Deep Learning Enables Automatic Detection of Joint Damage Progression in Rheumatoid Arthritis-Model Development and External Validation.

OBJECTIVES: Although deep learning has demonstrated substantial potential in automatic quantification of joint damage in rheumatoid arthritis (RA), evidence for detecting longitudinal changes at an individual patient level is lacking. Here, we introduce and externally validate our automated RA scoring algorithm (AuRA), and demonstrate its utility for monitoring radiographic progression in a real-world setting. METHODS: The algorithm, originally developed during the Rheumatoid Arthritis 2-Dialogue for Reverse Engineering Assessment and Methods (RA2-DREAM) challenge, was trained to predict expert-curated Sharp-van der Heijde total scores in hand and foot radiographs from two previous clinical studies (n = 367). We externally validated AuRA against data (n = 205) from Turku University Hospital and compared the performance against two top-performing RA2-DREAM solutions. Finally, for 54 patients, we extracted additional radiograph sets from another control visit to the clinic (average time interval of 4.6 years). RESULTS: In the external validation cohort, with a root-mean-square-error (RMSE) of 23.6, AuRA outperformed both top-performing RA2-DREAM algorithms (RMSEs 35.0 and 35.6). The improved performance was explained mostly by lower errors at higher expert-assessed scores. The longitudinal changes predicted by our algorithm were significantly correlated with changes in expert-assessed scores (Pearson's R = 0.74, p< 0.001). CONCLUSION: AuRA had the best external validation performance and demonstrated potential for detecting longitudinal changes in joint damage. Available in https://hub.docker.com/r/elolab/aura, our algorithm can easily be applied for automatic detection of radiographic progression in the future, reducing the need for laborious manual scoring.

Elastic Lumbar Support Versus Rigid Thoracolumbar Orthosis for Acute Pediatric Spondylolysis: A Prospective Controlled Study.

STUDY DESIGN: A prospective study on clinical, radiographic, and health-related quality of life (HRQoL) outcomes in children with acute spondylolysis treated with a rigid thoracolumbar orthosis or with an elastic lumbar support. OBJECTIVE: To compare outcomes of pediatric spondylosysis treated with a hard brace or an elastic lumbar support. SUMMARY OF BACKGROUND DATA: The benefits of the use of a rigid orthosis in treatment of spondylolysis are not clear. MATERIALS AND METHODS: Fifty-seven consecutive children with acute spondylolysis (mean age: 14.1 yr, range: 9-17 yr) were prospectively enrolled. Patients were treated with a rigid thoracolumbar orthosis (Boston brace) or with a low-profile, elastic lumbar support. First 14 patients were randomized the remaining 43 chose brace type themselves. Treatment period was four months. Treatment outcomes included bony union of the spondylolysis assessed with a computed tomography at four months and HRQoL using the Scoliosis Research Society-24 outcome questionnaire filled out before and after the treatment. RESULTS: Of the 57 patients, 54 completed the treatment protocol. Twenty-nine patients were treated using the Boston brace and 25 patients the elastic lumbar support. Bony union was obtained in 69.0% (20/29) of the Boston brace and in 60.0% (15/25) of the elastic lumbar support group patients. Difference in union rates was not significant (relative risk=1.14, 95% confidence interval: 0.44-2.98, P =0.785). There was no difference in the Scoliosis Research Society-24 total or domain scores at the end of follow-up between the treatment groups ( P >0.159 for all comparisons). In the whole cohort, the bony union did not predict better HRQoL in the end of the treatment ( P =0.869), although the pain domain improved significantly in the whole cohort ( P <0.001). CONCLUSIONS: A rigid thoracolumbar orthosis did not provide any benefits over an elastic lumbar support in terms of bony union or HRQoL outcomes in children with acute spondylolysis. LEVEL OF EVIDEN: 2.

Arthroscopic Bankart versus open Latarjet as a primary operative treatment for traumatic anteroinferior instability in young males: a randomised controlled trial with 2-year follow-up.

OBJECTIVES: To compare the success rates of arthroscopic Bankart and open Latarjet procedure in the treatment of traumatic shoulder instability in young males. DESIGN: Multicentre randomised controlled trial. SETTING: Orthopaedic departments in eight public hospitals in Finland. PARTICIPANTS: 122 young males, mean age 21 years (range 16-25 years) with traumatic shoulder anteroinferior instability were randomised. INTERVENTIONS: Arthroscopic Bankart (group B) or open Latarjet (group L) procedure. MAIN OUTCOME MEASURES: The primary outcome measure was the reported recurrence of instability, that is, dislocation at 2-year follow-up. The secondary outcome measures included clinical apprehension, sports activity level, the Western Ontario Shoulder Instability Index, the pain Visual Analogue Scale, the Oxford Shoulder Instability Score, the Constant Score and the Subjective Shoulder Value scores and the progression of osteoarthritic changes in plain films and MRI. RESULTS: 91 patients were available for analyses at 2-year follow-up (drop-out rate 25%). There were 10 (21%) patients with redislocations in group B and 1 (2%) in group L, p=0.006. One (9%) patient in group B and five (56%) patients in group L returned to their previous top level of competitive sports (p=0.004) at follow-up. There was no statistically significant between group differences in any of the other secondary outcome measures. CONCLUSIONS: Arthroscopic Bankart operation carries a significant risk for short-term postoperative redislocations compared with open Latarjet operation, in the treatment of traumatic anteroinferior instability in young males. Patients should be counselled accordingly before deciding the surgical treatment. TRIAL REGISTRATION NUMBER: NCT01998048.

