Level Fusion Research Articles

Vertebral Bone Quality Score as a Predictor of Adjacent Segment Disease After Lumbar Interbody Fusion.

With lumbar spine fusion being one of the most commonly performed spinal surgeries, investigating common complications such as adjacent segment disease (ASD) is a high priority. To the authors' knowledge, there are no previous studies investigating the utility of the preoperative magnetic resonance imaging-based vertebral bone quality (VBQ) score in predicting radiographic and surgical ASD after lumbar spine fusion. We aimed to investigate the predictive factors for radiographic and surgical ASD, focusing on the predictive potential of the VBQ score. A single-center retrospective analysis was conducted of all patients who underwent 1-3 level lumbar or lumbosacral interbody fusion for lumbar spine degenerative disease between 2014 and 2021 with a minimum 12 months of clinical and radiographic follow-up. Demographic data were collected, along with patient medical, and surgical data. Preoperative MRI was assessed in the included patients using the VBQ scoring system to identify whether radiographic ASD or surgical ASD could be predicted. A total of 417 patients were identified (mean age, 59.8 ± 12.4 years; women, 54.0%). Eighty-two (19.7%) patients developed radiographic ASD, and 58 (13.9%) developed surgical ASD. A higher VBQ score was a significant predictor of radiographic ASD in univariate analysis (2.4 ± 0.5 vs 3.3 ± 0.4; P < .001) and multivariate analysis (odds ratio, 1.601; 95% CI, 1.453-1.763; P < .001). For surgical ASD, a significantly higher VBQ score was seen in univariate analysis (2.3 ± 0.5 vs 3.3 ± 0.4; P < .001) and served as an independent risk factor in multivariate analysis (odds ratio, 1.509; 95% CI, 1.324-1.720; P < .001). We also identified preoperative disk bulge and preoperative existence of adjacent segment disk degeneration to be significant predictors of both radiographic and surgical ASD. Furthermore, 3-level fusion was also a significant predictor for surgical ASD. The VBQ scoring system might be a useful adjunct for predicting radiographic and surgical ASD.

Navigation-Assisted One-Staged Posterior Spinal Fusion Using Pedicle Screw Instrumentation in Adolescent Idiopathic Scoliosis-A Case Series.

Background and Objectives: Adolescent idiopathic scoliosis (AIS) is a prevalent three-dimensional spinal disorder, with a multifactorial pathogenesis, including genetics and environmental aspects. Treatment options include non-surgical and surgical treatment. Surgical interventions demonstrate positive outcomes in terms of deformity correction, pain relief, and improvements of the cardiac and pulmonary function. Surgical complications, including excessive blood loss and neurologic deficits, are reported in 2.27-12% of cases. Navigation-assisted techniques, such as the O-arm system, have been a recent focus with enhanced precision. This study aims to evaluate the results and complications of one-stage posterior instrumentation fusion in AIS patients assisted by O-arm navigation. Materials and Methods: This retrospective study assesses 55 patients with AIS (12-28 years) who underwent one-stage posterior instrumentation correction supported by O-arm navigation from June 2016 to August 2023. We examined radiological surgical outcomes (initial correction rate, loss of correction rate, last follow-up correction rate) and complications as major outcomes. The characteristics of the patients, intraoperative blood loss, operation time, number of fusion levels, and screw density were documented. Results: Of 73 patients, 55 met the inclusion criteria. The average age was 16.67 years, with a predominance of females (78.2%). The surgical outcomes demonstrated substantial initial correction (58.88%) and sustained positive radiological impact at the last follow-up (56.56%). Perioperative complications, including major and minor, occurred in 18.18% of the cases. Two patients experienced a major complication. Blood loss (509.46 mL) and operation time (402.13 min) were comparable to the literature ranges. Trend analysis indicated improvements in operation time and blood loss over the study period. Conclusions: O-arm navigation-assisted one-stage posterior instrumentation proves reliable for AIS corrective surgery, achieving significant and sustained positive radiological outcomes, lower correction loss, reduced intraoperative blood loss, and absence of implant-related complications. Despite the challenges, our study demonstrates the efficacy and maturation of this surgical approach.

Comparative analysis of changes in spinal dimensions following different correction methods in adult spinal deformity surgery.

