Objective:Middle ear cholesteatoma is a common otolaryngological disease, and traditional diagnostic methods have certain limitations. This study aims to construct a computer-aided diagnosis model for middle ear cholesteatoma based on integrated convolutional neural networks (CNNs) to improve diagnostic accuracy and efficiency.Methods:Firstly, Data were collected from patients who visited the Department of Otorhinolaryngology Head and Neck Surgery at the First People′s Hospital of Yinchuan between January 2020 and December 2021. 8 000 temporal bone CT images were collected, including 5 000 images diagnosed pathologically as middle ear cholesteatoma and 3 000 normal images. A five-fold cross-validation method was used to divide the dataset into training and testing sets. Next, a transfer learning approach was used to initialize model parameters, and the AlexNet, GoogleNet, and ResNet networks were pre-trained to extract deep features from the images. Then, the Softmax classification algorithm was applied to classify the features, resulting in three independent classifiers. These classifiers were combined using an ensemble learning method with a weighted voting approach to obtain the final diagnostic results. Finally, the model was evaluated by comparing the ensemble classifier with individual classifiers to assess its accuracy, precision, sensitivity, specificity, and diagnostic time, and a comparison with low-mid-and high-experience physician groups was conducted to comprehensively evaluate the model′s diagnostic performance.Results:The experimental results showed that the model achieved an accuracy of 88.8%(178/200), precision of 92.9%,(112/120) sensitivity of 89.8%(108/120), and specificity of 88.1%(70/80). The average diagnostic time for individual patient temporal bone CT images was reduced to 2-3 seconds. Compared to the diagnostic results from low-mid-and high-experience physician groups, the model demonstrated significant advantages and effectively assisted clinicians in making rapid and accurate middle ear cholesteatoma diagnoses.Conclusion:The proposed middle ear cholesteatoma diagnostic model based on integrated convolutional neural networks exhibits high recognition accuracy and rapid diagnostic speed, significantly improving clinical diagnostic efficiency, especially in early screening and auxiliary diagnosis, making it of considerable value in clinical practice.

Objective:Middle ear cholesteatoma is a common otolaryngological disease, and traditional diagnostic methods have certain limitations. This study aims to construct a computer-aided diagnosis model for middle ear cholesteatoma based on integrated convolutional neural networks (CNNs) to improve diagnostic accuracy and efficiency.Methods:Firstly, Data were collected from patients who visited the Department of Otorhinolaryngology Head and Neck Surgery at the First People′s Hospital of Yinchuan between January 2020 and December 2021. 8 000 temporal bone CT images were collected, including 5 000 images diagnosed pathologically as middle ear cholesteatoma and 3 000 normal images. A five-fold cross-validation method was used to divide the dataset into training and testing sets. Next, a transfer learning approach was used to initialize model parameters, and the AlexNet, GoogleNet, and ResNet networks were pre-trained to extract deep features from the images. Then, the Softmax classification algorithm was applied to classify the features, resulting in three independent classifiers. These classifiers were combined using an ensemble learning method with a weighted voting approach to obtain the final diagnostic results. Finally, the model was evaluated by comparing the ensemble classifier with individual classifiers to assess its accuracy, precision, sensitivity, specificity, and diagnostic time, and a comparison with low-mid-and high-experience physician groups was conducted to comprehensively evaluate the model′s diagnostic performance.Results:The experimental results showed that the model achieved an accuracy of 88.8%(178/200), precision of 92.9%,(112/120) sensitivity of 89.8%(108/120), and specificity of 88.1%(70/80). The average diagnostic time for individual patient temporal bone CT images was reduced to 2-3 seconds. Compared to the diagnostic results from low-mid-and high-experience physician groups, the model demonstrated significant advantages and effectively assisted clinicians in making rapid and accurate middle ear cholesteatoma diagnoses.Conclusion:The proposed middle ear cholesteatoma diagnostic model based on integrated convolutional neural networks exhibits high recognition accuracy and rapid diagnostic speed, significantly improving clinical diagnostic efficiency, especially in early screening and auxiliary diagnosis, making it of considerable value in clinical practice.

