Deep learning-based assessment of CT markers of sarcopenia and myosteatosis for outcome assessment in patients with advanced pancreatic cancer after high-intensity focused ultrasound treatment.

OBJECTIVES: To evaluate the prognostic value of CT-based markers of sarcopenia and myosteatosis in comparison to the Eastern Cooperative Oncology Group (ECOG) score for survival of patients with advanced pancreatic cancer treated with high-intensity focused ultrasound (HIFU). MATERIALS AND METHODS: For 142 retrospective patients, the skeletal muscle index (SMI), skeletal muscle radiodensity (SMRD), fatty muscle fraction (FMF), and intermuscular fat fraction (IMFF) were determined on superior mesenteric artery level in pre-interventional CT. Each marker was tested for associations with sex, age, body mass index (BMI), and ECOG. The prognostic value of the markers was examined in Kaplan-Meier analyses with the log-rank test and in uni- and multivariable Cox proportional hazards (CPH) models. RESULTS: The following significant associations were observed: Male patients had higher BMI and SMI. Patients with lower ECOG had lower BMI and SMI. Patients with BMI lower than 21.8 kg/m2 (median) also showed lower SMI and IMFF. Patients younger than 63.3 years (median) were found to have higher SMRD, lower FMF, and lower IMFF. In the Kaplan-Meier analysis, significantly lower survival times were observed in patients with higher ECOG or lower SMI. Increased patient risk was observed for higher ECOG, lower BMI, and lower SMI in univariable CPH analyses for 1-, 2-, and 3-year survival. Multivariable CPH analysis for 1-year survival revealed increased patient risk for higher ECOG, lower SMI, lower IMFF, and higher FMF. In multivariable analysis for 2- and 3-year survival, only ECOG and FMF remained significant. CONCLUSION: CT-based markers of sarcopenia and myosteatosis show a prognostic value for assessment of survival in advanced pancreatic cancer patients undergoing HIFU therapy. CLINICAL RELEVANCE STATEMENT: The results indicate a greater role of myosteatosis for additional risk assessment beyond clinical scores, as only FMF was associated with long-term survival in multivariable CPH analyses along ECOG and also showed independence to ECOG in group analysis. KEY POINTS: • This study investigates the prognostic value of CT-based markers of sarcopenia and myosteatosis for patients with pancreatic cancer treated with high-intensity focused ultrasound. • Markers for sarcopenia and myosteatosis showed a prognostic value besides clinical assessment of the physical status by the Eastern Cooperative Oncology Group score. In contrast to muscle size measurements, the myosteatosis marker fatty muscle fraction demonstrated independence to the clinical score. • The results indicate that myosteatosis might play a greater role for additional patient risk assessments beyond clinical assessments of physical status.

Generative Pre-trained Transformer 4 makes cardiovascular magnetic resonance reports easy to understand.

BACKGROUND: Patients are increasingly using Generative Pre-trained Transformer 4 (GPT-4) to better understand their own radiology findings. PURPOSE: To evaluate the performance of GPT-4 in transforming cardiovascular magnetic resonance (CMR) reports into text that is comprehensible to medical laypersons. METHODS: ChatGPT with GPT-4 architecture was used to generate three different explained versions of 20 various CMR reports (n = 60) using the same prompt: "Explain the radiology report in a language understandable to a medical layperson". Two cardiovascular radiologists evaluated understandability, factual correctness, completeness of relevant findings, and lack of potential harm, while 13 medical laypersons evaluated the understandability of the original and the GPT-4 reports on a Likert scale (1 "strongly disagree", 5 "strongly agree"). Readability was measured using the Automated Readability Index (ARI). Linear mixed-effects models (values given as median [interquartile range]) and intraclass correlation coefficient (ICC) were used for statistical analysis. RESULTS: GPT-4 reports were generated on average in 52 s ± 13. GPT-4 reports achieved a lower ARI score (10 [9-12] vs 5 [4-6]; p < 0.001) and were subjectively easier to understand for laypersons than original reports (1 [1] vs 4 [4,5]; p < 0.001). Eighteen out of 20 (90%) standard CMR reports and 2/60 (3%) GPT-generated reports had an ARI score corresponding to the 8th grade level or higher. Radiologists' ratings of the GPT-4 reports reached high levels for correctness (5 [4, 5]), completeness (5 [5]), and lack of potential harm (5 [5]); with "strong agreement" for factual correctness in 94% (113/120) and completeness of relevant findings in 81% (97/120) of reports. Test-retest agreement for layperson understandability ratings between the three simplified reports generated from the same original report was substantial (ICC: 0.62; p < 0.001). Interrater agreement between radiologists was almost perfect for lack of potential harm (ICC: 0.93, p < 0.001) and moderate to substantial for completeness (ICC: 0.76, p < 0.001) and factual correctness (ICC: 0.55, p < 0.001). CONCLUSION: GPT-4 can reliably transform complex CMR reports into more understandable, layperson-friendly language while largely maintaining factual correctness and completeness, and can thus help convey patient-relevant radiology information in an easy-to-understand manner.

