Level Fusion Research Articles

Bioactive peptides PDBSN improve mitochondrial function and suppression the oxidative stress in human adiposity cells

ABSTRACT Introduction: Mitochondria are essential for generating cellular energy and are significant in the pathogenesis of obesity. Peptide PDBSN has been demonstrated to inhibit the adipogenic differentiation of adipocytes in vitro and improves metabolic homoeostasis in vivo. Therefore, in this study, we further investigated the effects of PDBSN on the morphology, synthesis, and function of adipocyte mitochondria. Methods: Human visceral and subcutaneous primary preadipocytes (HPA-v and HPA-s) were cultured into mature adipocytes. Intracellular triglyceride content was assessed using oil-red O staining and tissue triglyceride determination. Gene and protein levels associated with mitochondrial synthesis were detected using real-time quantitative polymerase chain reaction and western blotting. Mitochondrial membrane potentials and ROS were detected using fluorescent indicators. Morphological changes were observed by electron microscopy. Results: PDBSN significantly increased mitochondrial membrane potential (MMP), while decreasing intracellular triglyceride (TG) and intracellular reactive oxygen species (ROS) levels. On the other hand, the transcription and protein levels of genetic marker genes PGC1-α and MTFA were significantly up-regulated after PDBSN administration. Further studies showed that transcriptional and protein levels of mitochondrial fusion and fission genetic markers MFN1, MFN2, NRF1, and DRP1 increased. Conclusion: PDBSN significantly reduces intracellular TG and ROS levels and increases MMP. The maximum respiratory capacity in adults significantly increases after PDBSN administration, and ROS levels are significantly reduced. This suggests that PDBSN improves mitochondrial function to some extent, which not only provides an essential basis for the pathophysiology of obesity but also provides insights for the development of new drugs to treat obesity and metabolic diseases.

Cannabis use Disorder and Complications After Anterior Cervical Diskectomy and Fusion

The aim of this study, a retrospective database analysis, was to assess the impact of baseline cannabis use disorder (CUD) on perioperative complication outcomes in patients undergoing primary 1- to 2-level anterior cervical diskectomy and fusion (ACDF) surgery. The PearlDiver Database was queried from January 2010 to December 2021 for patients who underwent primary 1- to 2-level ACDF surgery for degenerative spine disease. Patients with CUD diagnosis 6 months before the index ACDF surgery (i.e., CUD) were propensity matched with patients without CUD (i.e., control in a ratio of 1:1, employing age, gender, and Charlson Comorbidity Index as matching covariates). Univariate and multivariable analysis models with adjustment of confounding variables were used to evaluate the risk of CUD on perioperative complications between the propensity-matched cohorts. The 1:1 matched cohort included 838 patients in each group. Following multivariate analysis, CUD was demonstrated to be associated with an increased incidence of hospital readmission at 90 days (odds ratio [OR]= 2.64, 95% confidence interval: [1.19 to 6.78], [P= 0.027]) and revision surgery at 1 year postoperative (OR= 3.36, 95% confidence interval: [1.17 to 14.18], [P= 0.049]). CUD was additionally associated with reduced risk of overall medical complications at both 6 months and 1 year postoperative (OR= 0.55, [P= 0.021], and OR= 0.54, [P= 0.015], respectively). These findings indicate that isolated baseline CUD is associated with an increased risk of hospital readmission at 90 days postoperative and cervical spine reoperation at 1 year after primary 1- to 2-level ACDF surgery with a decrease in overall medical complications, cardiac arrhythmias, and acute renal failure.

An ensembled remaining useful life prediction method with data fusion and stage division

The remaining useful life (RUL) prediction method based on multi-sensor vibration data is a significant component of predictive maintenance for rolling bearings. However, during the fusion process, it is easy to overlook the consistency of multi-sensor vibration data and cannot adaptively divide degradation stages, resulting in a decrease in the accuracy of the prediction method and limits its applicability in industrial settings. Therefore, this article proposes an integrated prediction method for the RUL of rolling bearings based on data fusion and stage division. Firstly, a data-level fusion method based on multi-sensor vibration signals (MSDF) is proposed. This method dynamically weights sensor data, aiming to consider consistency and reliability in order to achieve data level fusion for multi-sensor vibration signals. Secondly, a stage division method is proposed, which adaptively divides the degradation process into three stages to guide data fusion and ensemble prediction results. Finally, the feature complementarity based ensemble prediction (TCEP) model is proposed to enhance prediction accuracy by learning the degradation difference information of features throughout the prediction process. Furthermore, the outstanding performance of the proposed method was validated using two sets of bearing lifetime vibration signal datasets.

