) in comparison with the popliteus muscle were calculated.

RESULTS

 The overall image quality was rated superior in 3D PDwFS compared to 2D PDwFS sequences (14.45 ± 0.83 vs. 12.85 ± 0.99; p < 0.01), particularly due to fewer artifacts (4.65 ± 0.67 vs. 3.65 ± 0.49; p < 0.01) and a more homogeneous fat saturation (4.95 ± 0.22 vs. 4.55 ± 0.51; p < 0.01). Scores for image sharpness were comparable (4.80 ± 0.41 vs. 4.65 ± 0.49; p = 0.30). Quantitative contrast ratios for all measured structures were superior in 3D PDwFS (MEN: p < 0.05; ACL: p = 0.06; PCL: p = 0.33). In one case a meniscal tear was only diagnosed using multiplanar reformation of 3D PDwFS, but it would have been missed on standard multiplanar 2D sequences.

CONCLUSION

 An isotropic fat-saturated 3D PD sequence with CS enables fast and high-quality 3D imaging of the knee joint at 1.5 T and may replace conventional multiplanar 2D sequences. Besides faster image acquisition, the 3D sequence provides advantages in small structure imaging by multiplanar reformation.

KEY POINTS

  · 3D PDwFS with compressed sensing enables knee imaging that is three times faster compared to multiplanar 2D sequences. · 3D PDwFS with compressed sensing provides high-quality knee imaging at 1.5 T. · Isotropic 3D sequences provide advantages in small structure imaging by using multiplanar reformations.

CITATION FORMAT

· Endler CH, Faron A, Isaak A et al. Fast 3D Isotropic Proton Density-Weighted Fat-Saturated MRI of the Knee at 1.5 T with Compressed Sensing: Comparison with Conventional Multiplanar 2D Sequences. Fortschr Röntgenstr 2021; 193: 813 - 821.

Audiovisual Breathing Guidance for Improved Image Quality and Scan Efficiency of T2- and Diffusion-Weighted Liver MRI

OBJECTIVES

Impaired image quality and long scan times frequently occur in respiratory-triggered sequences in liver magnetic resonance imaging (MRI). We evaluated the impact of an in-bore active breathing guidance (BG) application on image quality and scan time of respiratory-triggered T2-weighted (T2) and diffusion-weighted imaging (DWI) by comparing sequences with standard triggering (T2S and DWIS) and with BG (T2BG and DWIBG).

MATERIALS AND METHODS

In this prospective study, random patients with clinical indications for liver MRI underwent 3 T MRI with standard and BG acquisitions. The audiovisual BG application received the respiratory signal from the scanner, and animated breathing instructions were displayed using a mirror and screen behind the MRI bore. Prior to the DWIBG and T2BG acquisition, patients received a short video instruction about MRI with BG. Suitable parameters for desired breathing pattern for T2BG and DWIBG were set individually for each patient based on the patient's physical respiratory ability (ie, 4 seconds breathing followed by 4.5 seconds breath holding). Artifacts, sharpness, lesion conspicuity, and overall image quality were assessed using a Likert scale from 1 (nondiagnostic) to 5 (excellent). Scan time, apparent contrast-to-noise ratio, and apparent signal-to-noise ratio (aSNR) for all sequences were analyzed. Paired t test and Wilcoxon test were used for statistical analysis.

RESULTS

Thirty-two patients (mean age: 55 ± 13 years, 13 female) were included. T2BG showed less artifacts (4.5 ± 0.7 vs 4.1 ± 0.8, P < 0.001) and better sharpness, lesion conspicuity, and overall image quality (eg, overall image quality 4.6 ± 0.7 vs 4.4 ± 0.7, P = 0.004) compared with T2S. DWIBG demonstrated improved image quality in all categories compared with DWIS (eg, overall image quality 4.5 ± 0.5 vs 4.3 ± 0.5, P = 0.005) and less artifacts (4.1 ± 0.5 vs 3.8 ± 0.7, P = 0.007). Scan times of T2BG (286 ± 23 vs 345 ± 68 seconds, P < 0.001) and DWIBG (160 ± 4 vs 252 ± 70 seconds, P < 0.001) were reduced by 17% and 37%, respectively. aSNR and apparent contrast-to-noise ratio (eg, aSNR: 23.45 ± 11.31 [T2BG] vs 25.84 ± 10.76 [T2S]; P = 0.079) were similar for both sequences for both approaches.