SCMR expert consensus statement for cardiovascular magnetic resonance of patients with a cardiac implantable electronic device.

Cardiovascular magnetic resonance (CMR) is a proven imaging modality for informing diagnosis and prognosis, guiding therapeutic decisions, and risk stratifying surgical intervention. Patients with a cardiac implantable electronic device (CIED) would be expected to derive particular benefit from CMR given high prevalence of cardiomyopathy and arrhythmia. While several guidelines have been published over the last 16 years, it is important to recognize that both the CIED and CMR technologies, as well as our knowledge in MR safety, have evolved rapidly during that period. Given increasing utilization of CIED over the past decades, there is an unmet need to establish a consensus statement that integrates latest evidence concerning MR safety and CIED and CMR technologies. While experienced centers currently perform CMR in CIED patients, broad availability of CMR in this population is lacking, partially due to limited availability of resources for programming devices and appropriate monitoring, but also related to knowledge gaps regarding the risk-benefit ratio of CMR in this growing population. To address the knowledge gaps, this SCMR Expert Consensus Statement integrates consensus guidelines, primary data, and opinions from experts across disparate fields towards the shared goal of informing evidenced-based decision-making regarding the risk-benefit ratio of CMR for patients with CIEDs.

Elucidating the need for prostate cancer risk calculators in conjunction with mpMRI in initial risk assessment before prostate biopsy at a tertiary prostate cancer center.

OBJECTIVE: Utilizing personalized risk assessment for clinically significant prostate cancer (csPCa) incorporating multiparametric magnetic resonance imaging (mpMRI) reduces biopsies and overdiagnosis. We validated both multi- and univariate risk models in biopsy-naïve men, with and without the inclusion of mpMRI data for csPCa detection. METHODS: N = 565 men underwent mpMRI-targeted prostate biopsy, and the diagnostic performance of risk calculators (RCs), mpMRI alone, and clinical measures were compared using receiver operating characteristic curve (ROC) analysis and decision curve analysis (DCA). Subgroups were stratified based on mpMRI findings and quality. RESULTS: csPCa was detected in 56.3%. PI-RADS score achieved the highest area under the curve (AUC) when comparing univariate risk models (AUC 0.82, p < 0.001). Multivariate RCs showed only marginal improvement in csPCa detection compared to PI-RADS score alone, with just one of four RCs showing significant superiority. In mpMRI-negative cases, the non-MRI-based RC performed best (AUC 0.80, p = 0.016), with the potential to spare biopsies for 23%. PSA-density and multivariate RCs demonstrated comparable performance for PI-RADS 3 constellation (AUC 0.65 vs. 0.60-0.65, p > 0.5; saved biopsies 16%). In men with suspicious mpMRI, both mpMRI-based RCs and the PI-RADS score predicted csPCa excellently (AUC 0.82-0.79 vs. 0.80, p > 0.05), highlighting superior performance compared to non-MRI-based models (all p < 0.002). Quality-assured imaging consistently improved csPCa risk stratification across all subgroups. CONCLUSION: In tertiary centers serving a high-risk population, high-quality mpMRI provides a simple yet effective way to assess the risk of csPCa. Using multivariate RCs reduces multiple biopsies, especially in mpMRI-negative and PI-RADS 3 constellation.

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.

Current role of systematic biopsy in diagnosis of clinically significant prostate cancer in primary combined MRI-targeted biopsy: a high-volume single-center study.

PURPOSE: Additive systematic biopsy (SB) contributes to prostate cancer (PCA) detection in MRI-targeted biopsy (TB). However, the reasons for this are not yet clear. We compared the performance of TB, SB and the combined approach (CB) in biopsy-naive men to determine the added value of SB for tumor grading and spatial tumor distribution. METHODS: Two hundred and fifty-nine men with PI-RADS 3-5 graded lesions who underwent CB were enrolled. Data were prospectively collected, and cancer detection rates (CDR) were compared at patient and lesion level. Gleason grade up- and down-grading from biopsy to prostatectomy specimens (n = 56; 21.6%) were determined. Clinically significant cancer (csPCA) was defined as Gleason grade ≥ 2. RESULTS: CDR by CB based on PI-RADS categories 3, 4 and 5 for PCA were 24%, 72% and 98% and 17%, 64% and 96% for csPCA. CB detected more PCA and csPCA than TB (p < 0.001). However, TB showed higher efficiency, defined as CDR per biopsy core, for PCA and csPCA in PI-RADS 4-5 rated patients (p < 0.001). Concordance between biopsy and prostatectomy grading was highest in CB with misdiagnosis of csPCA in 25% of men. TB missed cancer attributed to the index lesion in 10.2% and underestimated csPCA in 7%. In these cases, 76% of csPCA were detected and 85% were upgraded to csPCA by SB in adjacent sectors. CONCLUSION: SB cannot be safely abundant without increased diagnostic uncertainty. When TB missed csPCA, SB detected it close to the MRI-target lesion. Therefore, perifocal biopsies could potentially replace 12-core SB with increased efficiency in taking manageable risks.