The effect of spinal range of motion on functional balance, quality of life, and perception of appearance in adolescent idiopathic scoliosis after posterior spinal fusion surgery.

Spinal fusion, which is widely used in the surgical treatment of adolescent idiopathic scoliosis (AIS), limits the movements of the vertebral column. In this study, it was aimed to investigate the relationship between spinal mobility in the postoperative period with functional balance, quality of life, and perception of appearance in individuals with AIS. Thirty patients with AIS who underwent posterior spinal fusion surgery 1 to 3years ago were included in the study. A universal goniometer was used to measure a spinal range of motion (ROM), functional reach test for functional balance, Scoliosis Research Society-30 (SRS-30) for quality of life, and Spinal Appearance Questionnaire (SAQ) for perception of appearance. Surgical fusion length was significantly correlated with movements in the sagittal and transverse planes (r = - 0.383-[- 0.608]; p = < 0.001-0.037). Except for spinal left rotation, there was a significant positive correlation between functional balance level and ROM results (r = 0.374-0.523; p = 0.003-0.42). The SRS-30 total score correlated significantly with all other ROM measures except for rotations (r = 0.434-0.574; p = 0.00-0.016). SAQ total data correlated significantly with all ROM measurements (r = - 0.553-[- 0.395]; p = 0.002-0.031). In AIS, limitation of movement in the coronal, sagittal, and transverse planes is observed after fusion surgery. Spinal ROM is affected by the level of fusion performed at surgery. Postoperative spinal limitation of motion adversely affected functional balance, quality of life, and perception of appearance. We believe that comprehensive rehabilitation approaches that improve postoperative range of motion and increase functionality are important for optimal postoperative recovery.

Multimodal fusion diagnosis of Alzheimer’s disease based on FDG-PET generation

Alzheimer’s disease (AD) is a central nervous system disease that mainly appears in the aged. Early diagnosis of AD is valuable in delaying the progression of the disease. With the development of medical imaging technology, various medical images such as structural Magnetic Resonance Imaging (sMRI) and Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) can obtain the structural and functional lesions of the brain to assist in diagnosing diseases. However, FDG-PET is usually incomplete due to radiation and high costs. Most existing methods exclude missing modal subjects, which is remarkably one-sided. Meanwhile, how to extract the features of different levels of multimodal fusion is still a challenge. To solve these issues, we propose a Consistent Manifold Projection Generative Adversarial Network (CMPGAN) for FDG-PET generation and a Multilevel Multimodal Fusion Diagnosis Network (MMFDN) for diagnosing AD. First, we propose a CMPGAN model to project the distribution onto low-dimensional manifolds through consistent manifold projection, and present a distribution distance metric to optimize the model. Our proposed model can avoid problems of mode collapse and gradient disappearance. Then, we construct a multiscale feature-level feature extraction network based on our proposed radial medley unit and a voxel-level feature extraction network based on a harmonic voxel fusion matrix. The fusion of the two parts obtains the final diagnosis result. Experimental results indicate that our proposed method performs better than state-of-the-art methods in FDG-PET generation and AD diagnosis. Our approach also has the significance of guiding clinicians in diagnosing diseases.

Abstract 17943: Biomechanical Finite Element Analysis of Asymmetric Bicuspid Aortic Valve With Different Commissure Positionings for Repair

