Validity of an ultrasonographic joint-specific scoring system in juvenile idiopathic arthritis: a cross-sectional study comparing ultrasound findings of synovitis with whole-body magnetic resonance imaging and clinical assessment.

OBJECTIVE: To assess the validity of an ultrasonographic scoring system in juvenile idiopathic arthritis (JIA) by comparing ultrasound detected synovitis with whole-body MRI and clinical assessment of disease activity. METHODS: In a cross-sectional study, 27 patients with active JIA underwent clinical 71-joints examination, non-contrast enhanced whole-body MRI and ultrasound evaluation of 28 joints (elbow, radiocarpal, midcarpal, metacarpophalangeal 2-3, proximal interphalangeal 2-3, hip, knee, tibiotalar, talonavicular, subtalar and metatarsophalangeal 2-3). One rheumatologist, blinded to clinical findings, performed ultrasound and scored synovitis (B-mode and power Doppler) findings using a semiquantitative joint-specific scoring system for synovitis in JIA. A radiologist scored effusion/synovial thickening on whole-body MRI using a scoring system for whole-body MRI in JIA. At patient level, associations between ultrasound synovitis sum scores, whole-body MRI effusion/synovial thickening sum scores, clinical arthritis sum scores, and the 71-joints Juvenile Arthritis Disease Activity Score (JADAS71) were calculated using Spearman's correlation coefficients (rs). To explore associations at joint level, sensitivity and specificity were calculated for ultrasound using whole-body MRI or clinical joint examination as reference. RESULTS: Ultrasound synovitis sum scores strongly correlated with whole-body MRI effusion/synovial thickening sum scores (rs=0.74,p<0.01) and the JADAS71 (rs=0.71,p<0.01), and moderately with clinical arthritis sum scores (rs=0.57,p<0.01). Sensitivity/specificity of ultrasound in detecting synovitis were 0.57/0.96 and 0.55/0.96 using whole-body MRI or clinical joint examination as reference, respectively. CONCLUSION: Our findings suggest that ultrasound is a valid instrument to detect synovitis, and that ultrasound synovitis sum scores can reflect disease activity and may be an outcome measure in JIA.

Automated segmentation of magnetic resonance bone marrow signal: a feasibility study.

BACKGROUND: Manual assessment of bone marrow signal is time-consuming and requires meticulous standardisation to secure adequate precision of findings. OBJECTIVE: We examined the feasibility of using deep learning for automated segmentation of bone marrow signal in children and adolescents. MATERIALS AND METHODS: We selected knee images from 95 whole-body MRI examinations of healthy individuals and of children with chronic non-bacterial osteomyelitis, ages 6-18 years, in a longitudinal prospective multi-centre study cohort. Bone marrow signal on T2-weighted Dixon water-only images was divided into three color-coded intensity-levels: 1 = slightly increased; 2 = mildly increased; 3 = moderately to highly increased, up to fluid-like signal. We trained a convolutional neural network on 85 examinations to perform bone marrow segmentation. Four readers manually segmented a test set of 10 examinations and calculated ground truth using simultaneous truth and performance level estimation (STAPLE). We evaluated model and rater performance through Dice similarity coefficient and in consensus. RESULTS: Consensus score of model performance showed acceptable results for all but one examination. Model performance and reader agreement had highest scores for level-1 signal (median Dice 0.68) and lowest scores for level-3 signal (median Dice 0.40), particularly in examinations where this signal was sparse. CONCLUSION: It is feasible to develop a deep-learning-based model for automated segmentation of bone marrow signal in children and adolescents. Our model performed poorest for the highest signal intensity in examinations where this signal was sparse. Further improvement requires training on larger and more balanced datasets and validation against ground truth, which should be established by radiologists from several institutions in consensus.

Hepatic magnetic resonance T1-mapping and extracellular volume fraction compared to shear-wave elastography in pediatric Fontan-associated liver disease.

BACKGROUND: Children with Fontan circulation are at risk of developing hepatic fibrosis/cirrhosis. Reliable noninvasive monitoring techniques are lacking or under development. OBJECTIVE: To investigate surrogate indicators of hepatic fibrosis in adolescents with Fontan circulation by evaluating hepatic magnetic resonance (MR) T1 mapping and extracellular volume fraction measurements compared to US shear-wave elastography. MATERIALS AND METHODS: We analyzed hepatic native T1 times and extracellular volume fractions with modified Look-Locker inversion recovery. Liver stiffness was analyzed with shear-wave elastography. We compared results between 45 pediatric patients ages 16.7±0.6 years with Fontan circulation and 15 healthy controls ages 19.2±1.2 years. Measurements were correlated to clinical and hemodynamic data from cardiac catheterization. RESULTS: MR mapping was successful in 35/45 patients, revealing higher hepatic T1 times (774±44 ms) than in controls (632±52 ms; P<0.001) and higher extracellular volume fractions (47.4±5.0%) than in controls (34.6±3.8%; P<0.001). Liver stiffness was 1.91±0.13 m/s in patients vs. 1.20±0.10 m/s in controls (P<0.001). Native T1 times correlated with central venous pressures (r=0.5, P=0.007). Native T1 was not correlated with elastography in patients (r=0.2, P=0.1) or controls (r = -0.3, P=0.3). Extracellular volume fraction was correlated with elastography in patients (r=0.5, P=0.005) but not in controls (r=0.2, P=0.6). CONCLUSION: Increased hepatic MR relaxometry and shear-wave elastography values in adolescents with Fontan circulation suggested the presence of hepatic fibrosis or congestion. Central venous pressure was related to T1 times. Changes were detected differently with MR relaxometry and elastography; thus, these techniques should not be used interchangeably in monitoring hepatic fibrosis.