Residual Feature Attentional Fusion Network for Lightweight Chest CT Image Super-Resolution

The diagnosis of COVID-19 requires chest computed tomography (CT). High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease, so it is of clinical importance to study super-resolution (SR) algorithms applied to CT images to improve the reso-lution of CT images. However, most of the existing SR algorithms are studied based on natural images, which are not suitable for medical images;and most of these algorithms improve the reconstruction quality by increasing the network depth, which is not suitable for machines with limited resources. To alleviate these issues, we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution (RFAFN). Specifically, we design a contextual feature extraction block (CFEB) that can extract CT image features more efficiently and accurately than ordinary residual blocks. In addition, we propose a feature-weighted cascading strategy (FWCS) based on attentional feature fusion blocks (AFFB) to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information. Finally, we suggest a global hierarchical feature fusion strategy (GHFFS), which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels. Numerous experiments show that our method performs better than most of the state-of-the-art (SOTA) methods on the COVID-19 chest CT dataset. In detail, the peak signal-to-noise ratio (PSNR) is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at x3 SR compared to the suboptimal method, but the number of parameters and multi-adds are reduced by 22K and 0.43G, respectively. Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.

The SARS-CoV-2 Antibody and Drug Research Based on the Structure of the Spike Protein and the Mechanism of Cell Entry.

COVID-19 is a severe acute respiratory syndrome caused by a novel coronavirus, SARS-CoV- 2.COVID-19 is now a pandemic, and is not yet fully under control.As the surface spike protein (S) mediates the recognition between the virus and cell membrane and the process of cell entry, it plays an important role in the course of disease transmission.The study on the S protein not only elucidates the structure and function of virus-related proteins and explains their cellular entry mechanism, but also provides valuable information for the prevention, diagnosis and treatment of COVII)-19.Concentrated on the S protein of SARS-CoV-2, this review covers four aspects: (1 ) The structure of the S protein and its binding with angiotensin converting enzyme II (ACE2) , the specific receptor of SARS-CoV-2, is introduced in detail.Compared with SARS-CoV, the receptor binding domain (RBD) of the SARS-CoV- 2 S protein has a higher affinity with ACE2, while the affinity of the entire S protein is on the contrary.(2) Currently, the cell entry mechanism of SARS-CoV-2 meditated by the S protein is proposed to include endosomal and non-endosomal pathways.With the recognition and binding between the S protein and ACE2 or after cell entry, transmembrane protease serine 2(TMPRSS2) , lysosomal cathepsin or the furin enzyme can cleave S protein at S1/S2 cleavage site, facilitating the fusion between the virus and target membrane.(3) For the progress in SARS-CoV-2 S protein antibodies, a collection of significant antibodies are introduced and compared in the fields of the target, source and type.(4) Mechanisms of therapeutic treatments for SARS-CoV-2 varied.Though the antibody and medicine treatments related to the SARS-CoV-2 S protein are of high specificity and great efficacy, the mechanism, safety, applicability and stability of some agents are still unclear and need further assessment.Therefore, to curb the pandemic, researchers in all fields need more cooperation in the development of SARS-CoV-2 antibodies and medicines to face the great challenge.Copyright © Palaeogeography (Chinese Edition).All right reserved.

Embedded system vehicle based on multi-sensor fusion

As intelligent driving vehicles came out of concept into people’s life, the combination of safe driving and artificial intelligence becomes the new direction of future transportation development. Autonomous driving technology is developing based on control algorithms and model recognitions. In this paper, a cloud-based interconnected multi-sensor fusion autonomous vehicle system is proposed that uses deep learning (YOLOv4) and improved ORB algorithms to identify pedestrians, vehicles, and various traffic signs. A cloud-based interactive system is built to enable vehicle owners to master the situation of their vehicles at any time. In order to meet multiple application of automatic driving vehicles, the environment perception technology of multi-sensor fusion processing has broadened the uses of automatic driving vehicles by being equipped with automatic speech recognition (ASR), vehicle following mode and road patrol mode. These functions enable automatic driving to be used in applications such as agricultural irrigation, road firefighting and contactless delivery under new coronavirus outbreaks. Finally, using the embedded system equipment, an intelligent car was built for experimental verification, and the overall recognition accuracy of the system was over 96%. Author

