A Deep Learning Tool for Automated Radiographic Measurement of Acetabular Component Inclination and Version After Total Hip Arthroplasty

BackgroundInappropriate acetabular component angular position is believed to increase the risk of hip dislocation after total hip arthroplasty. However, manual measurement of these angles is time consuming and prone to interobserver variability. The purpose of this study was to develop a deep learning tool to automate the measurement of acetabular component angles on postoperative radiographs.MethodsTwo cohorts of 600 anteroposterior (AP) pelvis and 600 cross-table lateral hip postoperative radiographs were used to develop deep learning models to segment the acetabular component and the ischial tuberosities. Cohorts were manually annotated, augmented, and randomly split to train-validation-test data sets on an 8:1:1 basis. Two U-Net convolutional neural network models (one for AP and one for cross-table lateral radiographs) were trained for 50 epochs. Image processing was then deployed to measure the acetabular component angles on the predicted masks for anatomical landmarks. Performance of the tool was tested on 80 AP and 80 cross-table lateral radiographs.ResultsThe convolutional neural network models achieved a mean Dice similarity coefficient of 0.878 and 0.903 on AP and cross-table lateral test data sets, respectively. The mean difference between human-level and machine-level measurements was 1.35° (σ = 1.07°) and 1.39° (σ = 1.27°) for the inclination and anteversion angles, respectively. Differences of 5? or more between human-level and machine-level measurements were observed in less than 2.5% of cases.ConclusionWe developed a highly accurate deep learning tool to automate the measurement of angular position of acetabular components for use in both clinical and research settings.Level of EvidenceIII.     

The effects of natalizumab on inflammatory mediators in multiple sclerosis: prospects for treatment‐sensitive biomarkers

Background: Natalizumab affects systemic cytokine expressions and clinical course in relapsing–remitting multiple sclerosis (RRMS). We analyzed levels of inflammatory cytokines in cerebrospinal fluid (CSF) cells and peripheral blood mononuclear cells (PBMCs), levels of matrix metalloproteinase (MMP)‐9 and osteopontin (OPN) in CSF, and clinical outcome measures in 22 natalizumab‐treated RRMS patients. Methods: mRNA levels of cytokines in cells were detected with real‐time RT‐PCR. Protein levels of OPN and MMP‐9 were measured by ELISA. Results: Natalizumab reduced CSF cell counts (P < 0.0001). Tumor necrosis factor (TNF) and interferon‐γ (IFN‐γ) mRNAs were significantly increased in PBMCs. In contrast, expressions of IFN‐γ and interleukin (IL)‐23 were decreased but IL‐10 increased in the CSF cells. OPN and MMP‐9 were reduced in the CSF. Patients being in remission at baseline showed the same deviations of mediators as those in relapse after natalizumab treatment. The open label clinical outcome measures were either stable or improved during therapy. Conclusions: Natalizumab attenuates pro‐inflammatory mediators intrathecally and the reduced pro‐inflammatory milieu may allow increased production of the anti‐inflammatory mediator IL‐10. The increased systemic cytokines may impede the improvement of certain clinical measures like fatigue. The affected mediators seem to be sensitive to an immune‐modifying treatment which could be used as biomarkers for this therapy.     

The analysis of association between <Emphasis Type="Italic">SNCA</Emphasis>, <Emphasis Type="Italic">HUSEYO</Emphasis> and <Emphasis Type="Italic">CSMD1</Emphasis> gene variants and Parkinson’s disease in Iranian population

Parkinson’s disease (PD) is the second most prevalent neurodegenerative disorder. Both genetic and environmental factors are involved in the etiology of the disease. Many studies have revealed the susceptibility genes and variations for PD which need further confirmation. Here we evaluated the association of variations in SNCA, HUSEYO and CSMD1 genes with PD. A case–control study was conducted with 489 PD patients and 489 healthy controls. DNA was extracted from peripheral blood of all subjects and rs356220 and rs11931074 in SNCA, rs2338971 in HUSEYO and rs12681349 in CSMD1 were genotyped using PCR–RFLP method. The genotypes and allele frequencies were significantly different between case and control groups for rs356220, rs11931074 and rs2338971 but not for rs12681349. We provided further evidence that rs356220 is associated with increased risk of PD supporting previous studies in Caucasian-based and Japanese populations. The association of rs11931074 with decreased risk of PD was also significant. This study revealed the first evidence of the association of rs2338971 with increased risk of PD in the Iranian population. Nevertheless, these findings need further validation via more replication studies.     

Individual and Combined Effects of Environmental Risk Factors for Esophageal Cancer Based on Results From the Golestan Cohort Study

1. Download high-res image (371KB)
2. Download full-size image

     

Epidemiology of upper gastrointestinal cancers in Iran： A Sub site analysis of 761 cases

AIM： To define the sub site distribution of upper gastrointestinal cancers in three provinces of Iran.
METHODS： The study was carried out in three provinces in Iran： Ardabil, Golestan, and Tehran. In Arbabil and Golestan, the data was collected from the sole referral center for gastrointestinal cancers and the local cancer registry. For Tehran province, data from two major private hospitals were used. All gastric and esophageal cancer patients diagnosed during the period from September 2000 and April 2002 were included in the study.
RESULTS： A total of 761 patients with upper gastrointestinal cancers were identified, 314 from Ardabil, 261 from Golestan, and 186 from Tehran. In Tehran, the relative rate of cancer increased from the upper esophagus to the distal stomach. In Golestan, the reverse pattern was observed. In Ardabil, the mid portion （distal esophagus and proximal stomach） was involved most frequently.
CONCLUSION： There were considerable variations in the sub site of upper gastrointestinal cancers in the three provinces studied, We cannot provide any explanation for this variation, Further research aimed at explaining the discrepancies in sub site distribution of upper gastrointestinal cancers may help identify important risk factors.