|
|
COVID-19 disease classification based on analysis of chest X-rays
Šteflík, Dominik ; Kiac, Martin (referee) ; Myška, Vojtěch (advisor)
This diploma thesis addresses the development and evaluation of artificial intelligence algorithms for classifying COVID-19 disease from chest X-ray images. Given the severity and impact of the COVID-19 pandemic on the global population, the ability to rapidly and accurately diagnose diseases from radiographic images has become critical. This study synthesizes current advancements in image processing and deep learning to evaluate the application of several novel classification methods in practice. Using a dataset obtained from a Czech medical environment, these methods are analyzed and validated in order to examine their effectiveness and accuracy in real life scenarios. The methods chosen for this study, COVID-Net, DarkCovidNet, and CoroNet, were selected due to their availability, widespread use and proven effectiveness in the field. The core of the thesis is the design of a convolutional neural network tailored to extract and learn from the subtle features present in X-ray images indicative of COVID-19. This initiative confronted significant challenges posed by variable acquisition parameters of X-ray images, which can substantially affect diagnostic accuracy. The uniformity of these parameters is crucial for reliable analysis, underscoring the importance of rigorous preprocessing techniques. In response, advanced normalization, contrast adjustment, and augmentation procedures were implemented to standardize the input data. The convolutional network itself employs a series of convolutional, pooling, and fully connected layers, optimized to handle the nuanced variations present in medical imaging data. Notably, the network architecture incorporates an attention mechanism, implemented through a Squeeze-and-Excitation block, to dynamically adjust the importance of different channels in the input image. By integrating these elements, the network model is trained to focus on significant features within the X-ray images, allowing it to distinguish subtle indicators of COVID-19 effectively. Furthermore, this work discusses the potential of integrating these AI-driven diagnostic tools into existing healthcare infrastructures to enhance early detection and treatment of COVID-19. The findings indicate that leveraging artificial intelligence in medical imaging can substantially aid in managing and controlling disease outbreaks, ultimately contributing to better health outcomes.
|
|
|
Bloodstream infection in patients during the COVID-19 pandemic in of General University Hospital in Prague
BAUER, Kristýna
Blood stream infection is one of the serious life-threatening conditions of hospitalized patients with coronavirus disease during the COVID-19 pandemic in the Czech Republic. This is the penetration of microorganisms into the bloodstream, which is accompanied by symptoms of a general infection. The most common consequence is the development of sepsis. The aim of the laboratory examination is to obtain a reliable blood culture result. Such a result can only be achieved if all procedures are followed, from the indication by the doctor to the process of sampling by the medical staff into the bottles directly intended for this purpose. Taking blood cultures confirms or excludes the presence of bacteria in the bloodstream. Blood cultures are the gold standard for diagnosing bloodstream infections. A detection culture is used for hemocultivation of the BacT/Alert 3D system, which is based on the colorimetric detection of CO2 produced by growing microorganisms in blood cultures.
|
|
|
Impacts of COVID-19 Pandemic on the Mental Health of Pregnant Women in the Czech Republic
Venclů, Viktorie ; Pařízek, Antonín (advisor) ; Richtárová, Adéla (referee)
This bachelor thesis examines the impact that the COVID-19 pandemic had on the mental health of pregnant women in the Czech Republic. The theoretical part includes the fundamental information essential for understanding the context of the topic. It focuses on the disease itself, the emergence and development of its pandemic in the Czech Republic, and its course in pregnant women. Additionally, it delves into the psychology of pregnant women and into mental health in general. The thesis also summarizes the results of some Czech studies investigating the impact of the pandemic on the mental health of the Czech population. The research section investigates the influence of the pandemic on the mental health of pregnant women through regression analysis. The numbers of births among women who required a certain form of psychiatric intervention during pregnancy, or within six months after childbirth are examined. The analysed dataset was obtained from the national registers NRRZ and NRHZS and includes records from January 2015 to December 2021. A regression log- log model was created for analysis, which did not show a statistically significant impact of the pandemic on the number of births for these women. Possible reasons for the different results between this research and mentioned studies are discussed...
|
|
|
COVID-19 and political preferences through stages of the pandemic: the case of the Czech Republic
Bičáková, Alena ; Jurajda, Štěpán
We track the effects of the COVID-19 pandemic on political preferences through ‘high’ and ‘low’ phases of the pandemic. We ask about the effects of the health and the economic costs of the pandemic measured at both personal and municipality levels. Consistent with the literature, we estimate effects suggestive of political accountability of leaders during ‘high’ pandemic phases. However, we also find that the pandemic political accountability effects are mostly short-lived, and do not extend to the first post-pandemic elections.