Background: Adult spinal deformity (ASD) surgery has gained popularity, with significant improvements in patient-reported outcomes. Posterior lumbar interbody fusion with multiple grade II osteotomies (PLIF + MOs) and lateral lumbar interbody fusion (LLIF) have been utilized to correct ASD; however, no studies have compared these methods with regard to the pre- and postoperative changes in length and volume of the spinal canal. This study aimed to investigate the 3-dimensional changes in the anterior vertical column length (AVCL), spinal canal length (SCL), and spinal canal volume (SCV) in patients with ASD after surgery, employing LLIF and PLIF + MOs. Methods: This retrospective study examined 44 patients with ASD who underwent surgery between 2010 and 2021 using two corrective surgical methods, LLIF and PLIF + MOs. Radiographic parameters and clinical outcomes were assessed, and three-dimensional models were created from computed tomography images to analyze changes in AVCL, SCL, and SCV. Results: We compared the effects of LLIF and PLIF + MOs on spinal canal dimensions during ASD surgery. LLIF demonstrated an increase in lumbar segment (L1-S1) AVCL and whole spine (T1-S1) SCL by 6.5 ± 8.0mm and 13.8 ± 7.6mm, respectively, compared with PLIF + MOs. However, PLIF + MOs exhibited a reduction in the lengths of the lumbar segment AVCL. Postoperative differences were significant for AVCL (L1-S1), SCL fusion level, and first-standing lumbar lordosis between the groups (p < 0.0001, 0.002, and 0.016, respectively). LLIF significantly increased the SCV at the fusion level and whole spine T1-S1 by 14.5% and 10.6%, respectively, outperforming PLIF + MOs. Despite changes in dimensions, the postoperative Oswestry disability index scores showed no significant difference between the two groups. Conclusions: Our study suggests that LLIF can increase spinal canal space, lumbar lordosis, and anterior column length in the lumbar spinal segment. Knowledge of these variations may be critical for enhancing surgical outcomes and preventing neurological complications.

Complications of the Use Allograft in 1- or 2-Level Anterior Cervical Discectomy and Fusion: A Systematic Review.

Study Design: Systematic literature reviewObjective: To critically analyze the literature and describe the complications associated with the use of allograft in 1- or 2- level anterior cervical discectomy and fusion (ACDF)Methods: A systematic search of PubMed/MEDLINE, EMBASE, and ClinicalTrials.gov databases was conducted for literature published between January 2000 and August 2020 reporting complications associated with the use of allograft in 1- or 2- level ACDF.Results: From 584 potentially relevant citations, 21 met the inclusion criteria (4 randomized controlled trials (RCT), 4 prospective, and 13 retrospective studies). The patient number varied between 26 and 463 in comparative studies (RCT and non-RCT) and between 29 and 345 in non-comparative studies. Fusion rate was reported in 14 studies and ranged between 68.5-100%. The most frequently reported complication was post-operative dysphagia or dysphonia, with incidences ranging between .5% and 14.4%. Revision surgery was the second most reported complication (14 studies) and ranged between 0% and 10.3%. Wound-related complications were reported in 6 studies and ranged between 0% and 22.8%.Conclusion: The overall reporting of complications was low with very few comparative studies. Reported complications with allografts are within the range of other osteobiologics and autografts and in most cases may not attributable to the use of osteobiologics and may be complications of the procedure itself. Comparative studies with a more robust methodology analyzing complications with allograft and other osteobiologics are needed to inform current practice with strong recommendations.

Mental health comorbidities in workers' compensation patients and the effect on pain, disability, quality of life, and return to work after lumbar spine surgery.