Introduction: While bicuspid aortic valves (BAVs) exist with a wide variety of phenotypes, type 1 valves that require surgery often present with varying levels of cusp fusion, raphe geometry, and commissure positioning angles. Regarding central coaptation angle, BAVs commonly present with asymmetry between fused and non-fused cusps, and surgical debate focuses on whether BAV repair should aim to minimize or accommodate for this asymmetry. We aimed to compare the hemostatic structural integrity of different commissure positionings for repair based on a BAV with an original 150° central angle. Methods: BAV models were designed based on literature of asymmetric valve geometry. The central angle of the pathological valve was 150°, which is common (Fig A). Two subsequent valve geometries were modeled to represent the repair conditions where commissure positioning forces result in central angles of 165° (Fig B) and 180° (Fig C). These models were matched with leaflet surface area and implemented with mechanical parameters of aortic leaflet tissues. Coaptation planes were modeled as encastre boundaries. A hemostatic pressure gradient was applied at 90 mmHg to mimic peak diastolic pressures, and Fusion360 was used for finite element simulations. Results: All three models showed maximum von Mises stresses in the belly regions of the fused leaflet (Fig A-C). Upon running the simulations, the 150° model showed maximum Von Mises stresses of 8103 Pa, the 165° model showed maximum stresses of 5405 Pa, and the 180° model showed stresses of 6116 Pa. Conclusions: By leveraging finite element models and computational biomechanics analyses, we were able to identify differences in BAV leaflet stresses based on alternate commissural positioning of an asymmetric BAV phenotype. Our finding suggests that peak diastolic leaflet forces may be minimized by focusing surgical BAV repair on a moderate reduction of leaflet asymmetry (i.e., 150° to 165°), without imposing perfect symmetry.

Dual mode information fusion with pre-trained CNN models and transformer for video-based non-invasive anaemia detection

Anaemia, caused by low haemoglobin levels, affects billions of people worldwide. India has one of the highest anaemia rates among developing nations, according to WHO data. Non-invasive, low-cost, and accurate anaemia screening technologies are in high demand because invasive methods are expensive and difficult to administer globally. The current effort aims to construct a reliable anaemia detection system by combining cutting-edge computational methods with the age-old practise of imprecise assessment of haemoglobin levels from pallor in palm. The proposed method utilises time-domain analysis to establish the connection between blood haemoglobin concentration and colour changes in the palm caused by pressure application and release. A smartphone camera sensor which records the full event of palm colour changes generated by a customised device is processed and analysed. Some key frames are selected from extracted frames and passed to the pre-trained deep learning models for feature extractions. These features are then passed through vision transformers for classification and regression tasks. This approach have the power of pre-trained models for feature extraction and utilises the flexibility of transformer encoders and MLP networks for efficient and effective representation learning, classification, and regression. Two different approaches are proposed i.e., decision level and feature level fusion. The suggested approach accurately estimates blood haemoglobin levels with RMSE and accuracy of 0.483 and 96.296%, respectively based on 531 video samples of palm evidence.

Validation of age-adjusted pelvic incidence minus lumbar lordosis and lordosis distribution index for assessing adjacent-segment disease after short-level lumbar fusion surgery: minimum 5 years of follow-up.

The purpose of this study was to investigate the influence of sagittal alignment according to age-adjusted pelvic incidence minus lumbar lordosis (PI-LL) and lordosis distribution index (LDI) on the occurrence of adjacent-segment disease (ASD) after lumbar fusion surgery. This study retrospectively reviewed 234 consecutive patients with lumbar degenerative diseases who underwent 1- or 2-level lumbar fusion surgery. Demographic and radiographic (preoperative and 3-month postoperative) data were collected and compared between ASD and non-ASD groups. Binary logistic regression analysis was performed to evaluate adjusted associations between potential variables and ASD development. A subanalysis was further conducted to assess their relationships in the range of different PI values. With a mean follow-up duration of 70.6 months (range 60-121 months), 118 patients (50.4%) were diagnosed as having cranial radiological ASD. Univariate analyses showed that older age, 2-level fusion, worse preoperative pelvic tilt and LL, lower pre- and postoperative LDI, and more improvement in sagittal vertical axis were significantly correlated with the occurrence of ASD. No significant differences in the PI-LL and age-adjusted PI-LL (offset) were detected between ASD and non-ASD groups. Multivariate analysis identified postoperative LDI (OR 0.971, 95% CI 0.953-0.989, p = 0.002); 2-level fusion (OR 3.477, 95% CI 1.964-6.157, p < 0.001); and improvement of sagittal vertical axis (OR 0.992, 95% CI 0.985-0.998, p = 0.039) as the independent variables for predicting the occurrence of ASD. When stratified by PI, LDI was identified as an independent risk factor in the groups with low and average PI. Lower segmental lordosis (OR 0.841, 95% CI 0.742-0.954, p = 0.007) could significantly increase the incidence of ASD in the patients with high LDI. Age-adjusted PI-LL may have limited ability to predict the development of ASD. LDI could exert an important effect on diagnosing the occurrence of ASD in the cases with low and average PI, but segmental lordosis was a more significant risk factor than LDI in individuals with high PI.

