Enhanced bone assessment of the shoulder using zero-echo time MRI with deep-learning image reconstruction.

OBJECTIVES: To assess a deep learning-based reconstruction algorithm (DLRecon) in zero echo-time (ZTE) MRI of the shoulder at 1.5 Tesla for improved delineation of osseous findings. METHODS: In this retrospective study, 63 consecutive exams of 52 patients (28 female) undergoing shoulder MRI at 1.5 Tesla in clinical routine were included. Coronal 3D isotropic radial ZTE pulse sequences were acquired in the standard MR shoulder protocol. In addition to standard-of-care (SOC) image reconstruction, the same raw data was reconstructed with a vendor-supplied prototype DLRecon algorithm. Exams were classified into three subgroups: no pathological findings, degenerative changes, and posttraumatic changes, respectively. Two blinded readers performed bone assessment on a 4-point scale (0-poor, 3-perfect) by qualitatively grading image quality features and delineation of osseous pathologies including diagnostic confidence in the respective subgroups. Quantitatively, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of bone were measured. Qualitative variables were compared using the Wilcoxon signed-rank test for ordinal data and the McNemar test for dichotomous variables; quantitative measures were compared with Student's t-testing. RESULTS: DLRecon scored significantly higher than SOC in all visual metrics of image quality (all, p < 0.03), except in the artifact category (p = 0.37). DLRecon also received superior qualitative scores for delineation of osseous pathologies and diagnostic confidence (p ≤ 0.03). Quantitatively, DLRecon achieved superior CNR (95 CI [1.4-3.1]) and SNR (95 CI [15.3-21.5]) of bone than SOC (p < 0.001). CONCLUSION: DLRecon enhanced image quality in ZTE MRI and improved delineation of osseous pathologies, allowing for increased diagnostic confidence in bone assessment.

Does quantitative assessment of arterial phase hyperenhancement and washout improve LI-RADS v2018-based classification of liver lesions?

OBJECTIVES: To compare interreader agreement and diagnostic accuracy of LI-RADS v2018 categorization using quantitative versus qualitative MRI assessment of arterial phase hyperenhancement (APHE) and washout (WO) of focal liver lesions. METHODS: Sixty patients (19 female; mean age, 56 years) at risk for HCC with 71 liver lesions (28 HCCs, 43 benign) who underwent contrast-enhanced MRI were included in this retrospective study. Four blinded radiologists independently assigned a qualitative LI-RADS score per lesion. Two other radiologists placed ROIs within the lesion, adjacent liver parenchyma, and paraspinal musculature on pre- and post-contrast MR images. The percentage of arterial enhancement and the liver-to-lesion contrast ratio were calculated for quantification of APHE and WO. Using these quantitative parameters, a quantitative LI-RADS score was assigned. Interreader agreement and AUCs were calculated. RESULTS: Interreader agreement was similar for qualitative and quantitative LI-RADS (κ = 0.38 vs. 0.40-0.47) with a tendency towards improved agreement for quantitatively assessed APHE (κ = 0.65 vs. 0.81) and WO (κ = 0.53 vs. 0.78). Qualitative LI-RADS showed an AUC of 0.86, 0.94, 0.94, and 0.91 for readers 1, 2, 3, and 4, respectively. The quantitative LI-RADS score where APHE/WO/or both were replaced showed an AUC of 0.89/0.84/0.89, 0.95/0.92/0.92, 0.93/0.91/0.89, and 0.91/0.86/0.88 for readers 1, 2, 3, and 4, respectively. Sensitivity of LR-4/5 slightly increased, while specificity slightly decreased using quantitative APHE. CONCLUSION: Qualitative and quantitative LI-RADS showed similar performance. Quantitatively assessed APHE showed the potential to increase interreader agreement and sensitivity of HCC diagnosis, whereas quantitatively assessed WO had the opposite effect and needs to be redefined. KEY POINTS: • Quantitative assessment of arterial phase hyperenhancement shows the potential to increase interreader agreement and sensitivity to diagnose hepatocellular carcinoma. • Adding quantitative measurements of major LI-RADS features does not improve accuracy over qualitative assessment alone according to the LI-RADS v2018 algorithm.

Anatomy-based MRI assessment of the iliopsoas muscle complex after pertrochanteric femoral fracture.

OBJECTIVE: To evaluate the quality of the iliopsoas muscle complex after pertrochanteric femoral fracture, using MRI; to propose an anatomy-based evaluation of the iliopsoas muscle complex; and to determine the inter-reader reliability of two classifications of fatty muscle degeneration. MATERIALS AND METHODS: We included adult patients with a displaced lesser trochanter following pertrochanteric femoral fracture. Muscle quality was evaluated using the Goutallier and Slabaugh classifications at three levels (L4/L5, L5/S1, and the anterior inferior iliac spine). Two radiologists independently reviewed the MRIs, and force measurement was performed on both hips. Linear mixed-effects models were used to determine the effect of fracture on muscle quality and strength, and Cohen's kappa statistic was used to assess inter-reader agreement. RESULTS: In the 18 patients included, the iliopsoas muscle complex showed higher grades of fatty muscle degeneration on the fractured side than on the non-fractured side. The mean difference between muscle strength on the fractured vs the non-fractured side was -12 N (p > 0.05). Inter-reader agreement for the Goutallier and Slabaugh classifications was good and very good respectively (weighted K = 0.78 and 0.85 respectively). CONCLUSION: Fatty muscle degeneration of the iliopsoas muscle complex after pertrochanteric femoral fracture was evident using both classification systems; however, fatty muscle degeneration resulted in only a minimal reduction of muscle strength. To provide a thorough assessment of iliopsoas muscle complex quality, we suggest evaluating it at different anatomical levels. Regarding inter-reader agreement, the Slabaugh classification was superior to the Goutallier classification.