The impact of mental health comorbidities on outcomes after lumbar spine surgery in workers' compensation (WC) patients has not been robustly explored. The goal of this study was to examine the impact of mental health comorbidities on pain, disability, quality of life, and return to work after lumbar spine surgery in WC patients. A nationwide, prospective surgical outcomes registry (National Neurosurgery Quality Outcomes Database [N2QOD]) was queried for all patients who underwent 1- to 4-level lumbar decompression and/or fusion from 2012 to 2021. Patients were stratified on the basis of compensation status into non-WC (25,507) and WC (1018) cohorts. Baseline demographic data, perioperative safety data, and patient-reported outcome measures were compared between groups. The WC cohort was further subdivided on the basis of mental health status into patients with anxiety and depression (n = 107) and those without anxiety and depression (n = 911). Propensity matching was used to generate parity between these subgroups, generating 214 patients (107 pairs) for analysis. Perioperative safety, facility utilization, 1-year patient-reported outcomes (back and leg pain, disability, and quality of life), and return to work were measured as a function of WC and mental health comorbidity status. A total of 26,525 patients (25,507 non-WC and 1018 WC) who underwent 1- to 4-level lumbar spine surgery were reviewed. WC patients were younger, healthier (lower American Society of Anesthesiologists class), more likely to be minorities, less educated, and more likely to smoke and had greater baseline back pain, disability, and quality of life compared to non-WC patients. The prevalence of anxiety and depression was similar between groups (11%). WC patients had worse outcomes for all measures and lower rates of return to work compared to non-WC patients. WC patients with anxiety and depression demonstrated even greater disparities in all outcomes. After propensity matching, WC patients with anxiety and depression continued to demonstrate significantly worse outcomes in comparison to WC patients without anxiety and depression. Disparities in outcomes after lumbar spine surgery in WC patients are exacerbated in patients with anxiety and depression. WC patients with mental health comorbidities receive the least benefit from lumbar spine surgery and may represent the most vulnerable subset of patients with spine pathology. Addressing mental health comorbidities preoperatively may represent an opportunity for valuable resource allocation and surgical optimization in the WC population.

Estimation of spectral similarities utilizing segmented regions' probability distribution in the block-optimized pan-sharpened image for material classification.

Pan-sharpening is an image fusion approach that combines the spectral information in multispectral (MS) images with the spatial properties of PAN (Panchromatic) images. This vital technique is used in categorization, detection, and other remote sensing applications. In the first step, the article focuses on increasing the finer spatial details in the MS image with PAN images using two levels of fusion without causing spectral deterioration. The suggested fusion method efficiently utilizes image transformation techniques and spatial domain image fusion methods. The luminance component of MS images typically contains spatial features that are not as detailed as the PAN images. A multiscale transform is applied to the intensity/luminance component and PAN image to introduce features into the intensity component. In the first level of processing, coefficients obtained from the non-subsampled contourlet transform are subjected to particle swarm optimization weighted block-based fusion. The second level of fusion is carried out using the concept of spatial frequency to reduce spectral distortion. Numerous reference and non-reference parameters are used to evaluate the sharpened image's quality. In the next step, the article focuses on designing an evaluation metric for analysing spectral distortion based on the Bhattacharyya coefficient and distance. The Bhattacharyya coefficient and distance are calculated for each segmented region to assess the sharpened images' quality. Spectral degradation analysis using proposed techniques can also be useful for analysing materials in the segmented regions. The research findings demonstrate that the spatial features of fused images obtained from the proposed technique increased with the least spectral degradation.

Analysis of duration of different stages of surgery in posterior spinal fusion (PSF) for adolescent idiopathic scoliosis (AIS) patients: comparison between severe versus non-severe AIS.

Prolonged surgical duration in severe adolescent idiopathic scoliosis (AIS) patients is associated with increased blood loss and perioperative complications. The aim of this study was to compare the duration of each stage of posterior spinal fusion (PSF) in severe AIS (Cobb angle ≥ 90°) with non-severe AIS patients. This analysis will identify the most time-consuming stage of PSF and help surgeons formulate strategies to shorten operative time. Retrospective study whereby 90 AIS patients (Lenke type 2, 3, 4, and 6) who underwent PSF from 2019 to 2023 were recruited. Twenty-five severe AIS patients were categorized in Gp1 and 65 non-severe AIS patientsin Gp2. Propensity score matching (PSM) with one-to-one with nearest neighbor matching (match tolerance 0.05) was performed. Outcomes measured via operation duration of each stage of surgery, blood loss, number of screws, fusion levels and screw density. Twenty-five patients from each group were matched. Total operative time was significantly higher in Gp1 (168.2 ± 30.8 vs. 133.3 ± 24.0min, p < 0.001). The lengthiest stage was screw insertion which took 58.5 ± 13.4min in Gp1 and 44.7 ± 13.7min in Gp2 (p = 0.001). Screw insertion contributed 39.5% of the overall increased surgical duration in Gp1. Intraoperative blood loss (1022.2 ± 412.5 vs. 714.2 ± 206.7mL, p = 0.002), number of screws (17.1 ± 1.5 vs. 15.5 ± 1.1, p < 0.001) and fusion level (13.1 ± 0.9 vs. 12.5 ± 1.0, p = 0.026) were significantly higher in Gp1. Screw insertion was the most time-consuming stage of PSF and was significantly longer in severe AIS. Adjunct technologies such as CT-guided navigation and robotic-assisted navigation should be considered to reduce screw insertion time in severe AIS.