Graph-Based Fusion of Imaging and Non-Imaging Data for Disease Trajectory Prediction

This study proposes a graph convolutional neural networks (GCN) architecture for fusion of radiological imaging and non-imaging tabular electronic health records (EHR) for the purpose of clinical event prediction. We focused on a cohort of hospitalized patients with positive RT-PCR test for COVID-19 and developed GCN based models to predict three dependent clinical events (discharge from hospital, admission into ICU, and mortality) using demographics, billing codes for procedures and diagnoses and chest X-rays. We hypothesized that the two-fold learning opportunity provided by the GCN is ideal for fusion of imaging information and tabular data as node and edge features, respectively. Our experiments indicate the validity of our hypothesis where GCN based predictive models outperform single modality and traditional fusion models. We compared the proposed models against two variations of imaging-based models, including DenseNet-121 architecture with learnable classification layers and Random Forest classifiers using disease severity score estimated by pre-trained convolutional neural network. GCN based model outperforms both imaging-only methods. We also validated our models on an external dataset where GCN showed valuable generalization capabilities. We noticed that edge-formation function can be adapted even after training the GCN model without limiting application scope of the model. Our models take advantage of this fact for generalization to external data. © 2023 IEEE.

Path Planning of Follow-up Transport Robot Based on Machine Vision

With the upgrading and innovation of the logistics industry, the requirements for the level of transportation smart technologies continue to increase. The outbreak of the COVID-19 has further promoted the development of unmanned transportation machines. Aimed at the requirements of intelligent following and automatic obstacle avoidance of mobile robots in dynamic and complex environments, this paper uses machine vision to realize the visual perception function, and studies the real-time path planning of robots in complicated environment. And this paper proposes the Dijkstra-ant colony optimization (ACO) fusion algorithm, the environment model is established by the link viewable method, the Dijkstra algorithm plans the initial path. The introduction of immune operators improves the ant colony algorithm to optimize the initial path. Finally, the simulation experiment proves that the fusion algorithm has good reliability in a dynamic environment. © 2022 IEEE.

A Survey on Machine Learning Techniques for Multimodal Biomedical Signal Processing

In recent years, there has been a significant growth in the development of machine learning algorithms towards better experience in patient care. In this paper, a contemporary survey on the deep learning and machine learning techniques used in multimodal signal processing for biomedical applications is presented. Specifically, an overview of the preprocessing approaches and the algorithms proposed for five major biomedical applications are presented, namely detection of cardiovascular diseases, retinal disease detection, stress detection, cancer detection and COVID-19 detection. In each case, processing on each multimodal data type, such as an image or a text is discussed in detail. A list of various publicly available datasets for each of these applications is also presented. © 2023 IEEE.

An Improved Soft Subspace Clustering Algorithm for Brain MR Image Segmentation

In recent years, the soft subspace clustering algorithm has shown good results for high-dimensional data, which can assign different weights to each cluster class and use weights to measure the contribution of each dimension in various features. The enhanced soft subspace clustering algorithm combines interclass separation and intraclass tightness information, which has strong results for image segmentation, but the clustering algorithm is vulnerable to noisy data and dependence on the initialized clustering center. However, the clustering algorithm is susceptible to the influence of noisy data and reliance on initialized clustering centers and falls into a local optimum;the clustering effect is poor for brain MR images with unclear boundaries and noise effects. To address these problems, a soft subspace clustering algorithm for brain MR images based on genetic algorithm optimization is proposed, which combines the generalized noise technique, relaxes the equational weight constraint in the objective function as the boundary constraint, and uses a genetic algorithm as a method to optimize the initialized clustering center. The genetic algorithm finds the best clustering center and reduces the algorithm's dependence on the initial clustering center. The experiment verifies the robustness of the algorithm, as well as the noise immunity in various ways and shows good results on the common dataset and the brain MR images provided by the Changshu First People's Hospital with specific high accuracy for clinical medicine.

