Objective To propose a classification method for ultrasound images of pedicle screw canals based on radiomics analysis,and to evaluate the integrity of the screw canal.Methods With thoracolumbar spine specimens from 4 fresh cadavers,50 pedicle screw canals were pre-established and ultrasound images of the canals were acquired.A total of 2 000 images(1 000 intact and 1 000 damaged canal samples)were selected.The dataset was randomly divided in a 4∶1 ratio using 5-fold cross-validation to form training and testing sets(consisting of 1 600 and 400 samples,respectively).Firstly,the optimal radius of the region of interest was identified using the Otsu's thresholding method,followed by feature extraction using pyradiomics.Principal component analysis and the least absolute shrinkage and selection operator algorithm were employed for dimensionality reduction and feature selection,respectively.Subsequently,3 machine learning models(support vector machine[SVM],logistic regression,and random forest)and 3 deep learning models(visual geometry group[VGG],ResNet,and Transformer)were used to classify the ultrasound images.The performance of each model was evaluated using accuracy.Results With a region of interest radius of 230 pixels,the SVM model achieved the highest classification accuracy of 96.25%.The accuracy of the VGG model was only 51.29%,while the accuracies of the logistic regression,random forest,ResNet,and Transformer models were 85.50%,80.75%,80.17%,and 75.18%,respectively.Conclusion For ultrasound images of pedicle screw canals,the machine learning model performs better than the deep learning model as a whole,and the SVM model has the best classification performance,which can be used to assist physicians in diagnosis.

PURPOSE: Details of patients hospitalized for asthma exacerbation in mainland China are lacking. To improve disease control and reduce economic burden, a large sample survey among this patient population is indispensable. This study aimed to investigate the clinical characteristics and outcomes of such patients.METHODS: A retrospective study was conducted on patients hospitalized for asthma exacerbation in 29 hospitals of 29 regions in mainland China during the period 2013 to 2014. Demographic features, pre-admission conditions, exacerbation details, and outcomes were summarized. Risk factors for exacerbation severity were analyzed.RESULTS: There were 3,240 asthmatic patients included in this study (57.7% females, 42.3% males). Only 28.0% used daily controller medications; 1,287 (39.7%) patients were not currently on inhaled corticosteroids. Acute upper airway infection was the most common trigger of exacerbation (42.3%). Patients with severe to life-threatening exacerbation tended to have a longer disease course, a smoking history, and had comorbidities such as hypertension, chronic obstructive pulmonary disease (COPD), and food allergy. The multivariate analysis showed that smoking history, comorbidities of hypertension, COPD, and food allergy were independent risk factors for more severe exacerbation. The number of patients hospitalized for asthma exacerbation varied with seasons, peaking in March and September. Eight patients died during the study period (mortality 0.25%).CONCLUSIONS: Despite enhanced education on asthma self-management in China during recent years, few patients were using daily controller medications before the onset of their exacerbation, indicating that more educational efforts and considerations are needed. The findings of this study may improve our understanding of hospital admission for asthma exacerbation in mainland China and provide evidence for decision-making.
Adrenal Cortex Hormones ; Asthma ; China ; Comorbidity ; Disease Progression ; Education ; Female ; Food Hypersensitivity ; Hospitalization ; Humans ; Hypertension ; Inpatients ; Medication Adherence ; Mortality ; Multivariate Analysis ; Pulmonary Disease, Chronic Obstructive ; Retrospective Studies ; Risk Factors ; Seasons ; Self Care ; Smoke ; Smoking