Deep hybrid classification model for leaf disease classification of underground crops

Underground crop leave disease classification is the most significant area in the agriculture sector as they are the significant source of carbohydrates for human food. However, a disease-ridden plant could threaten the availability of food for millions of people. Researchers tried to use computer vision (CV) to develop an image classification algorithm that might warn farmers by clicking the images of plant’s leaves to find if the crop is diseased or not. This work develops anew DHCLDC model for underground crop leave disease classification that considers the plants like cassava, potato and groundnut. Here, preprocessing is done by employing median filter, followed by segmentation using Improved U-net (U-Net with nested convolutional block). Further, the features extracted comprise of color features, shape features and improved multi text on (MT) features. Finally, Hybrid classifier (HC) model is developed for DHCLDC, which comprised CNN and LSTM models. The outputs from HC(CNN + LSTM) are then given for improved score level fusion (SLF) from which final detected e are attained. Finally, simulations are done with 3 datasets to show the betterment of HC (CNN + LSTM) based DHCLDC model. The specificity of HC (CNN + LSTM) is high, at 95.41, compared to DBN, NN, RF, KNN, CNN, LSTM, DCNN, and SVM.

Schisandrin B Alleviates LPS Induced Mitochondrial Damage in C28I2 Cells.

Osteoarthritis is a common joint disease characterized by damage to the joint cartilage that occurs throughout the entire joint tissue. This damage primarily manifests as pain in the affected area. In clinical practice, medication is commonly used to relieve pain, but the treatment's effectiveness is poor and recurrent attacks are likely. Schisandrin B is the most abundant biphenylcyclohexene lignan found in the traditional Chinese medicine Schisandra chinensis, and it possesses various pharmacological effects. This study aims to investigate the protective effect of Schisandrin B on mitochondrial damage in osteoarthritis (C28I2 cells) under an inflammatory environment induced by LPS. Cell proliferation and activity, scratch tests, and LDH release tests are utilized to assess cell growth and migration ability. The immunofluorescence assay was used to detect the expression levels of proliferation and apoptosis proteins. The Western Blot assay was used to detect the expression levels of mitochondrial fusion and division proteins. The JC-1 assay was used to detect changes in mitochondrial membrane potential. The mitochondrial fluorescence probe assay was used to detect mitochondrial activity. Through research, it was found that Schisandrin B promotes the proliferation, growth, and migration of C28I2 cells, reduces apoptosis of C28I2 cells, balances mitochondrial fusion and division, stabilizes mitochondrial membrane potential, and promotes mitochondrial activity in an LPS induced inflammatory environment.

A Space Infrared Dim Target Recognition Algorithm Based on Improved DS Theory and Multi-Dimensional Feature Decision Level Fusion Ensemble Classifier

Space infrared dim target recognition is an important applications of space situational awareness (SSA). Due to the weak observability and lack of geometric texture of the target, it may be unreliable to rely only on grayscale features for recognition. In this paper, an intelligent information decision-level fusion method for target recognition which takes full advantage of the ensemble classifier and Dempster–Shafer (DS) theory is proposed. To deal with the problem that DS produces counterintuitive results when evidence conflicts, a contraction–expansion function is introduced to modify the body of evidence to mitigate conflicts between pieces of evidence. In this method, preprocessing and feature extraction are first performed on the multi-frame dual-band infrared images to obtain the features of the target, which include long-wave radiant intensity, medium–long-wave radiant intensity, temperature, emissivity–area product, micromotion period, and velocity. Then, the radiation intensities are fed to the random convolutional kernel transform (ROCKET) architecture for recognition. For the micromotion period feature, a support vector machine (SVM) classifier is used, and the remaining categories of the features are input into the long short-term memory network (LSTM) for recognition, respectively. The posterior probabilities corresponding to each category, which are the result outputs of each classifier, are constructed using the basic probability assignment (BPA) function of the DS. Finally, the discrimination of the space target category is implemented according to improved DS fusion rules and decision rules. Continuous multi-frame infrared images of six flight scenes are used to evaluate the effectiveness of the proposed method. The experimental results indicate that the recognition accuracy of the proposed method in this paper can reach 93% under the strong noise level (signal-to-noise ratio is 5). Its performance outperforms single-feature recognition and other benchmark algorithms based on DS theory, which demonstrates that the proposed method can effectively enhance the recognition accuracy of space infrared dim targets.

