Narrow Results

Background and objective: The Covid-19 pandemic significantly affects the global population’s fitness and day-to-day life. The necessary action to fight against Covid is to have a fast, accurate and affordable diagnosis system. Most of the diagnostic systems available today have a low detection rate and are time consuming. Hence, there is a demand to design an affordable, accurate, and fast diagnostic system for Covid. The diagnostic system that uses the Convolutional Neural Network (CNN) does not consider the complex correlation of multimodal image data, thus misleading the diagnostic results. Graph Convolutional Network (GCN) provides a better solution for the complex representation of data, as it is modeled based on the pairwise relationship in the image features. Method: Diagnosis of Covid, Parasite, or Lung Tumor from X-ray images needs a more complex representative model. There is a demand to categorize the images grounded on highly complex features. To solve the issue mentioned earlier, this work proposes a Hypergraph- and convolutional neural network-based Fast and Accurate Diagnosis (FAT) system for Covid. The in-depth features are mined using a residual neural network from the X-ray images. The learning-based method optimizes a high-level correlation in the deep structures by constructing it as a hypergraph. Results: The proposed method is assessed based on the Covid dataset. The experimental outcomes show that the proposed system FAT provides the accuracy of 99.8%, sensitivity of 99.5%, and specificity of 99%. It outperforms all the current diagnosis systems for Covid. Conclusion: The proposed deep learning-based model is well suited for Covid diagnosis at the preliminary level. It allows diagnosing Covid by low radiation chest X-ray images with higher accuracy.

COVID-19 is a pandemic disease, which massively affected human lives in more than 200 countries. Caused by the coronavirus SARS-CoV-2, this acute respiratory illness affects the human lungs and can easily spread from person to person. Since the disease heavily affects human lungs, analyzing the X-ray images of the lungs may prove to be a powerful tool for disease investigation. In this research, we use the information contained within the complex structures of X-ray images between the cases of COVID-19 and other respiratory diseases, whereas the case of healthy lungs is taken as the reference point. To analyze X-ray images, we benefit from the concept of Shannon’s entropy and fractal theory. Shannon’s entropy is directly related to the amount of information contained within the X-ray images in question, whereas fractal theory is used to analyze the complexity of these images. The results, obtained in this study, show that the method of fractal analysis can detect the level of infection among different respiratory diseases and that COVID-19 has the worst effect on the human lungs. In other words, the complexity of X-ray images is proportional to the severity of the respiratory disease. The method of analysis, employed in this study, can be used even further to analyze how COVID-19 progresses in affected patients.

The current COVID-19 pandemic mainly affects the upper respiratory tract. People with COVID-19 report a wide range of symptoms, some of which are similar to those of common flu, such as sore throat and rhinorrhea. Additionally, COVID-19 shares many clinical symptoms with severe pneumonia, including fever, fatigue, dry cough, and respiratory distress. Several diagnostic strategies, such as the real-time polymerase chain reaction technique and computed tomography imaging, which are more costly than chest radiography, are employed as diagnostic tools. The purpose of this paper is to describe the role of the d-summable information dimension of X-ray images in differentiating several lesions and lung illnesses better than both fractal and information dimensions. The statistical analysis shows that the d-summable information dimension model better describes the information obtained from the X-ray images. Therefore, it is a more precise measure of complexity than the information and box-counting dimension. The results also show that the X-ray images of COVID-19 pneumonia reveal greater damage than those of tuberculosis, pneumonia, and various lung lesions, where the damage is minor or much focused. Because the d-summable information dimension increases as the image complexity decreases, it could pave the way to formulate a new measure to quantify the lung damage and assist the clinical diagnosis based on the area under the d-summable information model. In addition, the physical meaning of the $\nu$ parameter in the d-summable information dimension is given.

Purpose anterior cervical decompression and fusion is a common surgical procedure. Traditionally, experienced doctors observe X-ray films regularly examined by patients to determine postoperative conditions by observing the tiny movements between the limited vertebral bodies. But it is not accurate. This may lead to error diagnostics and serious deterioration of the condition and secondary injury to the patient and will also put a greater financial burden on them. Doctors need a quantitative standard to determine small motion with limited vertebral landmarks after surgery. Computer vision technology is needed to match the over-extension and over-flexion cervical vertebral body to provide objective measurement data for further quantification of intervertebral activity. Based on conventional scheme, the point mean square error is used as the evaluation criterion of the matching effect, and the iterative matching scheme is proposed to improve the stability of the original scheme. The cervical X-ray films of patients from the China–Japan Friendship Hospital were collected as samples to verify the reliability of the scheme. Compared with the existing image matching schemes based on feature points, our scheme is superior in matching effect, matching speed and stability. This scheme can provide a solid foundation for further assisting doctors in the study of rehabilitation after anterior cervical fusion.