CONCLUSIONS

Active BG for respiratory-triggered liver T2w and DWI sequences led to significant reduction of breathing artifacts, improved image quality, and shorter scan time compared with standard acquisitions.

Deep learning denoising reconstruction for improved image quality in fetal cardiac cine MRI

Purpose

This study aims to evaluate deep learning (DL) denoising reconstructions for image quality improvement of Doppler ultrasound (DUS)-gated fetal cardiac MRI in congenital heart disease (CHD).

Methods

Twenty-five fetuses with CHD (mean gestational age: 35 ± 1 weeks) underwent fetal cardiac MRI at 3T. Cine imaging was acquired using a balanced steady-state free precession (bSSFP) sequence with Doppler ultrasound gating. Images were reconstructed using both compressed sensing (bSSFP CS) and a pre-trained convolutional neural network trained for DL denoising (bSSFP DL). Images were compared qualitatively based on a 5-point Likert scale (from 1 = non-diagnostic to 5 = excellent) and quantitatively by calculating the apparent signal-to-noise ratio (aSNR) and contrast-to-noise ratio (aCNR). Diagnostic confidence was assessed for the atria, ventricles, foramen ovale, valves, great vessels, aortic arch, and pulmonary veins.

Results

Fetal cardiac cine MRI was successful in 23 fetuses (92%), with two studies excluded due to extensive fetal motion. The image quality of bSSFP DL cine reconstructions was rated superior to standard bSSFP CS cine images in terms of contrast [3 (interquartile range: 2-4) vs. 5 (4-5), P < 0.001] and endocardial edge definition [3 (2-4) vs. 4 (4-5), P < 0.001], while the extent of artifacts was found to be comparable [4 (3-4.75) vs. 4 (3-4), P = 0.40]. bSSFP DL images had higher aSNR and aCNR compared with the bSSFP CS images (aSNR: 13.4 ± 6.9 vs. 8.3 ± 3.6, P < 0.001; aCNR: 26.6 ± 15.8 vs. 14.4 ± 6.8, P < 0.001). Diagnostic confidence of the bSSFP DL images was superior for the evaluation of cardiovascular structures (e.g., atria and ventricles: P = 0.003).

Conclusion

DL image denoising provides superior quality for DUS-gated fetal cardiac cine imaging of CHD compared to standard CS image reconstruction.

Rapid and motion-robust pediatric brain imaging: T2-weighted turbo-spin-echo PROPELLER acquisition with compressed sensing

BACKGROUND

In pediatric magnetic resonance imaging (MRI), reducing the rate of non-diagnostic scans due to artifacts and shortening acquisition time are crucial not only for economic reasons but also to minimize sedation or general anesthesia.

OBJECTIVE

Enabling faster and motion-robust MRI of the brain in infants and children using a novel, enhanced compressed sensing (CS) algorithm in combination with a turbo-spin-echo T2-weighted sequence utilizing the PROPELLER-technique (periodically rotated overlapping parallel lines with enhanced reconstruction; T2PROPELLER CS).