The Modified 5-Factor Frailty Score May Not be Useful in Predicting Complications and Unplanned Readmission After 1-Level or 2-Level Anterior Cervical Decompression and Fusion

Background: The modified frailty index (mFI-5) has been shown to be a reliable risk stratification tool in different spine procedures. Its usefulness to predict complications after 1-level or 2-level anterior cervical decompression and fusion (ACDF) has not been studied extensively. Purpose: We aimed to assess the usefulness of the mFI-5 in 1-level or 2-level ACDF surgery by asking the following questions: (1) Is the mFI-5 a reliable tool to predict complications after 1-level or 2-level ACDF? (2) Is the mFI-5 useful in predicting prolonged hospital stay after 1-level or 2-level ACDF? (3) Is the mFI-5 useful in predicting readmission after 1-level or 2-level ACDF? Methods: We performed a retrospective analysis of the medical records of patients who underwent 1-level or 2-level ACDF at our institution. The mFI-5 was calculated based on the presence of 5 comorbidities: (1) congestive heart failure, (2) diabetes mellitus, (3) chronic obstructive pulmonary disease, (4) partially or totally dependent functional status, and (5) hypertension requiring medication. Patients were classified in 3 groups: not frail (mFI-5 items = 0), pre-frail (mFI-5 items = 1), and frail (mFI-5 items ≥2). Postoperative complications, length of stay, and readmission were recorded. Results: In the 662 patients included (mean age 51.4 ± 10.4 years), surgical and medical complications were not significantly different among groups. Lengths of stay and readmission rates were both significantly higher in the pre-frail group. Conclusion: Our study findings suggest that the mFI-5 might not be reliable to assess preoperative risk after 1-level or 2-level ACDF.

Investigating Determinants of Client Psychotherapy Preference: An Analog Study.

Increased emphasis has been placed on elucidating the contribution of client variables, such as treatment preference, to optimize evidence-based practice. This analog study sought to better understand variables associated with treatment preference using a convenience sample of college students (n = 54) who read brief descriptions of three interventions for negative thoughts-defusion, noticing, and restructuring. They rated each on acceptability and practicality and completed measures of cognitive fusion, emotional distress, and experiential avoidance as possible moderating variables. Restructuring was overwhelmingly preferred and rated as more acceptable than the two alternatives by both the overall sample and a distressed subsample. Preference for defusion or noticing was not predicted by ratings of acceptability or practicality but by elevated levels of cognitive fusion and emotional distress consistent with a compensation model. Limitations of the study and its implications for further research on psychotherapy preference and its integration within evidence-based practice are discussed.

Deception Velocity-Based Method to Discriminate Physical Targets and Active False Targets in a Multistatic Radar System

Due to the silent operation of the receiver station in a multistatic radar system, it is difficult for the jammer to generate the cooperative active deception target for the multistatic radar system. Making use of the spatial diversity property, a data level fusion method is proposed to counter the active deception jamming in this paper. According to the spatial correlation difference in physical target and active false target motion states, the deception velocity of the physical target, which is obtained by the radial velocity of each receiver, obeys the Gaussian distribution with zero mean, and the one of the active false target obeys the Gaussian distribution with the mean being its true deception velocity. Based on this fact, the active false target and physical target are discriminated by the deception velocity testing. The proposed deception velocity-based (DVB) method can keep a constant misjudgment probability for physical targets and discriminate active false targets effectively, especially in large deception velocity cases. The simulation verifies the feasibility and validity of the proposed discrimination method. Moreover, the proposed method can be combined with the location information association method to enhance the ability to discriminate the range–velocity joint deception of false targets.