Brown adipose tissue fat-fraction is associated with skeletal muscle adiposity.

PURPOSE: While brown adipose tissue (BAT) activity is known to be associated with both muscle and adipose tissue volumes, the association between BAT and muscle composition remains unclear, especially in adults. Therefore, the present study aimed to examine the association between BAT parameters (glucose uptake and fat-fraction) and muscle volumes and intramuscular adipose tissue contents among healthy young and middle-aged men. METHODS: BAT glucose uptake was determined using positron emission tomography with [18F]-2-deoxy-2-fluoro-D-glucose (18F-FDG) during cold exposure in 19 young and middle-aged men (36.3 ± 10.7 years). The fat-fraction of BAT was determined from volumes of interest set in cervical and supraclavicular adipose tissue depots using signal fat-fraction maps via magnetic resonance imaging (MRI). Muscle volumes and intramuscular adipose tissue contents of m. tibialis anterior and m. multifidus lumborum were measured using MRI. RESULTS: The fat-fraction of BAT was significantly associated with intramuscular adipose tissue content in m. tibialis anterior (n = 13, rs = 0.691, P = 0.009). A similar trend was also observed in m. multifidus lumborum (n = 19, rs = 0.454, P = 0.051). However, BAT glucose uptake was not associated with intramuscular adipose tissue contents in both muscles, nor were muscle volumes associated with the BAT glucose uptake and fat-fraction. CONCLUSION: The fat-fraction of BAT increases with skeletal muscle adiposity, especially in the lower leg, among healthy young and middle-aged men.

MR signal-fat-fraction analysis and T2* weighted imaging measure BAT reliably on humans without cold exposure.

OBJECTIVE: Brown adipose tissue (BAT) is compositionally distinct from white adipose tissue (WAT) in terms of triglyceride and water content. In adult humans, the most significant BAT depot is localized in the supraclavicular area. Our aim is to differentiate brown adipose tissue from white adipose tissue using fat T2* relaxation time mapping and signal-fat-fraction (SFF) analysis based on a commercially available modified 2-point-Dixon (mDixon) water-fat separation method. We hypothesize that magnetic resonance (MR) imaging can reliably measure BAT regardless of the cold-induced metabolic activation, with BAT having a significantly higher water and iron content compared to WAT. MATERIAL AND METHODS: The supraclavicular area of 13 volunteers was studied on 3T PET-MRI scanner using T2* relaxation time and SFF mapping both during cold exposure and at ambient temperature; and 18F-FDG PET during cold exposure. Volumes of interest (VOIs) were defined semiautomatically in the supraclavicular fat depot, subcutaneous WAT and muscle. RESULTS: The supraclavicular fat depot (assumed to contain BAT) had a significantly lower SFF and fat T2* relaxation time compared to subcutaneous WAT. Cold exposure did not significantly affect MR-based measurements. SFF and T2* values measured during cold exposure and at ambient temperature correlated inversely with the glucose uptake measured by 18F-FDG PET. CONCLUSIONS: Human BAT can be reliably and safely assessed using MRI without cold activation and PET-related radiation exposure.

Measurement of brown adipose tissue mass using a novel dual-echo magnetic resonance imaging approach: a validation study.

OBJECTIVE: The aim of this study was to evaluate and validate magnetic resonance imaging (MRI) for the visualization and quantification of brown adipose tissue (BAT) in vivo in a rat model. We hypothesized that, based on differences in tissue water and lipid content, MRI could reliably differentiate between BAT and white adipose tissue (WAT) and could therefore be a possible alternative for (18)F-Fluorodeoxyglucose Positron Emission Tomography ((18)FDG-PET), the current gold standard for non-invasive BAT quantification. MATERIALS/METHODS: Eleven rats were studied using both (18)FDG-PET/CT and MRI (1.5 T). A dual echo (in-and-out-of-phase) sequence was used, both with and without spectral presaturation inversion recovery (SPIR) fat suppression (DUAL-SPIR) to visualize BAT, after which all BAT was surgically excised. The BAT volume measurements obtained via (18)FDG-PET/CT and DUAL-SPIR MR were quantitatively compared with the histological findings. All study protocols were reviewed and approved by the local ethics committee. RESULTS: The BAT mass measurements that were obtained using DUAL-SPIR MR subtraction images correlated better with the histological findings (P=0.017, R=0.89) than did the measurements obtained using (18)FDG-PET/CT (P=0.78, R=0.15), regardless of the BAT metabolic activation state. Additionally, the basic feasibility of the DUAL-SPIR method was demonstrated in three human pilot subjects. CONCLUSIONS: This study demonstrates the potential for MRI to reliably detect and quantify BAT in vivo. MRI can provide information beyond that provided by (18)FDG-PET imaging, and its ability to detect BAT is independent of its metabolic activation state. Additionally, MRI is a low-cost alternative that does not require radiation.