A New Pneumonia Detection Model Based on Transformer with Improved Self-Attention Mechanism

Clinical diagnosis based on computed tomography (CT) could be used, as part of diagnosis standard of COVID-19 pneumonia. Addressing the problem that accuracy of CT-based traditional pneumonia classification diagnosis models is relatively low when employed for classification of community-acquired pneumonia (CP), COVID-19 pneumonia (NCP) and normal cases, a new network model is proposed which combines application of Swin Transformer and multi-head axial self-attention (MASA) mechanism, to analyze CT images and make intelligence-assisted diagnosis. The method in detail is to partially replace traditional multi-head self-attention (MSA) mechanism in encoders of Swin Transformer by MASA. The improved model is applied to train and test on commonly used pneumonia CT dataset CC-CCII. The results show that the proposed network outperforms traditional networks ResNet50 and Vision Transformer in indicators of accuracy, sensitivity and F1-measure. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

PVT-COV19D: COVID-19 Detection Through Medical Image Classification Based on Pyramid Vision Transformer

With the outbreak of COVID-19, a large number of relevant studies have emerged in recent years. We propose an automatic COVID-19 diagnosis model based on PVTv2 and the multiple voting mechanism. To accommodate the different dimensions of the image input, we classified the images using the Transformer model, sampled the images in the dataset according to the normal distribution, and fed the sampling results into the PVTv2 model for training. A large number of experiments on the COV19-CT-DB dataset demonstrate the effectiveness of the proposed method. Our method won the sixth place in the (2nd) COVID19 Detection Challenge of ECCV 2022 Workshop: AI-enabled Medical Image Analysis - Digital Pathology & Radiology/COVID19. Our code is publicly available at https://github.com/MenSan233/Team-Dslab-Solution. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A Framework of a User Interface Covid-19 Diagnosis Model

The world is facing the global challenge of COVID-19 pandemics, which is a topic of great concern.It is a contagious disease and infects others very fast.Artificial intelligence (AI) can assist healthcare professionals in assessing disease risks, assisting in diagnosis, prescribing medication, forecasting future well, and may be helpful in the current situation.Designing, a user-friendly Web application-based diagnosis model framework, is more useful in health care.The study focuses on a Web-based model for diagnosing the COVID-19 patients without direct contact with the patient.Chest CT scans have been important for the testing and diagnosing of COVID-19 disease.The Web-based model would take inputs, CT scan images, and users' symptoms and display classification results: NON-COVID-19 or COVID-19 infected. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Proposal and Implementation of a Model for Organizational Redesign and Its Influence on Digital Transformation in the Public Sector

This paper reviewed the literature on the topics of organizational redesign, digital transformation, strategic planning, process management, administrative simplification, continuous improvement, redesign and automation, and also considered the activities developed to implement organizational redesign in the quarantine declared by the Peruvian state as a result of COVID 19, with the purpose of proposing a method for organizational redesign towards digital transformation in public entities, with a strategic and operational approach. For the implementation of the strategic approach, the institutions that functionally depend on the Ministry of Education were involved, considering the current situation in relation to the operational and territorial capacities of each region, to develop the strategic and process design. Likewise, for the implementation of the operational approach, the results of the virtual course on process management for administrative simplification 2 were used, involving several institutions that proposed and implemented improvements towards the digitization of processes, promoting digital transformation. The results of the present work consider the effective time of the administrative procedures and the cost of implementation. The effective time of the procedures was reflected in a reduction of 11% and 52% in the reduction of the cost of the procedures. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Survey of Studies of COVID-19 Diagnosis Based on Deep Learning

The Corona Virus Disease 2019 COVID-19 is highly infectious and pathogenic, posing a serious threat to public safety.  Rapid and accurate detection and diagnosis of COVID-19 is key to the epidemic control. The existing detection and diagnosis methods are mainly based on nucleic acid tests or manual diagnosis using medical images.  However, nucleic acid tests are time-consuming and require special test boxes, while the manual diagnosis relies heavily on professional knowledge, takes longer time for analysis and often fail to detect concealed lesions. Since then, with the development of X-ray and Computer Tomography CT image datasets, researchers have built many deep learning-based COVID-19 detection and diagnosis models which effectively assist medical experts in the efficient diagnosis and treatment of COVID-19. This paper lists the mainstream image datasets for the detection and diagnosis of COVID-19 and related evaluation metrics. Then, it introduces the existing deep learning-based models for COVID-19 diagnosis from the perspectives of the model task and the image data type, and on this basis compares and analyzes the detection performance of the models in six different dimensions: Backbone network, data sets, image types, model performance, classification task types and park opening situation. In addition, this paper introduces the excellent application systems used to fight against COVID-19, and discusses the development trend of the studies in this field. © 2021, Editorial Office of Computer Engineering. All rights reserved.