Hidden blood loss and bleeding characteristics in children with congenital scoliosis undergoing spinal osteotomies.

Spinal osteotomies are often essential in the treatment of congenital scoliosis. Risk factors for bleeding in these patients needing extracavitatory approaches, especially hidden blood loss, are sparsely investigated. We aimed to investigate the bleeding characteristics and hidden blood loss in paediatric patients undergoing spinal osteotomies for congenital scoliosis. A retrospective analysis identified all patients with congenital scoliosis were retrospectively identified from the prospectively collected spine register from 2010 to 2022. Operative technique, perioperative laboratory results and imaging studies were extracted. The primary outcome was total blood loss including intraoperative, drain output and hidden blood loss. Fifty-seven children (32 boys) with a mean age of 8.3 years underwent spinal osteotomy for congenital scoliosis. Posterolateral hemivertebrectomy was sufficient in 34 (59%) patients, while vertebral column resection (VCR) was required in 23 patients. Total bleeding averaged 792 (523) ml accounting for 42% of the estimated blood volume. Hidden blood loss accounted for 40% of total bleeding and 21% of estimated blood volume with a mean of 317 (256) ml. VCR was associated with greater intraoperative and total bleeding than hemivertebrectomies (p = 0.001 and 0.007, respectively). After adjusting for patient weight and fusion levels, hidden blood loss was larger in hemivertebrectomies (4.18 vs. 1.77 ml/kg/fused level, p = 0.049). In multivariable analysis, intraoperative blood loss was inversely correlated with preoperative erythrocyte levels. Younger age was associated with significantly greater drain, hidden and total blood loss. Hidden blood loss constitutes a significant portion (40%) of total bleeding in congenital scoliosis surgery. Younger age is a risk factor for bleeding and the hidden blood loss should be taken into consideration in their perioperative management.

Validation of Roussouly classification in predicting the occurrence of adjacent segment disease after short-level lumbar fusion surgery

BackgroundRecent studies demonstrated that restoring sagittal alignment to the original Roussouly type can remarkably reduce complication rates after adult spinal deformity surgery. However, there is still no data proving the benefit of maintaining ideal Roussouly shape in the lumbar degenerative diseases and its association with the development of adjacent segment disease (ASD). Thus, this study was performed to validate the usefulness of Roussouly classification to predict the occurrence of ASD after lumbar fusion surgery.Materials and MethodsThis study retrospectively reviewed 234 consecutive patients with lumbar degenerative diseases who underwent 1- or 2-level fusion surgery. Demographic and radiographic data were compared between ASD and non-ASD groups. The patients were classified by both “theoretical” [based on pelvic incidence (PI)] and “current” (based on sacral slope) Roussouly types. The patients were defined as “matched” if their “current” shapes matched the “theoretical” types and otherwise as “mismatched”. The logistic regression analysis was performed to identify the factors associated with ASD. Finally, clinical data and spinopelvic parameters of “theoretical” and “current” types were compared.ResultsWith a mean follow-up duration of 70.6 months, evidence of ASD was found in the 68 cases. Postoperatively, ASD group had more “current” shapes classified as type 1 or 2 and fewer as type 3 than the non-ASD group (p < 0.001), but the distribution of “theoretical” types was similar between groups. Moreover, 80.9% (55/68) of patients with ASD were mismatched, while 48.2% (80/166) of patients without ASD were mismatched (p < 0.001). A multivariate analysis identified age [odds ratio (OR) = 1.058)], 2-level fusion (OR = 2.9830), postoperative distal lordosis (DL, OR = 0.949) and mismatched Roussouly type (OR = 4.629) as independent risk factors of ASD. Among the four "theoretical" types, type 2 had the lowest lumbar lordosis, DL, and segmental lordosis. When considering the "current" types, current type 2 was associated with higher rates of 2-level fusion, worse DL, and greater pelvic tilt compared with other current types.ConclusionsDL loss and mismatched Roussouly type were significant risk factors of ASD. To decrease the incidence of ASD, an appropriate value of DL should be achieved to restore sagittal alignment back to the ideal Roussouly type.Level of Evidence: Level 4.