MATERIALS AND METHODS

This prospective study included 31 patients (8.0 ± 4.7 years, 15 males) undergoing a clinically indicated MRI examination of the brain on a 3-T scanner. The T2PROPELLER CS sequence was compared to a conventional, CS-accelerated Cartesian turbo-spin-echo T2-weighted sequence (T2Cartesian CS). Apparent contrast-to-noise ratio (aCNR) and signal-to-noise ratio (aSNR) were calculated. Three blinded radiologists independently rated both sequences twice qualitatively on a 5-point Likert-scale from 1-5 (non-diagnostic-excellent) for artifacts, image sharpness, basal ganglia delineation, lesion conspicuity, and overall image quality. Statistical analysis was performed using the Wilcoxon signed-rank test and paired sample t test. Intra- and interrater reliability of qualitative image assessment was evaluated by computing Krippendorff's α reliability estimates.

RESULTS

The average acquisition time of the T2PROPELLER CS (189 ± 27 s) was 31% shorter than that of the T2Cartesian CS sequence (273 ± 21 s; P < 0.001). aCNR (7.7 ± 4.6 vs. 6.2 ± 2.8; P = 0.004) and aSNR (24.8 ± 9.7 vs. 18.8 ± 5.5; P < 0.001) were higher for the T2Cartesian CS compared to the T2PROPELLER CS sequence. The T2PROPELLER CS sequence significantly reduced (motion-)artifacts (P < 0.001) and increased image sharpness (P < 0.001), basal ganglia delineation (P<0.001), lesion conspicuity (raters 1 and 2, P < 0.001; rater 3, P = 0.004), and overall image quality (P < 0.001). Metal artifacts were prominent in both sequences, though slightly more pronounced in the T2PROPELLER CS sequence.

CONCLUSION

The T2PROPELLER CS sequence enables faster and motion-robust imaging of the brain in infants and children, reducing the rate of non-diagnostic scans and potentially allowing sedation or general anesthesia to be minimized in the future.

Deep learning super-resolution reconstruction for fast and high-quality cine cardiovascular magnetic resonance

OBJECTIVES

To compare standard-resolution balanced steady-state free precession (bSSFP) cine images with cine images acquired at low resolution but reconstructed with a deep learning (DL) super-resolution algorithm.

MATERIALS AND METHODS

Cine cardiovascular magnetic resonance (CMR) datasets (short-axis and 4-chamber views) were prospectively acquired in healthy volunteers and patients at normal (cineNR: 1.89 × 1.96 mm2, reconstructed at 1.04 × 1.04 mm2) and at a low-resolution (2.98 × 3.00 mm2, reconstructed at 1.04 × 1.04 mm2). Low-resolution images were reconstructed using compressed sensing DL denoising and resolution upscaling (cineDL). Left ventricular ejection fraction (LVEF), end-diastolic volume index (LVEDVi), and strain were assessed. Apparent signal-to-noise (aSNR) and contrast-to-noise ratios (aCNR) were calculated. Subjective image quality was assessed on a 5-point Likert scale. Student's paired t-test, Wilcoxon matched-pairs signed-rank-test, and intraclass correlation coefficient (ICC) were used for statistical analysis.

RESULTS

Thirty participants were analyzed (37 ± 16 years; 20 healthy volunteers and 10 patients). Short-axis views whole-stack acquisition duration of cineDL was shorter than cineNR (57.5 ± 8.7 vs 98.7 ± 12.4 s; p < 0.0001). No differences were noted for: LVEF (59 ± 7 vs 59 ± 7%; ICC: 0.95 [95% confidence interval: 0.94, 0.99]; p = 0.17), LVEDVi (85.0 ± 13.5 vs 84.4 ± 13.7 mL/m2; ICC: 0.99 [0.98, 0.99]; p = 0.12), longitudinal strain (-19.5 ± 4.3 vs -19.8 ± 3.9%; ICC: 0.94 [0.88, 0.97]; p = 0.52), short-axis aSNR (81 ± 49 vs 69 ± 38; p = 0.32), aCNR (53 ± 31 vs 45 ± 27; p = 0.33), or subjective image quality (5.0 [IQR 4.9, 5.0] vs 5.0 [IQR 4.7, 5.0]; p = 0.99).

