Search

Background: Lumbago is a global disease that affects more than 500 million people worldwide. Bone marrow oedema is one of the main causes of the condition and clinical diagnosis is mainly made by radiologists manually reviewing MRI images to determine whether oedema is present. However, the number of patients with Lumbago has risen dramatically in recent years, which has brought a huge workload to radiologists. In order to improve the efficiency of diagnosis, this paper is devoted to developing and evaluating a neural network for detecting bone marrow edema in MRI images. Related work: Inspired by the development of deep learning and image processing techniques, we design a deep learning detection algorithm specifically for the detection of bone marrow oedema from lumbar MRI images. We introduce deformable convolution, feature pyramid networks and neural architecture search modules, and redesign the existing neural networks. We explain in detail the construction of the network and illustrate the setting of the network hyperparameters. Results and discussion: The detection accuracy of our algorithm is excellent. And its accuracy of detecting bone marrow oedema reached up to 90.6 % , an improvement of 5.7 % compared to the original. The recall of our neural network is 95.1 % , and the F1-measure also reaches 92.8 % . And our algorithm is fast in detecting it, taking only 0.144 s per image. Conclusion: Extensive experiments have demonstrated that deformable convolution and aggregated feature pyramid structures are conducive for the detection of bone marrow oedema. Our algorithm has better detection accuracy and good detection speed compared to other algorithms. [ABSTRACT FROM AUTHOR]

Purpose: Contrary to the self-limiting nature of reversible bone marrow lesions, irreversible bone marrow lesions require early surgical intervention to prevent further morbidity. Thus, early discrimination of irreversible pathology is necessitated. The purpose of this study is to evaluate the efficacy of radiomics and machine learning regarding this topic. Material and methods: A database was scanned for patients who had undergone MRI of the hip for differential diagnosis of bone marrow lesions and had had follow-up images acquired within 8 weeks after the first imaging. Images that showed resolution of oedema were included in the reversible group. The remainders that showed progression into characteristic signs of osteonecrosis were included in the irreversible group. Radiomics was performed on the first MR images, calculating first- and second-order parameters. Support vector machine and random forest classifiers were performed using these parameters. Results: Thirty-seven patients (seventeen osteonecrosis) were included. A total of 185 ROIs were segmented. Forty-seven parameters were accepted as classifiers with an area under the curve value ranging from 0.586 to 0.718. Support vector machine yielded a sensitivity of 91.3% and a specificity of 85.1%. Random forest classifier yielded a sensitivity of 84.8% and a specificity of 76.7%. Area under curves were 0.921 for support vector machine and 0.892 for random forest classifier. Conclusions: Radiomics analysis could prove useful for discrimination of reversible and irreversible bone marrow lesions before the irreversible changes occur, which could prevent morbidities of osteonecrosis by guiding the decision-making process for management. [ABSTRACT FROM AUTHOR]

Background: Hip labral tear (LT) causes various degrees of hip pain, for which there are few objective measures. Bone marrow oedema (BME), characterized by a diffuse, widely spreading change in the bone marrow, is observed in some patients with LT. However, its pathological role has not been fully understood. The purpose of this study was to investigate the prevalence of BME on hip magnetic resonance imaging (MRI) in patients with LT and to determine whether BME was an objective indicator of hip pain. Methods: In total, 84 patients with LT who underwent MRI scanning under the same conditions were included. We determined the presence or absence of BME and its size on MRI and evaluated the relationships between BME and sex, age, and pain and total scores on the modified Harris hip score (MHHS). In addition, we collected data on surgical treatments such as hip arthroscopy within a one-year follow-up period and examined whether the presence of BME affected the course of therapy. Results: BME was found in 34.5% of patients. MHHS pain and total scores were significantly lower in patients with BME (MHHS pain score: non-BME vs. BME ≤ 1 cm: p = 0.022, non-BME vs. BME > 1 cm: p < 0.001; MHHS total score: non-BME vs. BME ≤ 1 cm: p = 0.131, non-BME vs. BME > 1 cm: p = 0.027). The presence of BME did not differ between patients who did and did not undergo surgery during follow-up (p = 0.563). Conclusion: BME on MRI in patients with LT might be an indicator of hip pain and hip joint dysfunction. [ABSTRACT FROM AUTHOR]

