ABSTRACT
Propofol sedation, routinely used for endoscopic procedures, is safe and acceptable for children. Adjuvants, such as esketamine or sufentanil, are commonly added to improve the efficacy and safety of propofol sedation. This study aimed to compare the clinical efficacy and safety of propofol-esketamine (PE) versus propofol-sufentanil (PS) for deep sedation and analgesia in children with autism undergoing colonoscopy procedure. One hundred and twenty-four children with autism undergoing colonoscopy procedure were included in the study. Patients were randomly assigned to receive one of the two adjuvants: esketamine (0.3 mg/kg) or sufentanil (0.2 µg/kg), subsequently administered propofol 2.0 mg/kg to induce anesthesia. Additional doses of propofol (0.5-1.0 mg/kg) were administered as needed to ensure patient tolerance for the remaining duration of the procedure. Movement during the procedure, hemodynamic variables, the total dose of propofol, recovery time, and adverse events were recorded. The PE group exhibited a significantly lower incidence of severe movement during the procedure compared with the PS group (14.52% vs. 32.26%, p = 0.020). The PE group showed significantly lower incidence of respiratory depression, hypotension, and severe injection pain of propofol than the PS group during the procedure (all p < 0.05). The mean arterial pressure (MAP) decreased significantly after anesthesia induction in the PS group and remained lower than baseline (all p < 0.05). Compared with the combination of low-dose sufentanil (0.2 µg/mg) with propofol, the low-dose esketamine (0.3 mg/kg) combined with propofol provided more stable hemodynamics, higher quality of sedation, and fewer adverse events in children with autism undergoing colonoscopy procedure.
ABSTRACT
Inspired by Fechner's law, we propose a Fechner multiscale local descriptor (FMLD) for feature extraction and face recognition. Fechner's law is a well-known law in psychology, which states that a human perception is proportional to the logarithm of the intensity of the corresponding significant differences physical quantity. FMLD uses the significant difference between pixels to simulate the pattern perception of human beings to the changes of surroundings. The first round of feature extraction is performed in two local domains of different sizes to capture the structural features of the facial images, resulting in four facial feature images. In the second round of feature extraction, two binary patterns are used to extract local features on the obtained magnitude and direction feature images, and four corresponding feature maps are output. Finally, all feature maps are fused to form an overall histogram feature. Different from the existing descriptors, the FMLD's magnitude and direction features are not isolated. They are derived from the "perceived intensity", thus there is a close relationship between them, which further facilitates the feature representation. In the experiments, we evaluated the performance of FMLD in multiple face databases and compared it with the leading edge approaches. The results show that the proposed FMLD performs well in recognizing images with illumination, pose, expression and occlusion changes. The results also indicate that the feature images produced by FMLD significantly improve the performance of convolutional neural network (CNN), and the combination of FMLD and CNN exhibits better performance than other advanced descriptors.
ABSTRACT
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.