CONCLUSION

Deep-learning reconstruction of cine images acquired at a lower spatial resolution led to a decrease in acquisition times of 42% with shorter breath-holds without affecting volumetric results or image quality.

KEY POINTS

Question Cine CMR acquisitions are time-intensive and vulnerable to artifacts. Findings Low-resolution upscaled reconstructions using DL super-resolution decreased acquisition times by 35-42% without a significant difference in volumetric results or subjective image quality. Clinical relevance DL super-resolution reconstructions of bSSFP cine images acquired at a lower spatial resolution reduce acquisition times while preserving diagnostic accuracy, improving the clinical feasibility of cine imaging by decreasing breath hold duration.

Fast and Robust Single-Shot Cine Cardiac MRI Using Deep Learning Super-Resolution Reconstruction

OBJECTIVE

The aim of the study was to compare the diagnostic quality of deep learning (DL) reconstructed balanced steady-state free precession (bSSFP) single-shot (SSH) cine images with standard, multishot (also: segmented) bSSFP cine (standard cine) in cardiac MRI.

METHODS AND MATERIALS

This prospective study was performed in a cohort of participants with clinical indication for cardiac MRI. SSH compressed-sensing bSSFP cine and standard multishot cine were acquired with breath-holding and electrocardiogram-gating in short-axis view at 1.5 Tesla. SSH cine images were reconstructed using an industry-developed DL super-resolution algorithm (DL-SSH cine). Two readers evaluated diagnostic quality (endocardial edge definition, blood pool to myocardium contrast and artifact burden) from 1 (nondiagnostic) to 5 (excellent). Functional left ventricular (LV) parameters were assessed in both sequences. Edge rise distance, apparent signal-to-noise ratio (aSNR) and contrast-to-noise ratio were calculated. Statistical analysis for the comparison of DL-SSH cine and standard cine included the Student's t-test, Wilcoxon signed-rank test, Bland-Altman analysis, and Pearson correlation.

RESULTS

Forty-five participants (mean age: 50 years ±18; 30 men) were included. Mean total scan time was 65% lower for DL-SSH cine compared to standard cine (92 ± 8 s vs 265 ± 33 s; P < 0.0001). DL-SSH cine showed high ratings for subjective image quality (eg, contrast: 5 [interquartile range {IQR}, 5-5] vs 5 [IQR, 5-5], P = 0.01; artifacts: 4.5 [IQR, 4-5] vs 5 [IQR, 4-5], P = 0.26), with superior values for sharpness parameters (endocardial edge definition: 5 [IQR, 5-5] vs 5 [IQR, 4-5], P < 0.0001; edge rise distance: 1.9 [IQR, 1.8-2.3] vs 2.5 [IQR, 2.3-2.6], P < 0.0001) compared to standard cine. No significant differences were found in the comparison of objective metrics between DL-SSH and standard cine (eg, aSNR: 49 [IQR, 38.5-70] vs 52 [IQR, 38-66.5], P = 0.74). Strong correlation was found between DL-SSH cine and standard cine for the assessment of functional LV parameters (eg, ejection fraction: r = 0.95). Subgroup analysis of participants with arrhythmia or unreliable breath-holding (n = 14/45, 31%) showed better image quality ratings for DL-SSH cine compared to standard cine (eg, artifacts: 4 [IQR, 4-5] vs 4 [IQR, 3-5], P = 0.04).

CONCLUSIONS

DL reconstruction of SSH cine sequence in cardiac MRI enabled accelerated acquisition times and noninferior diagnostic quality compared to standard cine imaging, with even superior diagnostic quality in participants with arrhythmia or unreliable breath-holding.

Fetal cardiovascular magnetic resonance feature tracking myocardial strain analysis in congenital heart disease

BACKGROUND

Cardiovascular magnetic resonance (CMR) is an emerging imaging modality for assessing the anatomy and function of the fetal heart in congenital heart disease (CHD). This study aimed to evaluate myocardial strain using fetal CMR feature tracking (FT) in different subtypes of CHD.