Reduce the spread risk of covid-19 based on clinical fusion data and monitoring system in wireless sensor network

The expression "COVID-19” has been the fiercest but most trending Google search since it first appeared in November 2019. Due to advances in mobile technology and sensors, Healthcare systems based on the Internet of Things are conceivable. Instead of the traditional reactive healthcare systems, these new healthcare systems can be proactive and preventive. This paper suggested a framework for real-time suspect detection based on the Internet of Things. In the early phases of predicting COVID-19, the framework evaluates the existence of the virus by extracting health variables obtained in real-time from sensors and other IoT devices, in order to better understand the behavior of the virus by collecting symptom data of COVID-19, In this paper, four machine learning models (Random Forest, Decision Tree, K-Nearest Neural Network, and Artificial Neural Network) are proposed, these data and applied as a machine learning model to obtain high diagnostic accuracy, however, it is noted that there is a problem when collecting clinical fusion data that is scarce and unbalanced, so a dataset augmented by Generative Adversarial Network (GAN) was used. Several algorithms achieved high levels of accuracy (ACC), including Random Forest (99%), and Decision Tree (99%), K-Nearest Neighbour (98%), and Artificial Neural Network (99%). These results show the ability of GANs to generate data and their ability to provide relevant data to efficiently manage Covid-19 and reduce the risk of its spread through accurate diagnosis of patients and informing health authorities of suspected cases. © 2023, American Scientific Publishing Group (ASPG). All rights reserved.

A Low-Cost Wireless Body Area Network for Human Activity Recognition in Healthy Life and Medical Applications

Moved by the necessity, also related to the ongoing COVID-19 pandemic, of the design of innovative solutions in the context of digital health, and digital medicine, Wireless Body Area Networks (WBANs) are more and more emerging as a central system for the implementation of solutions for well-being and healthcare. In fact, by elaborating the data collected by a WBAN, advanced classification models can accurately extract health-related parameters, thus allowing, as examples, the implementations of applications for fitness tracking, monitoring of vital signs, diagnosis, and analysis of the evolution of diseases, and, in general, monitoring of human activities and behaviours. Unfortunately, commercially available WBANs present some technological and economic drawbacks from the point of view, respectively, of data fusion and labelling, and cost of the adopted devices. To overcome existing issues, in this paper, we present the architecture of a low-cost WBAN, which is built upon accessible off-the-shelf wearable devices and an Android application. Then, we report its technical evaluation concerning resource consumption. Finally, we demonstrate its versatility and accuracy in both medical and well-being application scenarios. Author

Explainable AI for COVID-19 prognosis from early Chest X-ray and clinical data in the context of the COVID-CXR international hackathon

Although many AI-based scientific works regarding chest X-ray (CXR) interpretation focused on COVID-19 diagnosis, fewer papers focused on other relevant tasks, like severity estimation, deterioration, and prognosis. The same holds for explainable decisions to estimate COVID-19 prognosis as well. The international hackathon launched during Dubai Expo 2020, aimed at designing machine learning solutions to help physicians formulate COVID-19 patients' prognosis, was the occasion to develop a machine learning model capable of predicting such prognoses and justifying them through interpretable explanations. The large hackathon dataset comprised subjects characterized by their CXR and numerous clinical features collected during triage. To calculate the prognostic value, our model considered both patients' CXRs and clinical features. After automatic pre-processing to improve their quality, CXRs were processed by a Deep Learning model to estimate the lung compromise degree, which has been considered as an additional clinical feature. Original clinical parameters suffered from missing values that were adequately handled. We trained and evaluated multiple models to find the best one and fine-tune it before the inference process. Finally, we produced novel explanations, both visual and numerical, to justify the model predictions. Ultimately, our model processes a CXR and several clinical data to estimate a patient's prognosis related to the COVID-19 disease. It proved to be accurate and was ranked second in the final rankings with 75%, 73.9%, and 74.4% in sensitivity, specificity, and balanced accuracy, respectively. In terms of model explainability, it was ranked first since it was agreed to be the most interpretable by health professionals. © 2023 SPIE.

Cough Detection for Prevention Against the COVID-19 Pandemic

This paper proposes a novel and robust technique for remote cough recognition for COVID-19 detection. This technique is based on sound and image analysis. The objective is to create a real-time system combining artificial intelligence (AI) algorithms, embedded systems, and network of sensors to detect COVID-19-specific cough and identify the person who coughed. Remote acquisition and analysis of sounds and images allow the system to perform both detection and classification of the detected cough using AI algorithms and image processing to identify the coughing person. This will give the ability to distinguish between a normal person and a person carrying the COVID-19 virus. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Automated COVID-19 diagnosis and classification using convolutional neural network with fusion based feature extraction model.