Deep learning for standardized, MRI-based quantification of subcutaneous and subfascial tissue volume for patients with lipedema and lymphedema.

OBJECTIVES: To contribute to a more in-depth assessment of shape, volume, and asymmetry of the lower extremities in patients with lipedema or lymphedema utilizing volume information from MR imaging. METHODS: A deep learning (DL) pipeline was developed including (i) localization of anatomical landmarks (femoral heads, symphysis, knees, ankles) and (ii) quality-assured tissue segmentation to enable standardized quantification of subcutaneous (SCT) and subfascial tissue (SFT) volumes. The retrospectively derived dataset for method development consisted of 45 patients (42 female, 44.2 ± 14.8 years) who underwent clinical 3D DIXON MR-lymphangiography examinations of the lower extremities. Five-fold cross-validated training was performed on 16,573 axial slices from 40 patients and testing on 2187 axial slices from 5 patients. For landmark detection, two EfficientNet-B1 convolutional neural networks (CNNs) were applied in an ensemble. One determines the relative foot-head position of each axial slice with respect to the landmarks by regression, the other identifies all landmarks in coronal reconstructed slices using keypoint detection. After landmark detection, segmentation of SCT and SFT was performed on axial slices employing a U-Net architecture with EfficientNet-B1 as encoder. Finally, the determined landmarks were used for standardized analysis and visualization of tissue volume, distribution, and symmetry, independent of leg length, slice thickness, and patient position. RESULTS: Excellent test results were observed for landmark detection (z-deviation = 4.5 ± 3.1 mm) and segmentation (Dice score: SCT = 0.989 ± 0.004, SFT = 0.994 ± 0.002). CONCLUSIONS: The proposed DL pipeline allows for standardized analysis of tissue volume and distribution and may assist in diagnosis of lipedema and lymphedema or monitoring of conservative and surgical treatments. KEY POINTS: • Efficient use of volume information that MRI inherently provides can be extracted automatically by deep learning and enables in-depth assessment of tissue volumes in lipedema and lymphedema. • The deep learning pipeline consisting of body part regression, keypoint detection, and quality-assured tissue segmentation provides detailed information about the volume, distribution, and asymmetry of lower extremity tissues, independent of leg length, slice thickness, and patient position.

MRI proton density fat fraction for estimation of tumor grade in steatotic hepatocellular carcinoma.

OBJECTIVES: Image-based detection of intralesional fat in focal liver lesions has been established in diagnostic guidelines as a feature indicative of hepatocellular carcinoma (HCC) and associated with a favorable prognosis. Given recent advances in MRI-based fat quantification techniques, we investigated a possible relationship between intralesional fat content and histologic tumor grade in steatotic HCCs. METHODS: Patients with histopathologically confirmed HCC and prior MRI with proton density fat fraction (PDFF) mapping were retrospectively identified. Intralesional fat of HCCs was assessed using an ROI-based analysis and the median fat fraction of steatotic HCCs was compared between tumor grades G1-3 with non-parametric testing. ROC analysis was performed in case of statistically significant differences (p < 0.05). Subgroup analyses were conducted for patients with/without liver steatosis and with/without liver cirrhosis. RESULTS: A total of 57 patients with steatotic HCCs (62 lesions) were eligible for analysis. The median fat fraction was significantly higher for G1 lesions (median [interquartile range], 7.9% [6.0─10.7%]) than for G2 (4.4% [3.2─6.6%]; p = .001) and G3 lesions (4.7% [2.8─7.8%]; p = .036). PDFF was a good discriminator between G1 and G2/3 lesions (AUC .81; cut-off 5.8%, sensitivity 83%, specificity 68%) with comparable results in patients with liver cirrhosis. In patients with liver steatosis, intralesional fat content was higher than in the overall sample, with PDFF performing better in distinguishing between G1 and G2/3 lesions (AUC .92; cut-off 8.8%, sensitivity 83%, specificity 91%). CONCLUSIONS: Quantification of intralesional fat using MRI PDFF mapping allows distinction between well- and less-differentiated steatotic HCCs. CLINICAL RELEVANCE: PDFF mapping may help optimize precision medicine as a tool for tumor grade assessment in steatotic HCCs. Further investigation of intratumoral fat content as a potential prognostic indicator of treatment response is encouraged. KEY POINTS: • MRI proton density fat fraction mapping enables distinction between well- (G1) and less- (G2 and G3) differentiated steatotic hepatocellular carcinomas. • In a retrospective single-center study with 62 histologically proven steatotic hepatocellular carcinomas, G1 tumors showed a higher intralesional fat content than G2 and G3 tumors (7.9% vs. 4.4% and 4.7%; p = .004). • In liver steatosis, MRI proton density fat fraction mapping was an even better discriminator between G1 and G2/G3 steatotic hepatocellular carcinomas.