METHODS

Fetal CMR FT analysis was retrospectively performed on four-chamber cine images acquired with Doppler ultrasound gating at 3T. Left ventricular (LV) global longitudinal strain (GLS), LV global radial strain (GRS), LV global longitudinal systolic strain rate, and right ventricular (RV) GLS were quantified using dedicated software optimized for fetal strain analysis. Analysis was performed in normal fetuses and different CHD subtypes (d-transposition of the great arteries [dTGA], hypoplastic left heart syndrome [HLHS], coarctation of the aorta [CoA], tetralogy of Fallot [TOF], RV-dominant atrioventricular septal defect [AVSD], and critical pulmonary stenosis or atresia [PS/PA]). Analysis of variance with Tukey post-hoc test was used for group comparisons.

RESULTS

A total of 60 fetuses were analyzed (8/60 (13%) without CHD, 52/60 (87%) with CHD). Myocardial strain was successfully assessed in 113/120 ventricles (94%). Compared to controls, LV GLS was significantly reduced in fetuses with HLHS (-18.6±2.7% vs -6.2±5.6%; p<0.001) and RV-dominant AVSD (-18.6±2.7% vs -7.7±5.0%; p = 0.003) and higher in fetuses with CoA (-18.6±2.7% vs -25.0±4.3%; p = 0.038). LV GRS was significantly reduced in fetuses with HLHS (25.7±7.5% vs 11.4±9.7%; p = 0.024). Compared to controls, RV GRS was significantly reduced in fetuses with PS/PA (-16.1±2.8% vs -8.3±4.2%; p = 0.007). Across all strain parameters, no significant differences were present between controls and fetuses diagnosed with dTGA and TOF.

CONCLUSION

Fetal myocardial strain assessment with CMR FT in CHD is feasible. Distinct differences are present between various types of CHD, suggesting potential implications for clinical decision-making and prognostication in fetal CHD.

Compressed SENSE accelerated 3D single-breath-hold late gadolinium enhancement cardiovascular magnetic resonance with isotropic resolution: clinical evaluation

Aim

The purpose of this study was to investigate the clinical application of Compressed SENSE accelerated single-breath-hold LGE with 3D isotropic resolution compared to conventional LGE imaging acquired in multiple breath-holds.

Material & Methods

This was a retrospective, single-center study including 105 examinations of 101 patients (48.2 ± 16.8 years, 47 females). All patients underwent conventional breath-hold and 3D single-breath-hold (0.96 × 0.96 × 1.1 mm3 reconstructed voxel size, Compressed SENSE factor 6.5) LGE sequences at 1.5 T in clinical routine for the evaluation of ischemic or non-ischemic cardiomyopathies. Two radiologists independently evaluated the left ventricle (LV) for the presence of hyperenhancing lesions in each sequence, including localization and transmural extent, while assessing their scar edge sharpness (SES). Confidence of LGE assessment, image quality (IQ), and artifacts were also rated. The impact of LV ejection fraction (LVEF), heart rate, body mass index (BMI), and gender as possible confounders on IQ, artifacts, and confidence of LGE assessment was evaluated employing ordinal logistic regression analysis.

Results

Using 3D single-breath-hold LGE readers detected more hyperenhancing lesions compared to conventional breath-hold LGE (n = 246 vs. n = 216 of 1,785 analyzed segments, 13.8% vs. 12.1%; p < 0.0001), pronounced at subendocardial, midmyocardial, and subepicardial localizations and for 1%-50% of transmural extent. SES was rated superior in 3D single-breath-hold LGE (4.1 ± 0.8 vs. 3.3 ± 0.8; p < 0.001). 3D single-breath-hold LGE yielded more artifacts (3.8 ± 1.0 vs. 4.0 ± 3.8; p = 0.002) whereas IQ (4.1 ± 1.0 vs. 4.2 ± 0.9; p = 0.122) and confidence of LGE assessment (4.3 ± 0.9 vs. 4.3 ± 0.8; p = 0.374) were comparable between both techniques. Female gender negatively influenced artifacts in 3D single-breath-hold LGE (p = 0.0028) while increased heart rate led to decreased IQ in conventional breath-hold LGE (p = 0.0029).