COVID-19 was first identified in December 2019 at Wuhan, China. At present, the outbreak of COVID-19 pandemic has resulted in severe consequences on both economic and social infrastructures of the developed and developing countries. Several studies have been conducted and ongoing still to design efficient models for diagnosis and treatment of COVID-19 patients. The traditional diagnostic models that use reverse transcription-polymerase chain reaction (rt-qPCR) is a costly and time-consuming process. So, automated COVID-19 diagnosis using Deep Learning (DL) models becomes essential. The primary intention of this study is to design an effective model for diagnosis and classification of COVID-19. This research work introduces an automated COVID-19 diagnosis process using Convolutional Neural Network (CNN) with a fusion-based feature extraction model, called FM-CNN. FM-CNN model has three major phases namely, pre-processing, feature extraction, and classification. Initially, Wiener Filtering (WF)-based preprocessing is employed to discard the noise that exists in input chest X-Ray (CXR) images. Then, the pre-processed images undergo fusion-based feature extraction model which is a combination of Gray Level Co-occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRM), and Local Binary Patterns (LBP). In order to determine the optimal subset of features, Particle Swarm Optimization (PSO) algorithm is employed. At last, CNN is deployed as a classifier to identify the existence of binary and multiple classes of CXR images. In order to validate the proficiency of the proposed FM-CNN model in terms of its diagnostic performance, extension experimentation was carried out upon CXR dataset. As per the results attained from simulation, FM-CNN model classified multiple classes with the maximum sensitivity of 97.22%, specificity of 98.29%, accuracy of 98.06%, and F-measure of 97.93%.

A dePEGylated Lipopeptide-Based Pan-Coronavirus Fusion Inhibitor Exhibits Potent and Broad-Spectrum Anti-HIV-1 Activity without Eliciting Anti-PEG Antibodies.

We previously identified a lipopeptide, EK1C4, by linking cholesterol to EK1, a pan-CoV fusion inhibitory peptide via a polyethylene glycol (PEG) linker, which showed potent pan-CoV fusion inhibitory activity. However, PEG can elicit antibodies to PEG in vivo, which will attenuate its antiviral activity. Therefore, we designed and synthesized a dePEGylated lipopeptide, EKL1C, by replacing the PEG linker in EK1C4 with a short peptide. Similar to EK1C4, EKL1C displayed potent inhibitory activity against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and other coronaviruses. In this study, we found that EKL1C also exhibited broad-spectrum fusion inhibitory activity against human immunodeficiency virus type 1 (HIV-1) infection by interacting with the N-terminal heptad repeat 1 (HR1) of viral gp41 to block six-helix bundle (6-HB) formation. These results suggest that HR1 is a common target for the development of broad-spectrum viral fusion inhibitors and EKL1C has potential clinical application as a candidate therapeutic or preventive agent against infection by coronavirus, HIV-1, and possibly other class I enveloped viruses.

DeepCOVID-Fuse: A Multi-Modality Deep Learning Model Fusing Chest X-rays and Clinical Variables to Predict COVID-19 Risk Levels.

The COVID-19 pandemic has posed unprecedented challenges to global healthcare systems, highlighting the need for accurate and timely risk prediction models that can prioritize patient care and allocate resources effectively. This study presents DeepCOVID-Fuse, a deep learning fusion model that predicts risk levels in patients with confirmed COVID-19 by combining chest radiographs (CXRs) and clinical variables. The study collected initial CXRs, clinical variables, and outcomes (i.e., mortality, intubation, hospital length of stay, Intensive care units (ICU) admission) from February to April 2020, with risk levels determined by the outcomes. The fusion model was trained on 1657 patients (Age: 58.30 ± 17.74; Female: 807) and validated on 428 patients (56.41 ± 17.03; 190) from the local healthcare system and tested on 439 patients (56.51 ± 17.78; 205) from a different holdout hospital. The performance of well-trained fusion models on full or partial modalities was compared using DeLong and McNemar tests. Results show that DeepCOVID-Fuse significantly (p < 0.05) outperformed models trained only on CXRs or clinical variables, with an accuracy of 0.658 and an area under the receiver operating characteristic curve (AUC) of 0.842. The fusion model achieves good outcome predictions even when only one of the modalities is used in testing, demonstrating its ability to learn better feature representations across different modalities during training.