The integration of vocal music teaching and traditional music culture in colleges and universities with a full media perspective

Abstract The first part of this paper examines the classification of traditional music culture and the method of integrating it with modern vocal teaching. Then, the association rule algorithm was used to establish the calculation model of integrating college vocal teaching and traditional music culture, and the weighted MINWAL algorithm improved the model. Finally, the degree of integration and the effect of integration between college vocal music teaching and traditional music culture were analyzed using indicators of integration degree, value, and acceptance. The fusion levels of singing style, voice, tune melody, lyrics, performance technique and dynamics were 4, 3.5, 4.3, 4.4, 4.1 and 3.9, respectively. The fusion level regarding teaching content was 4.1, and the fusion level in terms of practical activities was 4.0. A teaching strategy that is feasible and effective and has promotion value is the combination of college vocal music teaching and traditional music culture.

Comparison between 3-level and 4-level anterior cervical discectomy and fusion in the treatment of cervical spondylotic myelopathy: A meta-analysis

ObjectiveOur objective is to estimate the clinical effectiveness of 3-level and 4-level anterior cervical discectomy and fusion (ACDF) in the management of cervical spondylotic myelopathy (CSM). MethodsWe conducted a thorough search in English databases. We gathered the data on surgical variables and complications to contrast the clinical effectiveness between 3-level and 4-level. We utilized RevMan 5.3 and STATA 12.0 to analyze the data. ResultsFinally, eight studies met inclusion criteria of this study. Our findings indicated that operation time [p for heterogeneity = 0.23, I2 = 32 %, p＜0.00001, OR = −24.93, 95%CI (−32.39,-17.49)], blood loss [p for heterogeneity = 0.33, I2 = 10 %, p＜0.00001, OR = −60.87, 95%CI (−85.43,-36.32)] and the total number of complications [p for heterogeneity = 0.36, I2 = 0 %, p = 0.004, OR = 0.37, 95%CI (0.18,0.72)] in 3-level ACDF were significantly less than in 4-level ACDF. No marked difference was found in hospital stay, revision rate, fusion rate, the number of readmissions, infection, hematoma, or pseudarthrosis between 3-level and 4-level ACDF. ConclusionsIt is easy to understand that performing 4-level needs more operation time and blood loss. No obvious discrepancy was found with regard to the subgroups of complications between the two procedures, yet 4-level procedures had a more number of complications.

Incidence of postoperative neurological deficit with the use of an intraoperative neuromonitoring protocol for lateral lumbar interbody fusion.

Intraoperative neuromonitoring (IONM) has become commonplace in assessing neurological integrity during lateral approaches to lumbar interbody fusion surgeries. Neuromonitoring is designed to aid surgeons in identifying the potential for intraoperative nerve injury and reducing associated postoperative complications. However, standardized protocols for neuromonitoring have not been provided, and outcomes are not well described. The purpose of this study was to provide a standardized protocol for IONM, and to describe clinical outcomes in a cohort of individuals who underwent lateral lumbar interbody fusion (LLIF) surgery. A retrospective review of 169 consecutive patients who underwent LLIF surgery at a single institution from October 2014 to October 2016 was performed. Patient characteristics, intraoperative details, clinical outcomes, and postoperative deficits (PODs) were compared between patients who did and did not trigger IONM alerts, and between patients who did and did not demonstrate a POD. A protocol for IONM decision-making was generated based on these observations. Most patients (91.7%) underwent surgery for a degenerative spine condition. Twenty-three patients (13.6%) triggered neuromonitoring alerts, and 16 patients (9.5%) demonstrated a POD. Leg pain, back pain, and disability improved significantly (p < 0.045), and 2 patients had both motor and sensory deficits at the 12-week postoperative time point. Patients with a POD demonstrated greater operating room time (p = 0.034) and a greater number of interbody fusion levels (p = 0.015) but were less likely to have triggered a neuromonitoring alert (p = 0.04). There was no association between retractor time and POD (p = 0.98). When an IONM protocol was followed, individuals who experienced a POD were less likely to trigger an alert than those who did not experience a POD (p = 0.04). This study provides a protocol algorithm for IONM alert responses in patients undergoing LLIF surgery. PODs are most associated with multilevel fusion, and patients with alerts had a low rate of persistent deficit. Future research is needed to validate these findings using a more rigorous comparative study design.

