Deep-learning-based image quality enhancement of CT-like MR imaging in patients with suspected traumatic shoulder injury.

PURPOSE: To evaluate the diagnostic performance of CT-like MR images reconstructed with an algorithm combining compressed sense (CS) with deep learning (DL) in patients with suspected osseous shoulder injury compared to conventional CS-reconstructed images. METHODS: Thirty-two patients (12 women, mean age 46 ± 14.9 years) with suspected traumatic shoulder injury were prospectively enrolled into the study. All patients received MR imaging of the shoulder, including a CT-like 3D T1-weighted gradient-echo (T1 GRE) sequence and in case of suspected fracture a conventional CT. An automated DL-based algorithm, combining CS and DL (CS DL) was used to reconstruct images of the same k-space data as used for CS reconstructions. Two musculoskeletal radiologists assessed the images for osseous pathologies, image quality and visibility of anatomical landmarks using a 5-point Likert scale. Moreover, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated. RESULTS: Compared to CT, all acute fractures (n = 23) and osseous pathologies were detected accurately on the CS only and CS DL images with almost perfect agreement between the CS DL and CS only images (κ 0.95 (95 %confidence interval 0.82-1.00). Image quality as well as the visibility of the fracture lines, bone fragments and glenoid borders were overall rated significantly higher for the CS DL reconstructions than the CS only images (CS DL range 3.7-4.9 and CS only range 3.2-3.8, P = 0.01-0.04). Significantly higher SNR and CNR values were observed for the CS DL reconstructions (P = 0.02-0.03). CONCLUSION: Evaluation of traumatic shoulder pathologies is feasible using a DL-based algorithm for reconstruction of high-resolution CT-like MR imaging.

Elucidation of the genetic causes of bicuspid aortic valve disease.

AIMS: The present study aims to characterize the genetic risk architecture of bicuspid aortic valve (BAV) disease, the most common congenital heart defect. METHODS AND RESULTS: We carried out a genome-wide association study (GWAS) including 2236 BAV patients and 11 604 controls. This led to the identification of a new risk locus for BAV on chromosome 3q29. The single nucleotide polymorphism rs2550262 was genome-wide significant BAV associated (P = 3.49 × 10-08) and was replicated in an independent case-control sample. The risk locus encodes a deleterious missense variant in MUC4 (p.Ala4821Ser), a gene that is involved in epithelial-to-mesenchymal transformation. Mechanistical studies in zebrafish revealed that loss of Muc4 led to a delay in cardiac valvular development suggesting that loss of MUC4 may also play a role in aortic valve malformation. The GWAS also confirmed previously reported BAV risk loci at PALMD (P = 3.97 × 10-16), GATA4 (P = 1.61 × 10-09), and TEX41 (P = 7.68 × 10-04). In addition, the genetic BAV architecture was examined beyond the single-marker level revealing that a substantial fraction of BAV heritability is polygenic and ∼20% of the observed heritability can be explained by our GWAS data. Furthermore, we used the largest human single-cell atlas for foetal gene expression and show that the transcriptome profile in endothelial cells is a major source contributing to BAV pathology. CONCLUSION: Our study provides a deeper understanding of the genetic risk architecture of BAV formation on the single marker and polygenic level.

MR elastography is a good response parameter for microwave ablation liver tumors.

OBJECTIVES: To determine the response of hepatic tissue to percutaneous microwave ablation (MWA) of liver tumors via MR elastography in a clinical setting using MRI and MR elastography. METHODS: 51 Patients (28 m, 23f) underwent MWA of liver tumors (HCC: 20, metastasis: 31) and received MRI and MR elastography immediately before and 24 h after MWA. Retrospective analysis included pre- and post-ablative tumor extent, T1/T2 mapping and stiffness values as well as the duration and energy dose of the MWA session. RESULTS: Total liver stiffness increased by 4.3% from 3.31 kPa to 3.45 kPa (p = 0.036). Total liver stiffness post-MWA significantly correlated with the duration of the MWA session (r = 0.369, p = 0.008). The higher the baseline tumor stiffness was, the more energy had to be applied in MWA (r = 0.391, p < 0.001) and the longer the duration of the session (r = 0.391, p = 0.007). Healthy parenchyma stiffness increased by 3.5% from 3.55 kPa to 3.68 kPa (p = 0.142) and was strongly influenced by the cumulative energy (r = 0.436, p < 0.001), the duration (r = 0.458, p < 0.001) and the energy intensity (r = 0.458, p < 0.001) of MWA. 43 patients had a technically successful ablation result (margin ≥ 5 mm). Those with successful ablation had increased ablation margin stiffness (5.3 kPa vs. 4.6 kPa, p = 0.26) and had received higher ablation intensity than those with unsuccessful ablation (5.73 kJ/min vs. 5.03 kJ/min, p = 0.002). CONCLUSION: Additional MRE may be used before and after MWA to assess treatment response and collateral tissue damage after MWA. Baseline tumor stiffness helps finding the appropriate MWA parameters.

Evaluation of MR elastography as a response parameter for transarterial chemoembolization of colorectal liver metastases.

OBJECTIVE: The aim of this study was to evaluate magnetic resonance elastography (MRE) as a response parameter in patients who received transarterial chemoembolization (TACE) for the treatment of colorectal liver metastases. MATERIALS AND METHODS: Forty-two patients (29 male patients; mean age, 61.5 years; range, 41-84 years) with repeated TACE therapy of colorectal liver metastases underwent on average 2 repetitive magnetic resonance imaging (MRI) and MRE exams in 4- to 6-week intervals using a 1.5-T scanner. MRE-based liver stiffness measurements were performed in normal liver parenchyma and in metastatic lesions. Moreover, the size of the liver metastases was assessed during treatment and compared with the results of the MRE analysis. RESULTS: Liver metastases showed a significantly higher degree of stiffness compared with the normal liver parenchyma (p < 0.001). However, only a weak correlation was found between the lesion size and stiffness (r = - 0.32, p = 0.1). MRE analysis revealed an increase in stiffness of the colorectal liver metastases from 4.4 to 7.1 kPa after three cycles of TACE (p < 0.001). Also, the mean size of the metastases decreased from 17.0 to 11.3 cm2 (p < 0.001). Finally, the entire liver stiffness increased from 2.9 to 3.1 kPa over the three cycles of TACE therapy. CONCLUSION: In conclusion, MRE showed a significant change in stiffness and size of liver metastases. Therefore, MRE may provide an added value for an evaluation of treatment response in patients with colorectal liver metastases undergoing TACE. KEY POINTS: • MRE showed an increase in stiffness of the colorectal liver metastases during TACE therapy. • Liver metastases showed a significantly higher degree of stiffness compared with the normal liver parenchyma. • However, only a weak correlation was found between the lesion size and stiffness.