Investigating Prior-Level Fusion Approaches for Enriched Semantic Segmentation of Urban LiDAR Point Clouds

Three-dimensional semantic segmentation is the foundation for automatically creating enriched Digital Twin Cities (DTCs) and their updates. For this task, prior-level fusion approaches show more promising results than other fusion levels. This article proposes a new approach by developing and benchmarking three prior-level fusion scenarios to enhance the outcomes of point cloud-enriched semantic segmentation. The latter were compared with a baseline approach that used the point cloud only. In each scenario, specific prior knowledge (geometric features, classified images, or classified geometric information) and aerial images were fused into the neural network’s learning pipeline with the point cloud data. The goal was to identify the one that most profoundly enhanced the neural network’s knowledge. Two deep learning techniques, “RandLaNet” and “KPConv”, were adopted, and their parameters were modified for different scenarios. Efficient feature engineering and selection for the fusion step facilitated the learning process and improved the semantic segmentation results. Our contribution provides a good solution for addressing some challenges, particularly for more accurate extraction of semantically rich objects from the urban environment. The experimental results have demonstrated that Scenario 1 has higher precision (88%) on the SensatUrban dataset compared to the baseline approach (71%), the Scenario 2 approach (85%), and the Scenario 3 approach (84%). Furthermore, the qualitative results obtained by the first scenario are close to the ground truth. Therefore, it was identified as the efficient fusion approach for point cloud-enriched semantic segmentation, which we have named the efficient prior-level fusion (Efficient-PLF) approach.

The Effects of Preoperative Epidural Steroid Injection on Pseudarthrosis Following Lumbar Fusion: A Retrospective Cohort Study.

Retrospective cohort study. The goal of this study is to evaluate the effects of preoperative lumbar epidural steroid injection on the rate of pseudarthrosis following lumbar spine fusion surgery. Epidural corticosteroids help to reduce nerve root edema and suppress proinflammatory cytokines in patients with radiculopathy. Corticosteroids may inhibit bone formation and reduce bone matrix synthesis rates. Thus, there is concern that corticosteroids may reduce lumbar fusion capability, potentially resulting in increased rates of symptomatic pseudarthrosis. We identified all patients who underwent 1-level or 2-level lumbar fusion surgery between 2018 and 2022. Patients were categorized into one of 3 groups: no preoperative epidural steroid injection (ESI) history (group 0), preoperative ESI within 90 days of surgery (group 1), or most recent ESI >90 days before surgery (group 2). The primary outcome of this study was pseudarthrosis. Binominal regression analyses were performed to determine the relationships between potential risk factors (sex, age, body mass index, smoking history, diabetes status, history of systemic steroid use, preoperative ESI, perioperative intravenous steroid administration, type of surgery, and postoperative ESI within 6mo) and the development of postoperative pseudarthrosis. A total of 446 patients were included in this study. Of those, 106 patients (23.7%) did not have a preoperative ESI (group 0), 132 patients (29.5%) had an ESI within 90 days of surgery (group 1), and 208 patients (46.6%) had their most recent ESI >90 days before surgery (group 2). The overall incidence of pseudarthrosis following lumbar fusion was 8.7% (39 of 446). Although the incidence of pseudarthrosis following ESI at any time point was higher than in our control cohort (group 0), this difference was not statistically significant. This study found no increased risk of postoperative pseudarthrosis in patients who underwent 1-level or 2-level lumbar fusions after preoperative ESI. Level III.

Multi-sensor data fusion framework for energy optimization in smart homes

Advancements in Internet of Energy (IoE) technologies drive the development of several energy efficient frameworks for better energy optimization, economic savings, safety, and security in smart homes. However, certain challenges such as real-time operational data for each micro-moment, proper application of data fusion techniques, and end-to-end computing and deployment architecture prevent the establishment of an effective energy-efficient framework to provide personalized energy-saving recommendations. This work presents energy management for smart spaces (EMSS), the proposed energy efficiency framework implemented in an edge-cloud computing platform that fuses data from heterogeneous data sources (environmental sensors, camera, plug data, etc.) at appropriate data fusion levels and process them to generate actionable, explainable, personalized, and persuasive recommendations at the right moment. The user response to the generated recommendations triggers the actuators to perform respective energy-saving actions and provide more personalized future recommendations. Further, SMARTHome - a data generation framework based on configurable scenario files and a set of software codes was proposed to generate synthetic data with respect to different building types and micro-moments. The functionalities of the EMSS (device and user registration), user dashboard, analytics, and energy-saving recommendations were made accessible to the user through web and mobile applications. The validation analysis of the EMSS was performed by (i) comparative analysis of the machine learning and deep learning algorithms used by the decision engine to generate energy-saving recommendations and (ii) benchmarking of EMSS based on the taxonomy of data fusion-based energy efficiency frameworks for smart homes.