MuA-SAR Fast Imaging Based on UCFFBP Algorithm with Multi-Level Regional Attention Strategy

Multistatic airborne SAR (MuA-SAR) benefits from the ability to flexibly adjust the positions of multiple transmitters and receivers in space, which can shorten the synthetic aperture time to achieve the required resolution. To ensure both imaging efficiency and quality of different system spatial configurations and trajectories, the fast factorized back projection (FFBP) algorithm is proposed. However, if the FFBP algorithm based on polar coordinates is directly applied to the MuA-SAR system, the interpolation in the recursive fusion process will bring the problem of redundant calculations and error accumulation, leading to a sharp decrease in imaging efficiency and quality. In this paper, a unified Cartesian fast factorized back projection (UCFFBP) algorithm with a multi-level regional attention strategy is proposed for MuA-SAR fast imaging. First, a global Cartesian coordinate system (GCCS) is established. Through designing the rotation mapping matrix and phase compensation factor, data from different bistatic radar pairs can be processed coherently and efficiently. In addition, a multi-level regional attention strategy based on maximally stable extremal regions (MSER) is proposed. In the recursive fusion process, only the suspected target regions are paid more attention and segmented for coherent fusion at each fusion level, which further improves efficiency. The proposed UCFFBP algorithm ensures both the quality and efficiency of MuA-SAR imaging. Simulation experiments verified the effectiveness of the proposed algorithm.

Surgeon Preferences Worldwide in Wound Drain Utilization in Open Lumbar Fusion Surgery for Degenerative Pathologies.

Cross-sectional survey. Although literature does not recommend routine wound drain utilization, there is a disconnect between the evidence and clinical practice. This study aims to explore into this controversy and analyze the surgeon preferences related to drain utilization, and the factors influencing drain use and criterion for removal. A survey was distributed to AO Spine members worldwide. Surgeon demographics and factors related to peri-operative drain use in 1 or 2-level open fusion surgery for lumbar degenerative pathologies were collected. Multivariate analyses by drain utilization, and criterion of removal were conducted. 231 surgeons participated, including 220 males (95.2%), orthopedics (178, 77.1%), and academic/university-affiliated (114, 49.4%). Most surgeons preferred drain use (186, 80.5%) and subfascial drains (169, 73.2%). Drains were removed based on duration by 52.87% of the surgeons, but 27.7% removed drains based on outputs. On multivariable analysis, significant predictors of drain use were surgeon's aged 35-44 (OR = 11.9, 95% CI = 1.2-117.2, P = .034), 45-54 (29.1, 3.1-269.6, P = .003), 55-64 (8.9, 1.4-56.5, .019), and wound closure using coaptive films (6.0, 1.2-29.0, P = .025). Additionally, surgeons from Asia Pacific (OR = 5.19, 95% CI = 1.65-16.38, P = .005), Europe (3.55, 1.22-10.31, P = .020), and Latin America (4.40, 1.09-17.83, .038) were more likely to remove drain based on time duration, but surgeons <5years of experience (10.23, 1.75-59.71, P = .010) were more likely to remove drains based on outputs. Most spine surgeons worldwide prefer to place a subfascial wound drain for degenerative open lumbar surgery. The choice for drain placement is associated with the surgeon's age and use of coaptive films for wound closure, while the criterion for drain removal is associated with the surgeons' region of practice and experience.

