METHODS: In this study, we propose a multi-view secondary input residual (MV-SIR) convolutional neural network model for 3D lung nodule segmentation using the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset of chest computed tomography (CT) images. Lung nodule cubes are prepared from the sample CT images. Further, from the axial, coronal, and sagittal perspectives, multi-view patches are generated with randomly selected voxels in the lung nodule cubes as centers. Our model consists of six submodels, which enable learning of 3D lung nodules sliced into three views of features; each submodel extracts voxel heterogeneity and shape heterogeneity features. We convert the segmentation of 3D lung nodules into voxel classification by inputting the multi-view patches into the model and determine whether the voxel points belong to the nodule. The structure of the secondary input residual submodel comprises a residual block followed by a secondary input module. We integrate the six submodels to classify whether voxel points belong to nodules, and then reconstruct the segmentation image.
RESULTS: The results of tests conducted using our model and comparison with other existing CNN models indicate that the MV-SIR model achieves excellent results in the 3D segmentation of pulmonary nodules, with a Dice coefficient of 0.926 and an average surface distance of 0.072.
CONCLUSION: our MV-SIR model can accurately perform 3D segmentation of lung nodules with the same segmentation accuracy as the U-net model.
METHOD: Retrospective study of children with ANE seen at University of Malaya Medical Centre from 2014 to 2019. All clinical details including ANE-severity score (ANE-SS), immunomodulation treatment and neurodevelopmental long-term outcome were collected.
RESULTS: Thirteen patients had ANE and brainstem death occurred in 5. In 10 patients (77%) viruses were isolated contributing to ANE: 8 influenza virus, 1 acute dengue infection, and 1 acute varicella zoster infection. The ANE-SS ranged 2-7: 9 were high risk and 4 were medium risk. Among the 8 survivors; 1 was lost to follow-up. Follow-up duration was 1-6 years (median 2.2). At follow-up among the 4 high-risk ANE-SS: 2 who were in a vegetative state, 1 remained unchanged and 1 improved to severe disability; the other 2 with severe disability improved to moderate and mild disability respectively. At follow-up all 3 medium-risk ANE-SS improved: 2 with severe disability improved to moderate and mild disability respectively, while 1 in a vegetative state improved to severe disability. Early treatment with immunomodulation did not affect outcome.
CONCLUSION: Our ANE series reiterates that ANE is a serious cause of encephalopathy with mortality of 38.5%. All survivors were in a vegetative state or had severe disability at discharge. Most of the survivors made a degree of recovery but good recovery was seen in 2. Follow-up of at least 12 months is recommended for accurate prognostication. Dengue virus infection needs to be considered in dengue endemic areas.
METHODS: A total of 33 sedentary men with metabolic syndrome (age: 46.2 ± 4.6 years; body mass index: 35.4 ± 1.9 kg.m2) were randomly assigned to one of 3 groups: aerobic interval training (n = 12), resistance training (n = 10), or control (n = 11). Participants in the exercise groups completed a 12-week training program, 3 sessions per week, while those in the control group maintained their sedentary lifestyle. The levels of high sensitivity C-reactive protein (hs-CRP), omentin-1, adiponectin, lipid profiles, blood pressure, glucose metabolism, body composition, and peak oxygen uptake (VO2peak) were measured at baseline and after the intervention.
RESULTS: Both aerobic interval training and resistance training significantly improved the levels of omentin-1 and adiponectin, as well as reduced inflammation, as indicated by a decrease in hs-CRP levels. Exercise training also led to significant improvements in lipid profiles, blood pressure, glucose metabolism, and body composition. Specifically, the aerobic interval training group had significantly greater increases in high-density lipoprotein cholesterol and VO2peak, as well as greater reductions in low-density lipoprotein cholesterol, triglycerides, and total cholesterol compared to the resistance training group.
CONCLUSION: Exercise training, particularly aerobic interval training and resistance training, can be an effective non-pharmacological intervention for managing inflammation and improving cardiovascular health in metabolic syndrome patients.
PURPOSE: Due to the high percentage of affected pregnant women, it should be mandatory to evaluate glucose levels during pregnancy and there is a need for a continuous monitoring system.
METHODS: Herein, the investigators modified the interdigitated (di)electrodes (IDE) sensing surface to detect the glucose on covalently immobilized glucose oxidase (GOx) with the graphene. The characterization of graphene and gold nanoparticle (GNP) was performed by high-resolution microscopy.
RESULTS: Sensitivity was found to be 0.06 mg/mL and to enhance the detection, GOx was complexed with GNP. GNP-GOx was improved the sensitive detection twofold from 0.06 to 0.03 mg/mL, and it also displayed higher levels of current changes at all the concentrations of glucose that were tested. High-performance of the above IDE sensing system was attested by the specificity, reproducibility and higher sensitivity detections. Further, the linear regression analysis indicated the limit of detection to be between 0.02 and 0.03 mg/mL.
CONCLUSION: This study demonstrated the potential strategy with nanocomposite for diagnosing gestational diabetes mellitus.