Conclusions

In clinical routine, Compressed SENSE accelerated 3D single-breath-hold LGE yields image quality and confidence of LGE assessment comparable to conventional breath-hold LGE while providing improved delineation of smaller LGE lesions with superior scar edge sharpness. Given the fast acquisition of 3D single-breath-hold LGE, the technique holds potential to drastically reduce the examination time of CMR.

Accelerated High-resolution T1- and T2-weighted Breast MRI with Deep Learning Super-resolution Reconstruction

RATIONALE AND OBJECTIVES

To assess the performance of an industry-developed deep learning (DL) algorithm to reconstruct low-resolution Cartesian T1-weighted dynamic contrast-enhanced (T1w) and T2-weighted turbo-spin-echo (T2w) sequences and compare them to standard sequences.

MATERIALS AND METHODS

Female patients with indications for breast MRI were included in this prospective study. The study protocol at 1.5 Tesla MRI included T1w and T2w. Both sequences were acquired in standard resolution (T1S and T2S) and in low-resolution with following DL reconstructions (T1DL and T2DL). For DL reconstruction, two convolutional networks were used: (1) Adaptive-CS-Net for denoising with compressed sensing, and (2) Precise-Image-Net for resolution upscaling of previously downscaled images. Overall image quality was assessed using 5-point-Likert scale (from 1=non-diagnostic to 5=excellent). Apparent signal-to-noise (aSNR) and contrast-to-noise (aCNR) ratios were calculated. Breast Imaging Reporting and Data System (BI-RADS) agreement between different sequence types was assessed.

RESULTS

A total of 47 patients were included (mean age, 58±11 years). Acquisition time for T1DL and T2DL were reduced by 51% (44 vs. 90 s per dynamic phase) and 46% (102 vs. 192 s), respectively. T1DL and T2DL showed higher overall image quality (e.g., 4 [IQR, 4-4] for T1S vs. 5 [IQR, 5-5] for T1DL, P<0.001). Both, T1DL and T2DL revealed higher aSNR and aCNR than T1S and T2S (e.g., aSNR: 32.35±10.23 for T2S vs. 27.88±6.86 for T2DL, P=0.014). Cohen k agreement by BI-RADS assessment was excellent (0.962, P<0.001).

CONCLUSION

DL for denoising and resolution upscaling reduces acquisition time and improves image quality for T1w and T2w breast MRI.

Feasibility and Implementation of a 4D Free-Breathing Variable Density Stack-of-Stars Functional Magnetic Resonance Urography in Young Children Without Sedation

BACKGROUND

Functional magnetic resonance urography (MRU) is well established in the diagnostic workup of urinary tract anomalies in children, providing comprehensive morphological and functional information. However, dynamic contrast-enhanced images acquired in the standard Cartesian k-space manner are prone to motion artifacts. A newly introduced 4D high spatiotemporal resolution dynamic contrast-enhanced magnetic resonance imaging based on variable density elliptical centric radial stack-of-stars sharing technique has shown improved image quality regarding motions under free breathing.

OBJECTIVE

The aims of this study were to implement this 4D free-breathing sequence for functional MRU and to compare its image quality and analyzability with standard breath-hold Cartesian MRU.