ConCs-Fusion: A Context Clustering-Based Radar and Camera Fusion for Three-Dimensional Object Detection

Multi-modality three-dimensional (3D) object detection is a crucial technology for the safe and effective operation of environment perception systems in autonomous driving. In this study, we propose a method called context clustering-based radar and camera fusion for 3D object detection (ConCs-Fusion) that combines radar and camera sensors at the intermediate fusion level to achieve 3D object detection. We extract features from heterogeneous sensors and input them as feature point sets into the fusion module. Within the fusion module, we utilize context cluster blocks to learn multi-scale features of radar point clouds and images, followed by upsampling and fusion of the feature maps. Then, we leverage a multi-layer perceptron to nonlinearly represent the fused features, reducing the feature dimensionality to improve model inference speed. Within the context cluster block, we aggregate feature points of the same object from different sensors into one cluster based on their similarity. All feature points within the same cluster are then fused into a radar–camera feature fusion point, which is self-adaptively reassigned to the originally extracted feature points from a simplex sensor. Compared to previous methods that only utilize radar as an auxiliary sensor to camera, or vice versa, the ConCs-Fusion method achieves a bidirectional cross-modal fusion between radar and camera. Finally, our extensive experiments on the nuScenes dataset demonstrate that ConCs-Fusion outperforms other methods in terms of 3D object detection performance.

Post-operative C-reactive protein and white blood cells changes pattern following spinal deformity surgery and its clinical correlation

ObjectiveFollowing the changing pattern of post-operative CRP and WBC counts and compare them to the patient’s clinical condition to find which one is better for early detection of early infection.MethodsA total of 50 patients who underwent spinal deformity correction surgery without clinical signs of infection such as fever, wound redness, or discharge were enrolled in this prospective study. The C-reactive protein (CRP) and white blood cell (WBC) counts were measured the 2nd and 7th post-operative days. We try to detect the type of correlation between both CRP and WBCs level and clinical condition of patient regarding wound local condition.ResultsAll cases showed high CRP by the 2nd day post-operative which decreased significantly but not reaching normal levels even by the 7th day. All cases showed elevated WBCs count by the 2nd day which decreased to normal levels by the 3rd day in 86% of patients, and by the 7th day, 94% of cases showed normal levels. In addition, WBCs in the 2nd day post-operative significantly positive correlated with fusion level and operative time. There was no significant correlation between WBCs and blood transfusion or age. No significant correlation between CRP and number of fusion levels, blood transfusion nor operative time.ConclusionWBCs count returned earlier to normal levels than CRP in our cases, so monitoring early changes in the 1st week in WBCs count pattern is more indicative of an ongoing infectious process.

Anterior lumbar interbody fusion (ALIF): a review of the procedure and associated complications

Degenerative disc disease and facet joint disease involving the lumbar spine are common in the aging population and are the most frequent causes of disability. Surgical interbody fusion of degenerative levels is the most common management technique. This is an effective treatment option to stabilize the spine and reduce mechanical pain and provides indirect decompression of the neural elements while restoring lordosis and correcting the deformity. Depending on the direction of the approach to the vertebral column, various techniques have been described. Anterior lumbar interbody fusion (ALIF) offers clear and wide visualization of the disc allowing the use of large interbody grafts, which provide a significant biomechanical advantage over other types of fusion. The transperitoneal approach is a much older technique and it is not commonly performed unless in isolated cases with extensive retroperitoneal scaring following multiple abdominal surgeries. The transperitoneal approach has been associated with higher rates of bowel injury, ileus, and retrograde ejaculation, and is limited at the L5–S1 segment, hence many spine surgeons favor a retroperitoneal approach. The major setback of ALIF is the need for great vessel mobilization. This manipulation of the vessels may lead to deep vein thrombosis and a direct vascular injury. This makes vascular anatomy studies in the preoperative stage invaluable in avoiding vascular injury. Other complications include possible injury to intraperitoneal and retroperitoneal organs, especially in patients with previous surgery and adhesions. Manipulation of the intestines causes postoperative ileus which lasts a few days. Sexual dysfunction in form of retrograde ejaculation is another complication seen in patients following ALIF and this has been attributed to injury to the superior hypogastric sympathetic nerves in the lower lumbar region.This article reviews the ALIF procedure i. e., transperitoneal and retroperitoneal approaches, and the associated intraoperative, early, and late complications.

