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 (T2_C) and non-Cartesian standard-resolution T2-weighted TSE sequence (T2_NC) between August and November 2022. Additionally, a low-resolution Cartesian DL-reconstructed T2-weighted TSE sequence (T2_DL) 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 T2_DL was 36% and 29% lower compared with that of T2_C and T2_NC (mean duration, 164 seconds ± 20 vs 257 seconds ± 32 and 230 seconds ± 28; P < .001 for both). T2_DL showed improved image sharpness compared with standard sequences using both qualitative (median score, 5 [IQR, 4-5] vs 4 [IQR, 3-4] for T2_C and 4 [IQR, 3-4] for T2_NC; P < .001 for both) and quantitative (mean edge rise distance, 0.75 mm ± 0.39 vs 1.15 mm ± 0.68 for T2_C and 0.98 mm ± 0.65 for T2_NC; P < .001 and P = .01) methods. PI-RADS score agreement between T2_NC and T2_DL 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.

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. 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. 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. 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.

BACKGROUND: Fetal cardiovascular magnetic resonance is an emerging tool for prenatal congenital heart disease assessment, but long acquisition times and fetal movements limit its clinical use. This study evaluates the clinical utility of deep learning super-resolution reconstructions for rapidly acquired, low-resolution fetal cardiovascular magnetic resonance. METHODS: This prospective study included participants with fetal congenital heart disease undergoing fetal cardiovascular magnetic resonance in the third trimester of pregnancy, with axial cine images acquired at normal resolution and low resolution. Low-resolution cine data was subsequently reconstructed using a deep learning super-resolution framework (cine _DL ). Acquisition times, apparent signal-to-noise ratio, contrast-to-noise ratio, and edge rise distance were assessed. Volumetry and functional analysis were performed. Qualitative image scores were rated on a 5-point Likert scale. Cardiovascular structures and pathological findings visible in cine _DL images only were assessed. Statistical analysis included the Student paired t test and the Wilcoxon test. RESULTS: A total of 42 participants were included (median gestational age, 35.9 weeks [interquartile range (IQR), 35.1–36.4]). Cine _DL acquisition was faster than cine images acquired at normal resolution (134±9.6 s versus 252±8.8 s; P <0.001). Quantitative image quality metrics and image quality scores for cine _DL were higher or comparable with those of cine images acquired at normal-resolution (eg, fetal motion, 4.0 [IQR, 4.0–5.0] versus 4.0 [IQR, 3.0–4.0]; P <0.001). Nonpatient-related artifacts (eg, backfolding) were more pronounced in cine _DL compared with cine images acquired at normal-resolution images (4.0 [IQR, 4.0–5.0] versus 5.0 [IQR, 3.0–4.0]; P <0.001). Volumetry and functional results were comparable. Cine _DL revealed additional structures in 10 of 42 fetuses (24%) and additional pathologies in 5 of 42 fetuses (12%), including partial anomalous pulmonary venous connection. CONCLUSIONS: Deep learning super-resolution reconstructions of low-resolution acquisitions shorten acquisition times and achieve diagnostic quality comparable with standard images, while being less sensitive to fetal bulk movements, leading to additional diagnostic findings. Therefore, deep learning super-resolution may improve the clinical utility of fetal cardiovascular magnetic resonance for accurate prenatal assessment of congenital heart disease.

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; T2_{PROPELLER 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 T2_{PROPELLER CS} sequence was compared to a conventional, CS-accelerated Cartesian turbo-spin-echo T2-weighted sequence (T2_{Cartesian 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 $$\alpha$$ α reliability estimates. Results: The average acquisition time of the T2_{PROPELLER CS} (189 ± 27 s) was 31% shorter than that of the T2_{Cartesian 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 T2_{Cartesian CS} compared to the T2_{PROPELLER CS} sequence. The T2_{PROPELLER 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 T2_{PROPELLER CS} sequence. Conclusion: The T2_{PROPELLER 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. Graphical

Objectives: The purpose of this study was to assess whether a 3-min 2D knee protocol can meet the needs for clinical application if using a SuperResolution reconstruction approach. Methods: In this prospective study, a total of 20 volunteers underwent imaging of the knee using a 3T MRI scanner (Philips Ingenia Elition X 3.0T, Philips). The imaging protocol, consisting of a fat-saturated 2D proton density sequence in coronal, sagittal, and transverse orientations, as well as a sagittal T1-weighted sequence, was acquired with standard and ultra-low resolution. The standard sequences were reconstructed using an AI-assisted Compressed SENSE method (SmartSpeed). The ultra-low-resolution sequences have been reconstructed using a vendor-provided prototype. Four experienced readers (two radiologists and two orthopedic surgeons) evaluated the sequences for image quality, anatomical structures, and incidental pathologies. The consensus evaluation of two different experienced radiologists specialized in musculoskeletal imaging served as the gold standard. Results: The acquisition time for the entire protocol was 11:01 min for standard resolution and 03:36 min for ultra-low resolution. In the overall assessment, CS-SuperRes-reconstructed sequences showed slightly improved accuracy and increased specificity compared to the standard CS-AI method (0.87 vs. 0.86 and 0.9 vs. 0.87, respectively), while the standard method exhibited a higher sensitivity (0.73 vs. 0.57). Overall, 24 out of 40 pathologies were detected in the ultra-low-resolution images compared to 26 in the standard images. Conclusions: The CS-SuperRes method enables a 2D knee protocol to be completed in 3 min, with improved accuracy compared to the clinical standard.

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. Strengths of this study: Compressed sensing allows accelerated imaging with reduction of motion artifacts without alteration of quantitative measurements Robust results in fat and iron quantification in a heterogeneous patient cohort Limitations of this study: No histopathological validation of the MR findings was performed The study was not performed at different field strengths