Application of Convolutional Neural Network in COVID-19 Diagnosis

Since the outbreak and spread of COVID-19 in large areas of the world, the importance of rapid diagnosis of COVID-19 has increased. In the first week after the onset of COVID-19, the density of lesions is uneven, and chest CT is often difficult to show local subpleural ground-glass shadows, resulting in missed diagnosis. The COVID-19 intelligent diagnosis system based on the convolutional neural network algorithm can not only accurately identify the feature points, reduce the workload of doctors and improve the diagnosis efficiency, but also reduce the rate of missed diagnosis and misdiagnosis, which is conducive to epidemic control. © 2022 ACM.

Effects of image quality and quantity on building a competitive COVID-19 diagnosis model

The outbreak of a health crisis, such as Covid-19, leads to decisions that must combine efficiency and speed. Often there is a trade-off between these two values, as the faster a decision is made, the less information is considered. This paper presents a deep learning model pipeline that balances these two values with the primary goal of classifying human lung X-rays into three categories: pneumonia, covid-19 and normal. Through this process, we tried to explore whether the quality of an image can enhance the learning process to a greater extent as opposed to having larger number of images. For this purpose, we follow two approaches by viewing quality and quantity as competing objectives to increasing the level of information obtained. The first is through increasing the number of X-ray images in the dataset, and the second is through improving the quality of the X-ray images. In the first approach, our goal is achieved using a Generative Adversarial Network (GAN) to generate plasmatic covid-19 class X-rays, while in the second approach, we improve the resolution of the X-ray images. To find the hyperparameters in both approaches that lead to better system performance, we exploit the Particle Swarm Optimization (PSO) algorithm. Rapid training and hyperparameter tuning better perform through this algorithm. Our experiments depict the performance that our models, based on the two approaches, achieved. Accuracy reaches 93% while sensitivity reaches 90% over Covid-19 cases. Finally, we conclude which characteristic, quality or quantity, is most useful in our case. © 2021 IEEE.

Selection of the Optimal Diagnosis Model for COVID-19 Using the SAW and PROMETHEE II Methods

The COVID-19 outbreak is one thing that is the main focus for all countries in the world, including Indonesia. The diagnosis of COVID-19 can be done in various ways, such as checking symptoms, rapid-testing, swab-testing, and checking with X-rays. The application of machine learning in diagnosing a disease is one way that can be used to maximize the diagnosis of COVID-19 disease. This is what lies behind the need for optimization in the application of machine learning. This research goal is to determine the most optimal algorithm for diagnosing COVID-19 disease with a dataset in the form of Xray photos by using a decision-making methodology. The dataset in the form of Xray images will be processed utilizing image preprocessing (resize, grayscale, augmentation) and feature extraction (GLCM) methods. The researcher uses the Backpropagation algorithm, Recurrent Neural Network, SVM Linear, SVM Non-Linear, and Naive Bayes. The decision-making methodology used is Simple Additive Weighting and PROMETHEE II. Results of research in the form of ranking the optimal algorithm model in diagnosing COVID-19 according to the two decision making methodologies used. The five algorithms will take feature extraction of data as input and output 9 assessment criteria, including Accuracy, Precision, Recall Metric, ROC Curve, F1 Score, TNR, FPR, FNR, and time. The decision-making methodology used is Simple Additive Weighting and PROMETHEE II with 9 evaluation criteria as parameters. Results of research in the form of ranking the optimal algorithm model in diagnosing COVID-19 according to the two decision making methodologies used. The conclusion is that Backpropagation was the most optimal algorithm model in diagnosing COVID-19 disease with evaluation criteria values are AUC / ROC 0.935;Accuracy 0.893;F-score 0.888;Precision 0.908;Recalls 0.869;FPR 0.084;FNR 0.131;TNR 0.916;Time 1.023. © 2021 IEEE.