MATERIALS AND METHODS

We retrospectively evaluated all functional 4D MRU performed without general anesthesia between September 2021 and December 2022 and compared them with matched pairs (age, affected kidney, diagnosis) of standard Cartesian MRU between 2016 and 2022. Image analysis was performed by 2 radiologists independently regarding the following criteria using a 4-point Likert scale, with 4 being the best: overall image quality, diagnostic confidence, respiratory motion artifacts, as well as sharpness and contrast of aorta, kidneys, and ureters. We also measured vertical kidney motion due to respiratory motion and compared the variance for each kidney using F test. Finally, both radiologists calculated the volume, split renal volume (vDRF), split renal Patlak function (pDRF), and split renal function considering the volume and Patlak function (vpDRF) for each kidney. Values were compared using Bland-Altman plots and F test.

RESULTS

Forty children (20 for 4D free-breathing and standard breath-hold, respectively) were enrolled. Ten children of each group were examined using feed-and-sleep technique (median age: 4D, 3.3 months; standard, 4.2 months), 10 were awake (median age: 4D, 8.9 years; standard, 8.6 years). Overall image quality, diagnostic confidence, respiratory motion artifacts, as well as sharpness and contrast of the aorta, kidneys, and ureters were rated significantly better for 4D free-breathing compared with standard breath-hold by both readers ( P ranging from <0.0001 to 0.005). Vertical kidney motion was significantly reduced in 4D free-breathing for the right and the left kidney (both P < 0.001). There was a significantly smaller variance concerning the differences between the 2 readers for vpDRF in 4D MRU ( P = 0.0003). In contrast, no significant difference could be demonstrated for volume ( P = 0.05), vDRF ( P = 0.93), and pDRF ( P = 0.14).

CONCLUSIONS

We demonstrated the feasibility of applying a 4D free-breathing variable density stack-of-stars imaging for functional MRU in young pediatric patients with improved image quality, fewer motion artifacts, and improved functional analyzability.

Accelerated diffusion-weighted imaging of the prostate employing echo planar imaging with compressed SENSE based reconstruction

Aim was to evaluate accelerated diffusion-weighted imaging (DWI) of the prostate using echo planar imaging with compressed SENSE based reconstruction (EPICS) and assess its performance in comparison to conventional DWI with parallel imaging. In this single-center, prospective study, 35 men with clinically suspected prostate cancer underwent prostate MRI at 3T. In each patient, two different DWI sequences, one with 3 b-values (b = 100, 400, 800s/mm²) for ADC-calculation and one with b = 1500s/mm², were acquired with conventional SENSE and with EPICS. Quantitative evaluation was done by regions-of-interest (ROIs) analysis of prostate lesions and normal appearing peripheral zones (PZ). Apparent contrast-to-noise (aCNR) and apparent signal-to-noise ratios (aSNR) were calculated. Mean ADC and coefficient of variation (CV) of ADC were compared. For qualitative assessment, artifacts, lesion conspicuity, and overall image quality were rated using a 5-point-Likert-scale (1: nondiagnostic to 5: excellent). Additionally, the Prostate Imaging Reporting and Data System (PIRADS 2.1) was rated for DWI. The average total scan time reduction with EPICS was 43%. Quantitative analysis showed no significant differences between conventional SENSE and EPICS, neither for aSNRLesion (e.g. b1500conv: 24.37 ± 10.28 vs. b1500EPICS: 24.08 ± 12.2; p = 0.98) and aCNRLesion (e.g. b1500conv:9.53 ± 7.22 vs. b1500EPICS:8.88 ± 6.16; p = 0.55) nor for aSNRPZ (e.g. b1500conv:15.18 ± 6.48 vs. b1500EPICS: 15 ± 7.4; p = 0.94). Rating of artifacts, lesion conspicuity, overall image quality and PIRADS-scores yielded comparable results for the two techniques (e.g. lesion conspicuity for ADCconv: 4(2-5) vs. ADCEPICS 4(2-5); p = 0.99 and for b1500conv: 4(2-5) vs. b1500EPICS 4(2-5); p = 0.25). Overall, accelerated DWI of the prostate using EPICS significantly reduced acquisition time without compromising image quality compared to conventional DWI.