A protective device was designed that can be worn on the elderly, which consists of protective airbag, control box and protective mechanism. The combined acceleration, combined angular velocity and human posture angle are selected as the parameters to determine the fall, and the threshold algorithm and SVM algorithm are used to detect the fall. The protective mechanism is an inflatable device based on CO₂ compressed air cylinder, and the equal-width cam structure is applied to its transmission part to improve the puncture efficiency of the compressed gas cylinder. A fall experiment was designed to obtain the combined acceleration and angular velocity eigenvalues of fall actions (forward fall, backward fall and lateral fall) and daily activities (sitting-standing, walking, jogging and walking up and down stairs), showing that the specificity and sensitivity of the protection module reached 92.1% and 84.4% respectively, which verified the feasibility of the fall protection device.
Humans ; Aged ; Monitoring, Ambulatory ; Activities of Daily Living ; Wearable Electronic Devices ; Walking ; Acceleration ; Algorithms

Objective To develop a PCR-ELISA assay for the rapid, specific and sensitive detec-tion of human seasonal influenza virus ( H1, H3 and B) by using molecular biological and immunological methods in combination.Methods The primers were designed according to the genes encoding the matrix protein ( M) , the H1 and H3 hemagglutinin ( HA) of influenza A virus and the nonstructural proteins ( B-NS) of influenza B virus and then were labeled with biotin.The PCR products were detected by ELISA by use of an internal catching probe labeled with DIG.Results The minimum copy numbers of genes encoding the M, H1, H3 and B-NS proteins detected by the established assay were 1.43?103 , 8.67?102 , 3.86?103 and 5.45?103 copies/μl, respectively, which indicated that the PCR-ELISA assay was about 10 times more sensitive than agarose gel electrophoresis in the detection of PCR products.No cross-reactions between the different subtypes of influenza virus or different species of virus were observed.Moreover, a total of 104 clin-ical specimens of influenza virus were examined by the PCR-ELISA assay, the results of which were consist-ent with those of the virus isolation method.Conclusion The newly developed PCR-ELISA assay was a highly sensitive and specific method for the rapid detection and subtyping of influenza virus, suggesting the possibility of using it in laboratory for the surveillance and detection of influenza virus.

Objective To evaluate clinical significance of ischemia grade to predict severe arrhythmia in patients with acute ST-segment elevation myocardial infarction(STEMI).Methods A total of 225 patients with STEMI admitting to emergency department were enrolled.All enrolled patients were divided into two groups based on the QRS complex electrocardiogram on admission:grade 1Ⅱ ischemia group(135 cases) and grade Ⅲ ischemia group (90 cases).All patients received thrombolytic therapy.The incidence rate of ST segment resolution (STR) and severe arrhythmia in hospital stay was observed.Results The ST segment elevation (Σ.ST) on admission and 2 h after thrombolysis in grade Ⅲ ischemia group was significantly higher than that in grade Ⅱ ischemia group [(0.84 ± 0.57) mV vs.(0.44 ± 0.35) mV,(0.50 ± 0.23) mV vs.(0.11 ± 0.06) mV] (P ＜ 0.01).The backing rate of ST segment ≥ 50％ 2 h after thrombolysis in grade Ⅲ ischemia group was significantly lower than that in grade Ⅱ ischemia group [56.7％ (51/90) vs.83.7％ (113/135)] (P ＜0.01).The creatine kinase MB (CK-MB) peak value in grade Ⅲ ischemia group was significantly higher than that in grade Ⅱ ischemia group [(363 ± 105) U/L vs.(212 ± 97) U/L] (P ＜ 0.01).There was no significant difference in the incidence of severe arrhythmia between two groups (P ＞ 0.05).Multiple Logistic regression analysis demonstrated that the independent predictors of severe arrhythmia were duration from symptom to thrombolysis and initial ΣST,whereas grade Ⅲ ischemia remained a strong predictor of severe arrhythmia.Conclusion Grade m ischemia on admission is associated with lower incidence of STR in patients with STEMI after thrombolysis and a strong predictor of severe arrhythmia.