A novel and simple cardiac magnetic resonance score (PE2RT) predicts outcome in takotsubo syndrome.

OBJECTIVES: To find simple imaging-based features on cardiac magnetic resonance (CMR) that are associated with major adverse cardiovascular events (MACE) in takotsubo syndrome (TTS). METHODS: Patients with TTS referred for CMR between 2007 and 2021 were retrospectively evaluated. Besides standard CMR analysis, commonly known complications of TTS based on expert knowledge were assessed and summarised via a newly developed PE2RT score (one point each for pleural effusion, pericardial effusion, right ventricular involvement, and ventricular thrombus). Clinical follow-up data was reviewed up to three years after discharge. The relationship between PE2RT features and the occurrence of MACE (cardiovascular death or new hospitalisation due to acute myocardial injury, arrhythmia, or chronic heart failure) was examined using Cox regression analysis and Kaplan-Meier estimator. RESULTS: Seventy-nine patients (mean age, 68 ± 14 years; 72 women) with TTS were included. CMR was performed in a median of 4 days (IQR, 2-6) after symptom onset. Over a median follow-up of 13.3 months (IQR, 0.4-36.0), MACE occurred in 14/79 (18%) patients: re-hospitalisation due to acute symptoms (9/79, 11%) or chronic heart failure symptoms (4/79, 5%), and cardiac death (1/79, 1%). Patients with MACE had a higher PE2RT score (median [IQR], 2 [2-3] vs 1 [0-1]; p < 0.001). PE2RT score was associated with MACE on Cox regression analysis (hazard ratio per PE2RT feature, 2.44; 95%CI: 1.62-3.68; p < 0.001). Two or more PE2RT complications were strongly associated with the occurrence of MACE (log-rank p < 0.001). CONCLUSIONS: The introduced PE2RT complication score might enable an easy-to-assess outcome evaluation of TTS patients by CMR. KEY POINTS: • Complications like pericardial effusion, pleural effusion, right ventricular involvement, and ventricular thrombus (summarised as PE2RT features) are relatively common in takotsubo syndrome. • The proposed PE2RT score (one point per complication) was associated with the occurrence of major adverse cardiac events on follow-up. • Complications easily detected by cardiac magnetic resonance imaging can help clinicians derive long-term prognostic information on patients with takotsubo syndrome.

Computed tomography derived cervical fat-free muscle fraction as an imaging-based outcome marker in patients with acute ischemic stroke: a pilot study.

BACKGROUND: Outcome assessment in stroke patients is essential for evidence-based stroke care planning. Computed tomography (CT) is the mainstay of diagnosis in acute stroke. This study aimed to investigate whether CT-derived cervical fat-free muscle fraction (FFMF) as a biomarker of muscle quality is associated with outcome parameters after acute ischemic stroke. METHODS: In this retrospective study, 66 patients (mean age: 76 ± 13 years, 30 female) with acute ischemic stroke in the anterior circulation who underwent CT, including CT-angiography, and endovascular mechanical thrombectomy of the middle cerebral artery between August 2016 and January 2020 were identified. Based on densitometric thresholds, cervical paraspinal muscles covered on CT-angiography were separated into areas of fatty and lean muscle and FFMF was calculated. The study cohort was binarized based on median FFMF (cutoff value: < 71.6%) to compare clinical variables and outcome data between two groups. Unpaired t test and Mann-Whitney U test were used for statistical analysis. RESULTS: National Institute of Health Stroke Scale (NIHSS) (12.2 ± 4.4 vs. 13.6 ± 4.5, P = 0.297) and modified Rankin scale (mRS) (4.3 ± 0.9 vs. 4.4 ± 0.9, P = 0.475) at admission, and pre-stroke mRS (1 ± 1.3 vs. 0.9 ± 1.4, P = 0.489) were similar between groups with high and low FFMF. NIHSS and mRS at discharge were significantly better in patients with high FFMF compared to patients with low FFMF (NIHSS: 4.5 ± 4.4 vs. 9.5 ± 6.7; P = 0.004 and mRS: 2.9 ± 2.1 vs.3.9 ± 1.8; P = 0.049). 90-day mRS was significantly better in patients with high FFMF compared to patients with low FFMF (3.3 ± 2.2 vs. 4.3 ± 1.9, P = 0.045). CONCLUSION: Cervical FFMF obtained from routine clinical CT might be a new imaging-based muscle quality biomarker for outcome prediction in stroke patients.

