|
|
Detection of foreign objects in X-ray chest images using machine learning methods
Matoušková, Barbora ; Kolář, Radim (referee) ; Chmelík, Jiří (advisor)
Foreign objects in Chest X-ray (CXR) cause complications during automatic image processing. To prevent errors caused by these foreign objects, it is necessary to automatically find them and ommit them in the analysis. These are mainly buttons, jewellery, implants, wires and tubes. At the same time, finding pacemakers and other placed devices can help with automatic processing. The aim of this work was to design a method for the detection of foreign objects in CXR. For this task, Faster R-CNN method with a pre-trained ResNet50 network for feature extraction was chosen which was trained on 4 000 images and lately tested on 1 000 images from a publicly available database. After finding the optimal learning parameters, it was managed to train the network, which achieves 75% precision, 77% recall and 76% F1 score. However, a certain part of the error is formed by non-uniform annotations of objects in the data because not all annotated foreign objects are located in the lung area, as stated in the description.
|
|
|
Identification of vertebrae type in CT data by machine learning methods
Matoušková, Barbora ; Kolář, Radim (referee) ; Chmelík, Jiří (advisor)
Identification of vertebrae type by machine learning is an important task to facilitate the work of medical doctors. This task is embarrassed by many factors. First, a spinal CT imagining is usually performed on patiens with pathologies such as lesions, tumors, kyphosis, lordosis, scoliosis or patients with various implants that cause artifacts in the images. Furthermore, the neighboring vertebraes are very similar which also complicates this task. This paper deals with already segmented vertebrae classification into cervical, thoracic and lumbar groups. Support vector machines (SVM) and convolutional neural networks (CNN) AlexNet and VGG16 are used for classification. The results are compared in the conclusion.
|
|
| |
|
| |
|
| |
|
|
Detection of foreign objects in X-ray chest images using machine learning methods
Matoušková, Barbora ; Kolář, Radim (referee) ; Chmelík, Jiří (advisor)
Foreign objects in Chest X-ray (CXR) cause complications during automatic image processing. To prevent errors caused by these foreign objects, it is necessary to automatically find them and ommit them in the analysis. These are mainly buttons, jewellery, implants, wires and tubes. At the same time, finding pacemakers and other placed devices can help with automatic processing. The aim of this work was to design a method for the detection of foreign objects in CXR. For this task, Faster R-CNN method with a pre-trained ResNet50 network for feature extraction was chosen which was trained on 4 000 images and lately tested on 1 000 images from a publicly available database. After finding the optimal learning parameters, it was managed to train the network, which achieves 75% precision, 77% recall and 76% F1 score. However, a certain part of the error is formed by non-uniform annotations of objects in the data because not all annotated foreign objects are located in the lung area, as stated in the description.
|
|
|
Didactic games in geography teaching
Matoušková, Barbora ; Matějček, Tomáš (advisor) ; Havelková, Lenka (referee)
This thesis deals with the use of didactic games in geography lessons in Czech schools. Its main goal is to use the questionnaire survey to find the so-called examples of good practice in schools. In the introduction there is a short literature search and definition of the term didactic game according to various authors. The main research method is an electronic questionnaire. A total of 72 faculty schools of the Faculty of Science of Charles University were addressed. Finally, 30 primary and secondary school teachers took part in the research.The questionnaire was divided into four parts. In the first part the general opinion of teachers on the concept of didactic game was investigated. The following section of questions was focused on teachers who use didactic games - the extent of games usage, in which topics of geography, as well as specific examples of games and their evaluation. The third section of the questions was intended for teachers who do not use games and found out the reasons that prevent them from using games. The last section of the questions deals with the sociodemographic characteristics of the research sample. The work contains analysis and interpretation of the questionnaire survey, including graphic outputs. The results were processed qualitatively and quantitatively...
|
|
|
Identification of vertebrae type in CT data by machine learning methods
Matoušková, Barbora ; Kolář, Radim (referee) ; Chmelík, Jiří (advisor)
Identification of vertebrae type by machine learning is an important task to facilitate the work of medical doctors. This task is embarrassed by many factors. First, a spinal CT imagining is usually performed on patiens with pathologies such as lesions, tumors, kyphosis, lordosis, scoliosis or patients with various implants that cause artifacts in the images. Furthermore, the neighboring vertebraes are very similar which also complicates this task. This paper deals with already segmented vertebrae classification into cervical, thoracic and lumbar groups. Support vector machines (SVM) and convolutional neural networks (CNN) AlexNet and VGG16 are used for classification. The results are compared in the conclusion.
|
|
|
Effect of temperature on life cycle of zygomycetes
Matoušková, Barbora ; Kubátová, Alena (advisor) ; Nováková, Alena (referee)
This thesis is aiming on zygomycetes, their importance, their current position in the Fungi kingdom and above all their ecological demands. The paper summarizes the influence of temperature on their life cycle (i.e. primarily on the growth, reproduction and production of metabolites). It focuses mainly on psychrophilic and thermophilic species and describes the mechanisms of adaptation to unfavorable living conditions. To investigate the influence of temperature, zygomycetes are exceptionally suitable model organisms, e.g. in the order Mucorales we can find relatives growing in diametrically different environments. Among the mechanisms of extreme temperature adaptation for zygomycetes are in particular trehalose production, a change in the degree of saturation of membrane phospholipids and the production of membrane stabilizing agents - sterols, glycolipids and sugar alcohols. Key words: temperature, growth, reproduction, life cycle, habitat, extremophiles, Mucoromycotina, Mortierellomycotina
|
|
|
Quality of education of pregnant women in nutrition during gravidity and suggestion for its improvement
Matoušková, Barbora ; Marádová, Eva (advisor) ; Komorná, Marie (referee)
The Diploma thesis deals with nutrition of women during pregnancy. The work is divided into theoretical and practical part. The theoretical part summarizes the dietary recommendations for pregnant women. The practical part is divided into two parts - a research and an educational part. In the research section are evaluated results of the survey, which pointed to some gaps in the knowledge of the respondents. It was also found, that the respondents are not satisfied with nutritional information that they receive from medical staff, and therefore use other information sources. Even for women with higher level of education is difficult to understand to information from different sources. For these reasons, in the educational part of the thesis has been prepared a simple material that would help women to understand dietary changes during pregnancy, including risk factors. The material is intended for women without special dietary measures and in its creation were used informations from the theoretical part. KEYWORDS nutrition, pregnancy, diet, fetus, education
|
guest ::