SARS-CoV-2 Omicron Specific Mutations Affecting Infectivity, Fusogenicity, and Partial TMPRSS2-Independency.

The COVID-19 pandemic resulted from the global spread of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Since its first appearance in 2019, new SARS-CoV-2 variants of concern (VOCs) have emerged frequently, changing the infection's dynamic. SARS-CoV-2 infects cells via two distinct entry routes; receptor-mediated endocytosis or membrane fusion, depending on the absence or presence of transmembrane serine protease 2 (TMPRSS2), respectively. In laboratory conditions, the Omicron SARS-CoV-2 strain inefficiently infects cells predominantly via endocytosis and is phenotypically characterized by decreased syncytia formation compared to the earlier Delta variant. Thus, it is important to characterize Omicron's unique mutations and their phenotypic manifestations. Here, by utilizing SARS-CoV-2 pseudovirions, we report that the specific Omicron Spike F375 residue decreases infectivity, and its conversion to the Delta S375 sequence significantly increases Omicron infectivity. Further, we identified that residue Y655 decreases Omicron's TMPRSS2 dependency and entry via membrane fusion. The Y655H, K764N, K856N and K969N Omicron revertant mutations, bearing the Delta variant sequence, increased the cytopathic effect of cell-cell fusion, suggesting these Omicron-specific residues reduced the severity of SARS-CoV-2. This study of the correlation of the mutational profile with the phenotypic outcome should sensitize our alertness towards emerging VOCs.

Blood pH Analysis in Combination with Molecular Medical Tools in Relation to COVID-19 Symptoms.

The global outbreak of SARS-CoV-2/COVID-19 provided the stage to accumulate an enormous biomedical data set and an opportunity as well as a challenge to test new concepts and strategies to combat the pandemic. New research and molecular medical protocols may be deployed in different scientific fields, e.g., glycobiology, nanopharmacology, or nanomedicine. We correlated clinical biomedical data derived from patients in intensive care units with structural biology and biophysical data from NMR and/or CAMM (computer-aided molecular modeling). Consequently, new diagnostic and therapeutic approaches against SARS-CoV-2 were evaluated. Specifically, we tested the suitability of incretin mimetics with one or two pH-sensitive amino acid residues as potential drugs to prevent or cure long-COVID symptoms. Blood pH values in correlation with temperature alterations in patient bodies were of clinical importance. The effects of biophysical parameters such as temperature and pH value variation in relation to physical-chemical membrane properties (e.g., glycosylation state, affinity of certain amino acid sequences to sialic acids as well as other carbohydrate residues and lipid structures) provided helpful hints in identifying a potential Achilles heel against long COVID. In silico CAMM methods and in vitro NMR experiments (including 31P NMR measurements) were applied to analyze the structural behavior of incretin mimetics and SARS-CoV fusion peptides interacting with dodecylphosphocholine (DPC) micelles. These supramolecular complexes were analyzed under physiological conditions by 1H and 31P NMR techniques. We were able to observe characteristic interaction states of incretin mimetics, SARS-CoV fusion peptides and DPC membranes. Novel interaction profiles (indicated, e.g., by 31P NMR signal splitting) were detected. Furthermore, we evaluated GM1 gangliosides and sialic acid-coated silica nanoparticles in complex with DPC micelles in order to create a simple virus host cell membrane model. This is a first step in exploring the structure-function relationship between the SARS-CoV-2 spike protein and incretin mimetics with conserved pH-sensitive histidine residues in their carbohydrate recognition domains as found in galectins. The applied methods were effective in identifying peptide sequences as well as certain carbohydrate moieties with the potential to protect the blood-brain barrier (BBB). These clinically relevant observations on low blood pH values in fatal COVID-19 cases open routes for new therapeutic approaches, especially against long-COVID symptoms.

Computational and experimental validation of phthalocyanine and hypericin as effective SARS-CoV-2 fusion inhibitors.