Association between single-slice and whole heart measurements of epicardial and pericardial fat in cardiac MRI.

BACKGROUND: Epicardial (ECF) and pericardial fat (PCF) are important prognostic markers for various cardiac diseases. However, volumetry of the fat compartments is time-consuming. PURPOSE: To investigate whether total volume of ECF and PCF can be estimated by axial single-slice measurements and in a four-chamber view. MATERIAL AND METHODS: A total of 113 individuals (79 patients and 34 healthy) were included in this retrospective magnetic resonance imaging (MRI) study. The total volume of ECF and PCF was determined using a 3D-Dixon sequence. Additionally, the area of ECF and PCF was obtained in single axial layers at five anatomical landmarks (left coronary artery, right coronary artery, right pulmonary artery, mitral valve, coronary sinus) of the Dixon sequence and in a four-chamber view of a standard cine sequence. Pearson's correlation coefficient was calculated between the total volume and each single-slice measurement. RESULTS: Axial single-slice measurements of ECF and PCF correlated strongly with the total fat volumes at all landmarks (ECF: r = 0.85-0.94, P < 0.001; PCF: r = 0.89-0.94, P < 0.001). The best correlation was found at the level of the left coronary artery for ECF and PCF (r = 0.94, P < 0.001). Correlation between single-slice measurement in the four-chamber view and the total ECF and PCF volume was lower (r = 0.75 and r = 0.8, respectively, P < 0.001). CONCLUSION: Single-slice measurements allow an estimation of ECF and PCF volume. This time-efficient analysis allows studies of larger patient cohorts and the opportunistic determination of ECF/PCF from routine examinations.

Percutaneous transhepatic biliary drainage: a retrospective single-center study of 372 patients.

BACKGROUND: Complication rates in percutaneous transhepatic biliary drainage (PTBD) are non-uniform and vary considerably. In addition, the impact of peri-procedural risk factors is under-investigated. PURPOSE: To compare success and complication rates of PTBD in patients with and without accompanying technical risk factors. MATERIAL AND METHODS: A single-center retrospective study was conducted from January 2004 to December 2016. Patients receiving PTBD due to biliary obstruction or biliary leakage were included. Technical risk factors (non-distended bile ducts, ascites, obesity, anasarca, non-compliance) were assessed. Complications were classified according to the Society of Interventional Radiology. RESULTS: In total, 372 patients were included (57.3% men, 42.7% women; mean age = 66 years). Overall, 466 PTBDs were performed. Of the patients, 70.1% presented with malignancy and biliary obstruction; 26.8% had benign biliary obstruction; 3.1% had biliary leakage. Technical risk factors were reported in 57 (15.3%) patients. Overall technical success of initial PTBD was 98.7%, primary technical success was 97.9%. In patients with non-dilatated bile ducts, primary technical success was 68.2%. Overall complication rate was 15.0% (8.1% major complications, 6.9% minor complications). Neither major nor minor complications were more frequent in patients with technical risk factors (P > 0.05). In left-sided PTBD, hemorrhage was more frequent (P = 0.015). Patients with malignancy were significantly more affected by drainage-related complications (P = 0.004; odds ratio = 2.03). The mortality rate was 0.5% (n = 2). CONCLUSION: PTBD is a safe and effective method for the treatment of biliary obstruction and biliary leaks. Complication rates are low, even in procedures with risk factors.

Prospective analysis of pain expectancy and experience during MR-fusion prostate biopsy: does reality match patients' expectancy?