|
|
|
Web Application for Takeways in Times of Covid19 Quarantine
Žák, David ; Rozman, Jaroslav (referee) ; Hrubý, Martin (advisor)
The aim of this thesis is to create a web application enabling management of offers and orders for businesses affected by the Covid-19 pandemic. The application is implemented using Vue.js, PHP and MySQL. The thesis consists of a theoretical and practical part. The theoretical part focuses on current possibilities of web application development and technologies used in this thesis. The practical part describes the designing process, implementation and testing of the application. The resulting application allows customers to browse through offers and to place an order. Additionally, for individual business it provides an option of managing their offer, orders and settings through the administration.
|
|
|
Epidemiological modeling of Covid-19
Schubert, Richard ; Kašpar, Jakub (referee) ; Mézl, Martin (advisor)
This thesis deals with the continuous epidemiological deterministic compartmental models and the COVID-19 pandemic modeling distinctive features. The effect of different probability distributions of individuals stay in compartments is studied numerically in relation to basic reproductive number and the final size of the epidemic, respectively. New model for a retrospective analysis of the first half of 2020 northern Italy epidemiological data is proposed. The model parameters estimation is performed using minimisation of weighted sum of squared residuals and the search through parameter space with BFGS algorithm implementation.
|
|
|
Face masks and respirators as protection against viruses and bacteria
Varga, Michal ; Mišík, Ondrej (referee) ; Lízal, František (advisor)
Pandemic caused by virus SARS-CoV-2 brought high attention to face masks and raised some questions about their filtration efficiency and performance affecting parameters such as high humidity, long term usage, fit factor, or possible decontamination methods for usage prolonging. In this thesis, mechanisms of SARS-CoV-2 transmission and structure and materials of face masks are firstly discussed. Then mechanisms of particle deposition on filter fibers are described. Subsequently standards of surgical masks, cloth masks and respirators are described and compared, with detail on carbon dioxide concentration under respirator. Nanoparticles and their possible effects on enhancing face mask parameters are briefly characterized. Then filtration efficiency and affecting parameters are evaluated. And finally possible decontamination methods for face masks reusability are summarized.
|
|
|
NEWkus - Sara and Bara
Wollasch, Sara ; Olivová, Kateřina (referee) ; Klodová, Lenka (advisor)
The bachelor's thesis presents a series of events of the artistic duo NEWkus. Artistic duo NEWkus deals with transformation of relationships and solid definition of the concept of a NEWkus’s body. It copes with the isolation which was caused by the coronavirus pandemic and with the apathy caused by the monotonous lifestyle in an enclosed space with still the same person and the impossibility of meeting within the duo NEWkus. Thanks to our series of events in the home environment, the group is aware of its own existence on a much wider scale, it finds that it is not only two-member, that its structure is more extensive. The series of realized events is built on the border of social and artistic experiment and intimate realism. The whole experience is screened in a single space, as part of a festival called Dny NEWkusu (The NEWkus Days). The space consists of an object inspired by a screen,which inner surface is adapted to the image and needs of both authors..The spectator is thus allowed to meet the story that will be presented from many points of views during the festival and thus provide an opportunity to mingle with the body of NEWkus in real time and space.
|
|
|
NEWKUS - Bara and Sara
Smékalová, Barbora ; Alster, Darina (referee) ; Klodová, Lenka (advisor)
The diploma thesis consists of a series of events by the art duo NEWkus. The NEWkus art duo deals with the transformation of relationships and the overall definition of the NEWkus body concept. It copes with the isolation caused by the coronavirus pandemic as well as with the apathy caused by the monotonous lifestyle in an enclosed space with the same person and the impossibility of meeting within the NEWkus duo. Thanks to a series of events in the home environment, the group is aware of its own existence on a much wider scale, it finds that it is not only two-member, that its structure is more extensive. The series of realized events is built on the borders of social, artistic experiment and intimate realism. The whole experience is screened in a single space, as part of the NEWkus Days festival. The space is defined by an object inspired by a screen, the internal environment of which is adapted to the image and the needs of both authors. The spectator is thus allowed to meet the story, which will be presented from many angles during the festival and will provide the opportunity to blend with the body of NEWkus in real time and space.
|
|
|
Lab Automation with SCARA Robot
Machala, Jan ; Lang, Stanislav (referee) ; Matoušek, Radomil (advisor)
The aim of this thesis is to design and program a robotic cell for processing Covid-19 laboratory samples. To prevent the leakage of hazardous substances into the environment, the entire robotic cell is restricted to the space of a laminar box. The Epson LS3-B SCARA robot was chosen for handling the tubes. The robotic cell was designed using a digital twin in the simulation environment of Epson RC+ software. The digital twin facilitated the prototyping of the robot end effector and helped to detect any collisions that may have occurred in the confined space. After successful design using the digital twin, this robot cell was assembled and tested in a real-world environment.
|
guest ::