Phthalocyanine and hypericin have been previously identified as possible SARS-CoV-2 Spike glycoprotein fusion inhibitors through a virtual screening procedure. In this paper, atomistic simulations of metal-free phthalocyanines and atomistic and coarse-grained simulations of hypericins, placed around a complete model of the Spike embedded in a viral membrane, allowed to further explore their multi-target inhibitory potential, uncovering their binding to key protein functional regions and their propensity to insert in the membrane. Following computational results, pre-treatment of a pseudovirus expressing the SARS-CoV-2 Spike protein with low compounds concentrations resulted in a strong inhibition of its entry into cells, suggesting the activity of these molecules should involve the direct targeting of the viral envelope surface. The combination of computational and in vitro results hence supports the role of hypericin and phthalocyanine as promising SARS-CoV-2 entry inhibitors, further endorsed by literature reporting the efficacy of these compounds in inhibiting SARS-CoV-2 activity and in treating hospitalized COVID-19 patients.Communicated by Ramaswamy H. Sarma.

Fusion-Extracted Features by Deep Networks for Improved COVID-19 Classification with Chest X-ray Radiography.

Convolutional neural networks (CNNs) have shown promise in accurately diagnosing coronavirus disease 2019 (COVID-19) and bacterial pneumonia using chest X-ray images. However, determining the optimal feature extraction approach is challenging. This study investigates the use of fusion-extracted features by deep networks to improve the accuracy of COVID-19 and bacterial pneumonia classification with chest X-ray radiography. A Fusion CNN method was developed using five different deep learning models after transferred learning to extract image features (Fusion CNN). The combined features were used to build a support vector machine (SVM) classifier with a RBF kernel. The performance of the model was evaluated using accuracy, Kappa values, recall rate, and precision scores. The Fusion CNN model achieved an accuracy and Kappa value of 0.994 and 0.991, with precision scores for normal, COVID-19, and bacterial groups of 0.991, 0.998, and 0.994, respectively. The results indicate that the Fusion CNN models with the SVM classifier provided reliable and accurate classification performance, with Kappa values no less than 0.990. Using a Fusion CNN approach could be a possible solution to enhance accuracy further. Therefore, the study demonstrates the potential of deep learning and fusion-extracted features for accurate COVID-19 and bacterial pneumonia classification with chest X-ray radiography.

Spinal fusion is an aerosol generating procedure.

BACKGROUND: Transmission of severe acute respiratory syndrome coronavirus 2 can occur during aerosol generating procedures. Several steps in spinal fusion may aerosolize blood but little data exists to quantify the risk this may confer upon surgeons. Aerosolized particles containing infectious coronavirus are typically 0.5-8.0 µm. AIM: To measure the generation of aerosols during spinal fusion using a handheld optical particle sizer (OPS). METHODS: We quantified airborne particle counts during five posterior spinal instrumentation and fusions (9/22/2020-10/15/2020) using an OPS near the surgical field. Data were analyzed by 3 particle size groups: 0.3-0.5 µm/m3, 1.0-5.0 µm/m3, and 10.0 µm/m3. We used hierarchical logistic regression to model the odds of a spike in aerosolized particle counts based on the step in progress. A spike was defined as a > 3 standard deviation increase from average baseline levels. RESULTS: Upon univariate analysis, bovie (P < 0.0001), high speed pneumatic burring (P = 0.009), and ultrasonic bone scalpel (P = 0.002) were associated with increased 0.3-0.5 µm/m3 particle counts relative to baseline. Bovie (P < 0.0001) and burring (P < 0.0001) were also associated with increased 1-5 µm/m3 and 10 µm/m3 particle counts. Pedicle drilling was not associated with increased particle counts in any of the size ranges measured. Our logistic regression model demonstrated that bovie (OR = 10.2, P < 0.001), burring (OR = 10.9, P < 0.001), and bone scalpel (OR = 5.9, P < 0.001) had higher odds of a spike in 0.3-0.5 µm/m3 particle counts. Bovie (OR = 2.6, P < 0.001), burring (OR = 5.8, P < 0.001), and bone scalpel (OR = 4.3, P = 0.005) had higher odds of a spike in 1-5 µm/m3 particle counts. Bovie (OR = 0.3, P < 0.001) and drilling (OR = 0.2, P = 0.011) had significantly lower odds of a spike in 10 µm/m3 particle counts relative to baseline. CONCLUSION: Several steps in spinal fusion are associated with increased airborne particle counts in the aerosol size range. Further research is warranted to determine if such particles have the potential to contain infectious viruses. Previous research has shown that electrocautery smoke may be an inhalation hazard for surgeons but here we show that usage of the bone scalpel and high-speed burr also have the potential to aerosolize blood.