Objective Several pharmacological treatments have been proposed for the treatment of complex regional pain syndrome type-I (CRPS-I) in adults, but data regarding the efficacy of various agents for this disease is scarce. We performed a systematic review and meta-analysis of randomized controlled trials (RCTs) to analyse the efficacy of the various pharmacological approaches in adults with CRPS-I. Methods We systematically searched PubMed, Scopus, and Web of Science databases from the inception date to 30 June 2021 to identify placebo-controlled or active-controlled RCTs using bisphosphonates, ketamine, CSs, anti-epileptics, NSAIDs/COXIBs, opiates, antidepressants, scavengers/magnesium sulphate or IVIGs for the treatment of CRPS-I. The primary outcomes included changes in the visual analogue scale (VAS) or numeric rating scale (NRS) for pain before and after treatment. Results We included 20 placebo-controlled or active-controlled RCTs (including a total of 818 adults with CRPS-I) that used bisphosphonates (n  = 7), ketamine (n  = 2), CSs (n  = 2), anti-epileptics (n  = 1), NSAIDs/selective inhibitors of cyclooxygenase-2 (COXIBs) (n  = 2), scavengers/magnesium sulphate (n  = 5), or IVIGs (n  = 1) to treat CRPS-I during a median follow-up of 26 weeks. Treatment with bisphosphonates showed a significant reduction in the values of the VAS/NRS pain scale compared with placebo or reference therapy (random effects weighted mean difference [WMD]: −23.8, 95% CI: −28.0 to −19.6; I 2 = 36.4%). Treatment with ketamine also documented a reduction in the values of the VAS/NRS for pain (random effects WMD: −8.27, 95% CI: −12.9 to −3.70; I 2 = 0%). Treatment with other agents did not reduce the values of the VAS/NRS assessments of pain. Conclusion This systematic review and meta-analysis supports the recommendation of parenteral bisphosphonates as the first-line agent in the treatment of CRPS-I. Trial registration Open Science Framework registries, https://osf.io/et9gu/ , osf.io/et9gu. [ABSTRACT FROM AUTHOR]

Objective ACHILLES aimed to demonstrate efficacy of secukinumab on Achilles' tendon enthesitis in spondyloarthritis (SpA) patients. Methods Patients ≥18 years (n  = 204) with active PsA or axial SpA and heel enthesitis were randomized 1:1 to secukinumab 150/300 mg or placebo up to week 24, and thereafter placebo patients were switched to secukinumab. Results At week 24, a higher, yet statistically non-significant (P  = 0.136), proportion of patients in secukinumab vs placebo reported resolution of Achilles tendon enthesitis in affected foot (42.2% vs 31.4%; odds ratio [OR] = 1.63; 95% CI: 0.87, 3.08). Proportion of patients reporting resolution of enthesitis based on Leeds Enthesitis Index was higher with secukinumab vs placebo (33.3% vs 23.5%; OR = 1.65; 95% CI: 0.85, 3.25) at week 24. Mean change from baseline in heel pain at week 24 was higher in secukinumab patients vs placebo (−2.8 [3.0] vs −1.9 [2.7]). Greater improvements with secukinumab were observed in heel enthesopathy activity and global assessment of disease activity. Imaging evaluation by local reading confirmed heel enthesitis on MRI at screening for all patients. Based on central reading, 56% presented with bone marrow oedema and/or tendinitis; according to Heel Enthesitis MRI Scoring System (HEMRIS) post hoc analysis, 76% had signs of entheseal inflammation while 86% had entheseal inflammation and/or structural changes. Conclusion A substantial proportion of patients showed no signs of inflammation on the centrally read MRIs despite a clinical diagnosis of heel enthesitis, thus highlighting that the discrepancy between the clinical and imaging assessments of enthesitis requires further investigation. Although ACHILLES did not meet the primary end point, the study reported clinically meaningful improvements in patient-related outcomes. Trial registration clinicaltrials.gov, NCT02771210 [ABSTRACT FROM AUTHOR]