PURPOSE: Multiparametric magnetic resonance imaging fusion targeted prostate biopsy (MR-TB) has emerged to the biopsy technique of choice for evaluation of patients with suspected prostate cancer (PCA). The study aimed to determine expected and experienced pain during MR-TB depending on patients' psychological state. METHODS: We prospectively enrolled 108 men with suspicion of PCA who underwent MR-TB. All patients completed self-reported validated questionnaires assessing pain, stress, self-efficacy, anxiety and study-specific questionnaires on expected and experienced pain before, during and after MR-TB. Patient characteristics and survey scores were obtained. RESULTS: Overall, pain levels during MR-TB were low (mean 2.8/10 ± 2.5 Numerical Rating Scale, NRS). 10/86 (11.6%) participants reported severe pain (≥ 7/10 NRS). Pain correlated significantly with anxiety (r = 0.42), stress (r = 0.22) and pain expectancy (r = 0.58). High self-efficacy did not show increased pain resilience. Participants anticipated more pain than experienced during each step of MR-TB with significant differences concerning local anesthesia and core sampling (both p < 0.001), among others. Expectancy and actual pain did not match regarding severity and impact of the total amount of cores taken (p < 0.05). Independent predictors of increased pain at biopsy were prostate volume > 50 ml (p = 0.0179) and expected pain during rectal manipulation (p < 0.001). CONCLUSION: Pain during MR-TB can be positively influenced by reducing men's anxiety, stress and pain expectancy. To meet the needs of the audience, clinicians should address concrete pain levels of each procedural step and consider special treatment for patients with prostate volume > 50 ml and men reporting on increased rectal sensitivity.

End-to-end automated body composition analyses with integrated quality control for opportunistic assessment of sarcopenia in CT.

OBJECTIVES: To develop a pipeline for automated body composition analysis and skeletal muscle assessment with integrated quality control for large-scale application in opportunistic imaging. METHODS: First, a convolutional neural network for extraction of a single slice at the L3/L4 lumbar level was developed on CT scans of 240 patients applying the nnU-Net framework. Second, a 2D competitive dense fully convolutional U-Net for segmentation of visceral and subcutaneous adipose tissue (VAT, SAT), skeletal muscle (SM), and subsequent determination of fatty muscle fraction (FMF) was developed on single CT slices of 1143 patients. For both steps, automated quality control was integrated by a logistic regression model classifying the presence of L3/L4 and a linear regression model predicting the segmentation quality in terms of Dice score. To evaluate the performance of the entire pipeline end-to-end, body composition metrics, and FMF were compared to manual analyses including 364 patients from two centers. RESULTS: Excellent results were observed for slice extraction (z-deviation = 2.46 ± 6.20 mm) and segmentation (Dice score for SM = 0.95 ± 0.04, VAT = 0.98 ± 0.02, SAT = 0.97 ± 0.04) on the dual-center test set excluding cases with artifacts due to metallic implants. No data were excluded for end-to-end performance analyses. With a restrictive setting of the integrated segmentation quality control, 39 of 364 patients were excluded containing 8 cases with metallic implants. This setting ensured a high agreement between manual and fully automated analyses with mean relative area deviations of ΔSM = 3.3 ± 4.1%, ΔVAT = 3.0 ± 4.7%, ΔSAT = 2.7 ± 4.3%, and ΔFMF = 4.3 ± 4.4%. CONCLUSIONS: This study presents an end-to-end automated deep learning pipeline for large-scale opportunistic assessment of body composition metrics and sarcopenia biomarkers in clinical routine. KEY POINTS: • Body composition metrics and skeletal muscle quality can be opportunistically determined from routine abdominal CT scans. • A pipeline consisting of two convolutional neural networks allows an end-to-end automated analysis. • Machine-learning-based quality control ensures high agreement between manual and automatic analysis.

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.

Cardiac MRI in Patients with Prolonged Cardiorespiratory Symptoms after Mild to Moderate COVID-19.

Background Myocardial injury and inflammation at cardiac MRI in patients with COVID-19 have been described in recent publications. Concurrently, a chronic COVID-19 syndrome (CCS) after SARS-CoV-2 infection has been observed and manifests with symptoms such as fatigue and exertional dyspnea. Purpose To explore the relationship between CCS and myocardial injury and inflammation as an underlying cause of the persistent complaints in previously healthy individuals. Materials and Methods In this prospective study from January 2021 to April 2021, study participants without known cardiac or pulmonary diseases prior to SARS-CoV-2 infection who had persistent CCS symptoms such as fatigue or exertional dyspnea after convalescence and healthy control participants underwent cardiac MRI. The cardiac MRI protocol included evaluating the T1 and T2 relaxation times, extracellular volume, T2 signal intensity ratio, and late gadolinium enhancement (LGE). Student t tests, Mann-Whitney U tests, and χ2 tests were used for statistical analysis. Results Forty-one participants with CCS (mean age, 39 years ± 13 [standard deviation]; 18 men) and 42 control participants (mean age, 39 years ± 16; 26 men) were evaluated. The median time between the initial incidence of mild to moderate COVID-19 not requiring hospitalization and undergoing cardiac MRI was 103 days (interquartile range, 88-158 days). Troponin T levels were normal. Parameters indicating myocardial inflammation and edema were comparable between participants with CCS and control participants (T1 relaxation times: 978 msec ± 23 vs 971 msec ± 25 [P = .17]; T2 relaxation times: 53 msec ± 2 vs 52 msec ± 2 [P = .47]; T2 signal intensity ratios: 1.6 ± 0.2 vs 1.6 ± 0.3 [P = .10]). Visible myocardial edema was present in none of the participants. Three of 41 (7%) participants with CCS demonstrated nonischemic LGE, whereas no participants in the control group demonstrated nonischemic LGE (0 of 42 [0%]; P = .07). None of the participants fulfilled the 2018 Lake Louise criteria for the diagnosis of myocarditis. Conclusion Individuals with chronic COVID-19 syndrome who did not undergo hospitalization for COVID-19 did not demonstrate signs of active myocardial injury or inflammation at cardiac MRI. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Lima and Bluemke in this issue.