Electronic Nose With Detection Method for Alcohol, Acetone, and Carbon Monoxide in Coronavirus Disease 2019 Breath Simulation Model.

Electronic nose technology may have the potential to substantially slow the spread of contagious diseases with rapid signal indication. As our understanding of infectious diseases such as Corona Virus Disease 2019 improves, we expect electronic nose technology to detect changes associated with pathogenesis of the disease such as biomarkers of immune response for respiratory symptoms, central nervous system injury, and/or peripheral nervous system injury in the breath and/or odor of an individual. In this paper, a design of an electronic nose was configured to detect the concentration of a COVID-19 breath simulation sample of alcohol, acetone, and carbon monoxide mixture. After preheating for 24 hours, the sample was carried into an internal bladder of the collection vessel for analysis and data was collected from three sensors to determine suitability of these sensors for the application of exhaled breath analysis. Test results show a detection range in parts-per-million within the sensor detection range of at least 10-300 ppm. The output response of an MQ-2 and an MQ-135 sensor to a diverse environment of target gasses show the MQ-2 taking a greater length of time to normalize baseline drift compared to an MQ-135 sensor due to cross interferences with other gasses. The COVID-19 breath simulation sample was established and validated based on preliminary data obtained from parallel COVID-19 breath studies based in Edinburgh and Dortmund. This detection method provides a non-invasive, rapid, and selective detection of gasses in a variety of applications in virus detection as well as agricultural and homeland security.

Identifying COVID-19 cases in outpatient settings.

Case identification is an ongoing issue for the COVID-19 epidemic, in particular for outpatient care where physicians must decide which patients to prioritise for further testing. This paper reports tools to classify patients based on symptom profiles based on 236 severe acute respiratory syndrome coronavirus 2 positive cases and 564 controls, accounting for the time course of illness using generalised multivariate logistic regression. Significant symptoms included abdominal pain, cough, diarrhoea, fever, headache, muscle ache, runny nose, sore throat, temperature between 37.5 and 37.9 °C and temperature above 38 °C, but their importance varied by day of illness at assessment. With a high percentile threshold for specificity at 0.95, the baseline model had reasonable sensitivity at 0.67. To further evaluate accuracy of model predictions, leave-one-out cross-validation confirmed high classification accuracy with an area under the receiver operating characteristic curve of 0.92. For the baseline model, sensitivity decreased to 0.56. External validation datasets reported similar result. Our study provides a tool to discern COVID-19 patients from controls using symptoms and day from illness onset with good predictive performance. It could be considered as a framework to complement laboratory testing in order to differentiate COVID-19 from other patients presenting with acute symptoms in outpatient care.

Classification of COVID-19 by Compressed Chest CT Image through Deep Learning on a Large Patients Cohort.

Corona Virus Disease (COVID-19) has spread globally quickly, and has resulted in a large number of causalities and medical resources insufficiency in many countries. Reverse-transcriptase polymerase chain reaction (RT-PCR) testing is adopted as biopsy tool for confirmation of virus infection. However, its accuracy is as low as 60-70%, which is inefficient to uncover the infected. In comparison, the chest CT has been considered as the prior choice in diagnosis and monitoring progress of COVID-19 infection. Although the COVID-19 diagnostic systems based on artificial intelligence have been developed for assisting doctors in diagnosis, the small sample size and the excessive time consumption limit their applications. To this end, this paper proposed a diagnosis prototype system for COVID-19 infection testing. The proposed deep learning model is trained and is tested on 2267 CT sequences from 1357 patients clinically confirmed with COVID-19 and 1235 CT sequences from non-infected people. The main highlights of the prototype system are: (1) no data augmentation is needed to accurately discriminate the COVID-19 from normal controls with the specificity of 0.92 and sensitivity of 0.93; (2) the raw DICOM image is not necessary in testing. Highly compressed image like Jpeg can be used to allow a quick diagnosis; and (3) it discriminates the virus infection within 6 seconds and thus allows an online test with light cost. We also applied our model on 48 asymptomatic patients diagnosed with COVID-19. We found that: (1) the positive rate of RT-PCR assay is 63.5% (687/1082). (2) 45.8% (22/48) of the RT-PCR assay is negative for asymptomatic patients, yet the accuracy of CT scans is 95.8%. The online detection system is available: http://212.64.70.65/covid .