A generalized image steganalysis approach via decision level fusion of deep models

A generalized image steganalysis approach via decision level fusion of deep models

Data-driven real-time prediction for attitude and position of super-large diameter shield using a hybrid deep learning approach

The presented research introduces a novel hybrid deep learning approach for the dynamic prediction of the attitude and position of super-large diameter shields - a critical consideration for construction safety and tunnel lining quality. This study proposes a hybrid deep learning approach for predicting dynamic attitude and position prediction of super-large diameter shield. The approach consists of principal component analysis (PCA) and temporal convolutional network (TCN). The former is used for employing feature level fusion based on features of the shield data to reduce uncertainty, improve accuracy and the data effect, and 9 sets of required principal component characteristic data are obtained. The latter is adopted to process sequence data in predicting the dynamic attitude and position for the advantages and potential of convolution network. The approach’s effectiveness is exemplified using data from a tunnel construction project in China. The obtained results show remarkable accuracy in predicting the global attitude and position, with an average error ratio of less than 2 mm on four shield outputs in 97.30% of cases. Moreover, the approach displays strong performance in accurately predicting sudden fluctuations in shield attitude and position, with an average prediction accuracy of 89.68%. The proposed hybrid model demonstrates superiority over TCN, long short-term memory (LSTM), and recurrent neural network (RNN) in multiple indexes. Shapley additive exPlanations (SHAP) analysis is also performed to investigate the significance of different data features in the prediction process. This study provides a real-time warning for the shield driver to adjust the attitude and position of super-large diameter shields.

Symptoms of sacral fractures after posterior spinal instrumented fusion: A case series

BackgroundImprovements in spinal fusion devices and techniques have enabled stronger spinal fusion, resulting in excellent clinical outcomes. Nevertheless, complications associated with implants, such as screw misalignment, screw lubrication, cage dislocation, and skin issues, might occur. This study aimed to investigate the characteristics and symptoms of sacral fractures after spinal instrumented fusion. MethodsThis case series retrospectively examined the medical records of eight patients (one man and seven women; mean age: 74 years) diagnosed with sacral fractures after undergoing posterior spinal instrumented fusion from February 2015 to March 2022. ResultsThe average number of fusion levels in all patients was 3.5 (range, 1–10). The lowest instrumented vertebrae (LIV) ranged from L5 to the ilium. Sacral fractures were diagnosed at 18.8 (range, 0.5–84) months postoperatively. The average time from consultation to diagnosis was nine days (range, 0–25 days). Two patients had subclinical fractures, two had H-shaped fractures with the LIV at L5, and four had U-shaped fractures, including screw holes. Buttock pain and lower extremity pain, the most commonly reported symptoms, were observed in seven patients each. There were also instances of leg numbness, muscle weakness, and unilateral leg pain that may be related to L5 or S1 radiculopathy. In all patients, leg and buttock pain were worse during movement and in the sitting position, and better while resting and in the supine position. Three patients were treated conservatively, and five were treated with extended fixation to the ilium. ConclusionsSacral fractures following posterior spinal fusion can cause radiculopathy and buttock pain. Symptoms are especially severe when instability occurs in the pelvic region, such as during movements or sitting. As atypical radiculopathy may lead to delays in diagnosis, spine surgeons should recognize the symptoms of this condition.

Wind Turbine Surface Defect Detection Method Based on YOLOv5s-L

In order to solve the problems of low efficiency, time consumption and high costs in the detection of defects on wind turbine surfaces in industrial scenarios, an improved YOLOv5 algorithm for wind turbine surface defect detection is proposed, named YOLOv5s-L. Firstly, the C3 module of YOLOv5s is replaced with the C2f module, which is more abundant in gradient flow, to enhance the ability of feature extraction and feature fusion. Secondly, the Squeeze and Excitation (SE) module is embedded in the YOLOv5 Backbone network to filter out redundant feature information and retain important feature information. Thirdly, the weighted Bidirectional Feature Pyramid Network (BiFPN) is introduced to replace the FPN + PAN, which can achieve a higher level of feature fusion while keeping the weight light. Finally, the Focal Loss function is used to replace the CIOU Loss function of the YOLOv5 algorithm to optimize the training model and improve the accuracy of the algorithm. The experimental results show that, compared with the traditional YOLOv5 algorithm, the average precision mAP is improved by 1.9%, and the frame rate FPS can reach 145 F/s without increasing the model parameters; it can satisfy the requirements for real-time, accurate detection on mobile devices. This method provides effective support for surface defect detection of wind turbines and provides reference for intelligent wind farm operation and maintenance.