Diagnostic Benefit of MRI for Exclusion of Ligamentous Injury in Patients with Lateral Atlantodental Interval Asymmetry at Initial Trauma CT.

Background Cervical spine CT is regularly performed to exclude cervical spine injury during the initial evaluation of trauma patients. Patients with asymmetry of the lateral atlantodental interval (LADI) often undergo subsequent MRI to rule out ligamentous injuries. The clinical relevance of an asymmetric LADI and the benefit of additional MRI remain unclear. Purpose To evaluate the diagnostic benefit of additional MRI in patients with blunt trauma who have asymmetry of the LADI and no other cervical injuries. Materials and Methods Patients who underwent cervical spine CT during initial trauma evaluation between March 2017 and August 2019 were retrospectively evaluated. Those who underwent subsequent MRI because of LADI asymmetry of 1 mm or greater with no other signs of cervical injury were identified and reevaluated by two readers blinded to clinical data and initial study reports regarding possible ligamentous injuries. Results Among 1553 patients, 146 (9%) had LADI asymmetry of 1 mm or greater. Of these, 46 patients (mean age ± standard deviation, 39 years ± 22; 28 men; median LADI asymmetry, 2.4 mm [interquartile range, 1.8-3.1 mm]) underwent supplementary MRI with no other signs of cervical injury at initial CT. Ten of the 46 patients (22%) showed cervical tenderness at clinical examination, and 36 patients (78%) were asymptomatic. In two of the 46 patients (4%), MRI revealed alar ligament injury; both of these patients showed LADI asymmetry greater than 3 mm, along with cervical tenderness at clinical examination, and underwent treatment for ligamentous injury. In 13 of the 46 patients (28%), signal intensity alterations of alar ligaments without signs of rupture were observed. Four of these 13 patients (31%) were subsequently treated for ligamentous injury despite being asymptomatic. Conclusion Subsequent MRI following CT of the cervical spine in trauma patients with lateral atlantodental interval asymmetry may have diagnostic benefit only in symptomatic patients. In asymptomatic patients without proven cervical injuries, subsequent MRI showed no diagnostic benefit and may even lead to overtreatment. © RSNA, 2021 Online supplemental material is available for this article.

Cardiac MRI Depicts Immune Checkpoint Inhibitor-induced Myocarditis: A Prospective Study.

Background Immune checkpoint inhibitors (ICIs) for cancer treatment are associated with a spectrum of immune-related adverse events, including ICI-induced myocarditis; however, the extent of subclinical acute cardiac effects related to ICI treatment is unclear. Purpose To explore the extent of cardiac injury and inflammation related to ICI therapy that can be detected with use of cardiac MRI. Materials and Methods In this prospective study from November 2019 to April 2021, oncologic participants, without known underlying structural heart disease or cardiac symptoms, underwent multiparametric cardiac MRI before planned ICI therapy (baseline) and 3 months after starting ICI therapy (follow-up). The cardiac MRI protocol incorporated assessment of cardiac function, including systolic myocardial strain, myocardial edema, late gadolinium enhancement (LGE), T1 and T2 relaxation times, and extracellular volume fraction. The paired t test, Wilcoxon signed-rank test, and McNemar test were used for intraindividual comparisons. Results Twenty-two participants (mean age ± standard deviation, 65 years ± 14; 13 men) were evaluated, receiving a median of four infusions of ICI therapy (interquartile range, four to six infusions). Compared with baseline MRI, participants displayed increased markers of diffuse myocardial edema at follow-up (T1 relaxation time, 972 msec ± 26 vs 1006 msec ± 36 [P < .001]; T2 relaxation time, 54 msec ± 3 vs 58 msec ± 4 [P < .001]; T2 signal intensity ratio, 1.5 ± 0.3 vs 1.7 ± 0.3 [P = .03]). Left ventricular average systolic longitudinal strain had decreased at follow-up MRI (-23.4% ± 4.8 vs -19.6% ± 5.1, respectively; P = .005). New nonischemic LGE lesions were prevalent in two of 22 participants (9%). Compared with baseline, small pericardial effusions were more evident at follow-up (one of 22 participants [5%] vs 10 of 22 [45%]; P = .004). Conclusion In participants who received immune checkpoint inhibitor therapy for cancer treatment, follow-up cardiac MRI scans showed signs of systolic dysfunction and increased parameters of myocardial edema and inflammation. © RSNA, 2021 Online supplemental material is available for this article.