Prediction of Fusion Rod Curvature Angles in Posterior Scoliosis Correction Using Artificial Intelligence.

This study aimed to estimate post-operative rod angles in both concave and convex sides of scoliosis curvature in patients who had undergone posterior surgery, using neural networks and support vector machine (SVM) algorithms. Radiographs of 72 scoliotic individuals were obtained to predict post-operative rod angles at all fusion levels (all spinal joints fused by rods). Pre-operative radiographical indices and pre-operatively resolved net joint moments of the apical vertebrae were employed as inputs for neural networks and SVM with biomechanical modeling using inverse dynamics analysis. Various group combinations were considered as inputs, based on the number of pre-operative angles and moments. Rod angles on both the concave and convex sides of the Cobb angle were considered as outputs. To assess the outcomes, root mean square errors (RMSEs) were evaluated between actual and predicted rod angles. Among eight groups with various combinations of radiographical and biomechanical parameters (such as Cobb, kyphosis, and lordosis, as well as joint moments), RMSEs of groups 4 (with seven radiographical angles in each case, which is greater in quantity) and 5 (with four radiographical angles and one biomechanical moment in each case, which is the least possible number of inputs with both radiographical and biomechanical parameters) were minimum, particularly in prediction of the concave rod kyphosis angle (errors were 5.5° and 6.3° for groups 4 and 5, respectively). Rod lordosis angles had larger estimation errors than rod kyphosis ones. Neural networks and SVM can be effective techniques for the post-operative estimation of rod angles at all fusion levels to assist surgeons with rod bending procedures before actual surgery. However, since rod lordosis fusion levels vary widely across scoliosis cases, it is simpler to predict rod kyphosis angles, which is more essential for surgeons.

Lordosis distribution index for predicting mechanical complications after long-level fusion surgery: comparison of Global Alignment and Proportion score and Roussouly classification.

Both the Global Alignment and Proportion (GAP) score and Roussouly classification account for the lordosis distribution index (LDI), but the LDI of the GAP score (G-LDI) is typically set to 50%-80%, while the LDI of the Roussouly classification (R-LDI) varies depending on the degree of pelvic incidence (PI). The objective of this study was to validate the ability of the G-LDI to predict mechanical complications and compare it with the predictive probability of R-LDI in patients with long-level fusion surgery. A total of 171 patients were divided into two groups: 93 in the nonmechanical complication group (non-MC group) and 78 in the mechanical complication group (MC group). The mean age of the participants was 66.79 ± 8.56 years (range 34-83 years), and the mean follow-up period was 45.49 ± 16.20 months (range 24-62 months). The inclusion criteria for the study were patients who underwent > 4 levels of fusion and had > 2 years of follow-up. The predictive models for mechanical complications using the G-LDI and R-LDI were analyzed using binomial logistic regression and receiver operating characteristic analyses. There was a significant correlation between R-LDI and PI (r = -0.561, p < 0.001), while there was no correlation between G-LDI and PI (r = 0.132, p = 0.495). In reference to G-LDI, most patients in the non-MC group were classified as having alignment (72, 77.4%), while the MC group had an inhomogeneous composition (aligned: 34, 43.6%; hyperlordosis: 37, 47.4%). The agreement between the G-LDI and R-LDI was moderate (κ = 0.536, p < 0.001) to fair (κ = 0.383, p = 0.011) for patients with average or large PI, but poor (κ = -0.255, p = 0.245) for those with small PI. The areas under the curve for the G-LDI and R-LDI were 0.674 (95% CI, 0.592-0.757) and 0.745 (95% CI, 0.671-0.820), respectively. The R-LDI, which uses a PI-based proportional parameter, enables individual quantification of LL for all PI sizes and has been shown to have a higher accuracy in classifying cases and a stronger correlation with the risk of mechanical complications compared with G-LDI.