National Repository of Grey Literature 3 records found  Search took 0.00 seconds. 
Machine learning based method for medical image generation
Hrtoňová, Valentina ; Chmelík, Jiří (referee) ; Jakubíček, Roman (advisor)
This thesis deals with the use of generative adversarial networks for the synthesis of medical images. Firstly, artificial neural networks are described with a focus on convolutional neural networks and generative adversarial networks. Applications of generative adversarial networks in medicine are reviewed, and selected publications on the topic of medical image synthesis are described in more detail. Furthermore, multiple models of generative adversarial networks are designed and implemented in the Python programming language. First is a model of the deep convolutional generative adversarial network and the model „pix2pix“ for the generation of skin lesion images. Moreover, the „pix2pix“ model is used for the generation of both axial and sagittal CT images of the spine. Finally, the results of generating medical images using generative adversarial networks are presented and discussed.
Machine learning based method for medical image generation
Hrtoňová, Valentina ; Chmelík, Jiří (referee) ; Jakubíček, Roman (advisor)
This thesis deals with the use of generative adversarial networks for the synthesis of medical images. Firstly, artificial neural networks are described with a focus on convolutional neural networks and generative adversarial networks. Applications of generative adversarial networks in medicine are reviewed, and selected publications on the topic of medical image synthesis are described in more detail. Furthermore, multiple models of generative adversarial networks are designed and implemented in the Python programming language. First is a model of the deep convolutional generative adversarial network and the model „pix2pix“ for the generation of skin lesion images. Moreover, the „pix2pix“ model is used for the generation of both axial and sagittal CT images of the spine. Finally, the results of generating medical images using generative adversarial networks are presented and discussed.
Skin lesions prevention in perioperative care
POHLOVÁ, Lucie
Thesis objectives: The diploma thesis deals with the issue of prevention of skin lesions in perioperative care. In the theoretical part, the current state of knowledge is presented concerning the pressure ulcers identification due to the persisting real problems in differential diagnostics in clinical practice. Further, the thesis deals with the issue of wet and thermal lesions, which occur also during the perioperative care. In the empirical part of the diploma thesis, the first objective was to find the frequency of documented occurrence of decubital lesions in connection with the surgery in Jihlava Hospital for a period of one year. The second objective of the thesis was to find out whether, and what barriers exist when using specific preventive measures. The last aim of the diploma thesis was to compare the efficiency of preventive measures from the point of view of perioperative nurses and nurses from service units. Three hypotheses were formulated to meet the objectives of the thesis. Method for achieving the objectives: The set objectives were achieved through a retrospective analysis of the hospital information system data and a quantitative questionnaire survey. The study included nurses working in surgery, orthopaedics, traumatology, intensive care units and perioperative nurses in Jihlava Hospital. The total number of respondents was 140. Scientific benefits of the thesis: The research implies that the use of prophylactic aids in pre-operative preparation contributes significantly to reducing the risk of skin lesions. The addressed set of nurses did not indicate any serious barriers to their application and, on the contrary, considered it to be very effective. The results of the thesis can be used in practice, especially in a specific health facility for further care improvement. The findings and conclusions: On the research group we have verified that the declared use of preventive strategies in the area of prevention of lesions in perioperative care differs according to the type and focus of the workplace; (p = 0.000) the least frequent use was declared by the general nurse from orthopaedics, however, the methods used did not differ (p = 0,220). In addition, we found out that there was a statistically significant difference in the opinion on efficiency of prophylactic covering in lesion prevention (p = 0.001, the worst evaluation was by the respondents from orthopaedics) but only 2 respondents stated negative experience with their use.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.