Epicardial adipose tissue (EAT) is a visceral fat deposit related to coronary artery disease. Fully automated quantification of EAT volume in clinical routine could be a timesaving and reliable tool for cardiovascular risk assessment. We propose a new fully automated deep learning framework for EAT and thoracic adipose tissue (TAT) quantification from non-contrast coronary artery calcium computed tomography (CT) scans. The first multi-task convolutional neural network (ConvNet) is used to determine heart limits and perform segmentation of heart and adipose tissues. The second ConvNet, combined with a statistical shape model, allows for pericardium detection. EAT and TAT segmentations are then obtained from outputs of both ConvNets. We evaluate the performance of the method on CT data sets from 250 asymptomatic individuals. Strong agreement between automatic and expert manual quantification is obtained for both EAT and TAT with median Dice score coefficients of 0.823 (inter-quartile range (IQR): 0.779-0.860) and 0.905 (IQR: 0.862-0.928), respectively; with excellent correlations of 0.924 and 0.945 for EAT and TAT volumes. Computations are performed in <6 s on a standard personal computer for one CT scan. Therefore, the proposed method represents a tool for rapid fully automated quantification of adipose tissue and may improve cardiovascular risk stratification in patients referred for routine CT calcium scans.

Background: Coronary computed tomography angiography (CTA) allows quantification of stenosis. However, such quantitative analysis is not part of clinical routine. We evaluated the feasibility of utilizing deep learning for quantifying coronary artery disease from CTA. Methods: A total of 716 diseased segments in 156 patients (66 ± 10 years) who underwent CTA were analyzed. Minimal luminal area (MLA), percent diameter stenosis (DS), and percent contrast density difference (CDD) were measured using semi-automated software (Autoplaque) by an expert reader. Using the expert annotations, deep learning was performed with convolutional neural networks using 10-fold cross-validation to segment CTA lumen and calcified plaque. MLA, DS and CDD computed using deep-learning-based approach was compared to expert reader measurements. Results: There was excellent correlation between the expert reader and deep learning for all quantitative measures (r=0.984 for MLA; r=0.957 for DS; and r=0.975 for CDD, p<0.001 for all). The expert reader and deep learning method was not significantly different for MLA (median 4.3 mm2 for both, p=0.68) and CDD (11.6 vs 11.1%, p=0.30), and was significantly different for DS (26.0 vs 26.6%, p<0.05); however, the ranges of all the quantitative measures were within inter-observer variability between 2 expert readers. Conclusions: Our deep learning-based method allows quantitative measurement of coronary artery disease segments accurately from CTA and may enhance clinical reporting.

Aims The value of core decompression (CD) in the treatment of osteonecrosis of the femoral head (ONFH) remains controversial. We conducted a systematic review and meta-analysis to evaluate whether CD combined with other treatments could improve the clinical and radiological outcomes of ONFH patients compared with CD alone. Methods We searched the PubMed, Embase, Web of Science, and Cochrane Library databases until June 2020. All randomized controlled trials (RCTs) and clinical controlled trials (CCTs) comparing CD alone and CD combined with other measures (CD + cell therapy, CD + bone grafting, CD + porous tantalum rod, etc.) for the treatment of ONFH were considered eligible for inclusion. The primary outcomes of interest were Harris Hip Score (HHS), ONFH stage progression, structural failure (collapse) of the femoral head, and conversion to total hip arthroplasty (THA). The pooled data were analyzed using Review Manager 5.3 software. Results A total of 20 studies with 2,123 hips were included (CD alone = 768, CD combined with other treatments = 1,355). The combination of CD with other therapeutic interventions resulted in a higher HHS (mean difference (MD) = 6.46, 95% confidence interval (CI) = 2.10 to 10.83, p = 0.004) and Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) score (MD = −10.92, 95% CI = -21.41 to -4.03, p = 0.040) and a lower visual analogue scale (VAS) score (MD = −0.99, 95% CI = -1.56 to -0.42, p < 0.001) than CD alone. For the rates of disease stage progression, 91 (20%) progressed in the intervention group compared to 146 (36%) in the control group (odds ratio (OR) = 0.32, 95% CI = 0.16 to 0.64, p = 0.001). In addition, the intervention group had a more significant advantage in delaying femoral head progression to the collapsed stage (OR = 0.32, 95% CI = 0.17 to 0.61, p < 0.001) and reducing the odds of conversion to THA (OR = 0.35, 95% CI = 0.23 to 0.55, p < 0.001) compared to the control group. There were no serious adverse events in either group. Subgroup analysis showed that the addition of cell therapy significantly improved clinical and radiological outcomes compared to CD alone, and this approach appeared to be more effective than other therapies, particularly in precollapse (stage I to II) ONFH patients. Conclusion There was marked heterogeneity in the studies. There is a trend towards improved clinical outcomes with the addition of stem cell therapy to CD. Cite this article: Bone Joint Res 2021;10(7):445–458.

Primary glomus tumors of the kidney are rare and have never been reported in children under 16 years of age. Tuberous sclerosis complex (TSC) is an extremely variable genetic condition that can affect virtually any organ in the body. Only a single case of glomus tumor associated with TSC was reported in 1964. In this article, we describe the clinical, radiologic, and pathological features of a primary renal glomus tumor in an 8-year-old girl with TSC. This tumor is large, has a deep location, and has infiltrative margins and numerous mitoses. However, there was no disease progression in a 16-month period of follow-up. To our knowledge, this is the second report of primary renal glomus tumor in childhood, the youngest one in the literature.