A 3D Hand Attitude Estimation Method for Fixed Hand Posture Based on Dual-View RGB Images.

This work provides a 3D hand attitude estimation approach for fixed hand posture based on a CNN and LightGBM for dual-view RGB images to facilitate the application of hand posture teleoperation. First, using dual-view cameras and an IMU sensor, we provide a simple method for building 3D hand posture datasets. This method can quickly acquire dual-view 2D hand image sets and automatically append the appropriate three-axis attitude angle labels. Then, combining ensemble learning, which has strong regression fitting capabilities, with deep learning, which has excellent automatic feature extraction capabilities, we present an integrated hand attitude CNN regression model. This model uses a Bayesian optimization based LightGBM in the ensemble learning algorithm to produce 3D hand attitude regression and two CNNs to extract dual-view hand image features. Finally, a mapping from dual-view 2D images to 3D hand attitude angles is established using a training approach for feature integration, and a comparative experiment is run on the test set. The results of the experiments demonstrate that the suggested method may successfully solve the hand self-occlusion issue and accomplish 3D hand attitude estimation using only two normal RGB cameras.

Experimental study on the accuracy of non-invasive temperature measurement by magnetic resonance in microwave ablation.

Aims: This study aimed to explore the accuracy of non-invasive temperature measurement based on proton resonance frequency (PRF) phase subtraction in microwave ablation (MWA). Methods and Material: The signal change of the agar phantom during the ablation process was monitored by the gradient echo sequence under 1.5 T superconducting magnetic resonance imagining (MRI), and the temperature change was converted by the phase subtraction method of the PRF, which was compared with the temperature measured using an optical fiber. Statistical Analysis Used: SPSS software version 22.0 was used for data processing, and the independent sample t-test was used for comparative analysis. P < 0.05 indicated statistical significance. Results: The maximum error between the MRI temperature measurement and the standard value was 3.61°C, whereas the minimum and average errors were 0.01°C and 1.19°C ± 0.78°C, respectively. Conclusions: The temperature measurement technology, which is based on the PRF phase method, has good accuracy in MRI-guided MWA.

Long noncoding RNA MALAT1 and its target microRNA-125b are potential biomarkers for Alzheimer's disease management via interactions with FOXQ1, PTGS2 and CDK5.

This study aimed to investigate the intercorrelation among long noncoding RNA MALAT1 (lnc-MALAT1), microRNA-125b (miR-125b), FOXQ1, PTGS2 and CDK5, as well as their correlations with disease risk, severity and progression of Alzheimer's disease (AD). In total, 120 AD patients, 120 Parkinson's disease (PD) patients and 120 controls were enrolled. Cerebrospinal fluid (CSF) samples were collected from 50 AD patients, 50 PD patients and 50 controls; plasma samples were obtained from all participants. Lnc-MALAT1, miR-125b, FOXQ1, PTGS2 and CDK5 were detected by RT-qPCR. CSF lnc-MALAT1/FOXQ1 and plasma lnc-MALAT1 were downregulated, while CSF miR-125b/PTGS2/CDK5 and plasma miR-125b/PTGS2 were upregulated in AD patients compared to PD patients and controls, which differentiated AD patients from PD patients and controls, as demonstrated by ROC curve analyses. In AD patients, CSF/plasma lnc-MALAT1 negatively correlated with miR-125b and PTGS2 but positively correlated with FOXQ1; CSF/plasma miR-125b negatively correlated with FOXQ1 but positively correlated with PTGS2/CDK5. In addition, CSF/plasma lnc-MALAT1 and FOXQ1 correlated with alleviated disease severity, while miR-125b, PTGS2 and CDK5 correlated with exacerbated disease severity, which were manifested by their correlations with MMSE score, Aß42, t-tau and p-tau in AD patients. However, their correlations with MMSE score, Aß42, t-tau and p-tau were weak in PD patients and controls. Notably, CSF but not plasma lnc-MALAT1 and miR-125b could predict the MMSE score decline at 1 year, 2 years and 3 years in AD patients. In conclusion, lnc-MALAT1 and its target miR-125b are potential biomarkers for AD management via their intercorrelation with FOXQ1, PTGS2 and CDK5.