Detection of liver cirrhosis in standard T2-weighted MRI using deep transfer learning.

OBJECTIVES: To investigate the diagnostic performance of deep transfer learning (DTL) to detect liver cirrhosis from clinical MRI. METHODS: The dataset for this retrospective analysis consisted of 713 (343 female) patients who underwent liver MRI between 2017 and 2019. In total, 553 of these subjects had a confirmed diagnosis of liver cirrhosis, while the remainder had no history of liver disease. T2-weighted MRI slices at the level of the caudate lobe were manually exported for DTL analysis. Data were randomly split into training, validation, and test sets (70%/15%/15%). A ResNet50 convolutional neural network (CNN) pre-trained on the ImageNet archive was used for cirrhosis detection with and without upstream liver segmentation. Classification performance for detection of liver cirrhosis was compared to two radiologists with different levels of experience (4th-year resident, board-certified radiologist). Segmentation was performed using a U-Net architecture built on a pre-trained ResNet34 encoder. Differences in classification accuracy were assessed by the χ2-test. RESULTS: Dice coefficients for automatic segmentation were above 0.98 for both validation and test data. The classification accuracy of liver cirrhosis on validation (vACC) and test (tACC) data for the DTL pipeline with upstream liver segmentation (vACC = 0.99, tACC = 0.96) was significantly higher compared to the resident (vACC = 0.88, p < 0.01; tACC = 0.91, p = 0.01) and to the board-certified radiologist (vACC = 0.96, p < 0.01; tACC = 0.90, p < 0.01). CONCLUSION: This proof-of-principle study demonstrates the potential of DTL for detecting cirrhosis based on standard T2-weighted MRI. The presented method for image-based diagnosis of liver cirrhosis demonstrated expert-level classification accuracy. KEY POINTS: • A pipeline consisting of two convolutional neural networks (CNNs) pre-trained on an extensive natural image database (ImageNet archive) enables detection of liver cirrhosis on standard T2-weighted MRI. • High classification accuracy can be achieved even without altering the pre-trained parameters of the convolutional neural networks. • Other abdominal structures apart from the liver were relevant for detection when the network was trained on unsegmented images.

Magnetic resonance parametric mapping of the spleen for non-invasive assessment of portal hypertension.

OBJECTIVES: In patients with advanced liver disease, portal hypertension is an important risk factor, leading to complications such as esophageal variceal bleeding, ascites, and hepatic encephalopathy. This study aimed to determine the diagnostic value of T1 and T2 mapping and extracellular volume fraction (ECV) for the non-invasive assessment of portal hypertension. METHODS: In this prospective study, 50 participants (33 patients with indication for trans-jugular intrahepatic portosystemic shunt (TIPS) and 17 healthy volunteers) underwent MRI. The derivation and validation cohorts included 40 and 10 participants, respectively. T1 and T2 relaxation times and ECV of the liver and the spleen were assessed using quantitative mapping techniques. Direct hepatic venous pressure gradient (HVPG) and portal pressure measurements were performed during TIPS procedure. ROC analysis was performed to compare diagnostic performance. RESULTS: Splenic ECV correlated with portal pressure (r = 0.72; p < 0.001) and direct HVPG (r = 0.50; p = 0.003). No significant correlations were found between native splenic T1 and T2 relaxation times with portal pressure measurements (p > 0.05, respectively). In the derivation cohort, splenic ECV revealed a perfect diagnostic performance with an AUC of 1.000 for the identification of clinically significant portal hypertension (direct HVPG ≥ 10 mmHg) and outperformed other parameters: hepatic T2 (AUC, 0.731), splenic T2 (AUC, 0.736), and splenic native T1 (AUC, 0.806) (p < 0.05, respectively). The diagnostic performance of mapping parameters was comparable in the validation cohort. CONCLUSION: Splenic ECV was associated with portal pressure measurements in patients with advanced liver disease. Future studies should explore the diagnostic value of parametric mapping accross a broader range of pressure values. KEY POINTS: • Non-invasive assessment and monitoring of portal hypertension is an area of unmet interest. • Splenic extracellular volume fraction is strongly associated with portal pressure in patients with end-stage liver disease. • Quantitative splenic and hepatic MRI-derived parameters have a potential to become a new non-invasive diagnostic parameter to assess and monitor portal pressure.