|
|
Friction and lubrication of fascia
Chmelík, Jiří ; Daniel, Matej (referee) ; Vrbka, Martin (advisor)
The diploma thesis was part of the project "Regeneration and lubrication of fascia with hyaluronan" of the company Contipro a.s., whose main goal is the development of an injectable medicinal product. The number of patients suffering from so-called myofascial lower back pain is increasing. The cause of the pain is increased hyaluronic acid, which is produced between the layers of the fascia. If the viscosity is low, the fascia layers are not affected and the coefficient of friction is low. The purpose of the product is to improve the sliding movement of the fascia and relieve patients of pain. The main component of the medicine is hyaluronic acid. The project included rheological and tribological analysis of hyaluronic acid samples. A tribological model of fascia in a pin-on-plate configuration was created for the analysis of the coefficient of friction. Based on the fascia models used, the dependence between the coefficient of friction and viscosity of native hyaluronic acid solutions was found. For models and real fascias, the native solution (Bonharen) was found to have better friction properties than hyaluronic acid derivatives. These analyzes have contributed not only to the development of the drug, but also to the emergence of other studies that would like to address the biotribology of fascia.
|
|
|
Image filtration effect on quality of subtractive angiography-based CT brain images of blood-vessels
Šipula, Samuel ; Nohel, Michal (referee) ; Chmelík, Jiří (advisor)
The aim of the bachelor thesis is to design filtering methods for the resulting quality of digital subtraction angiography. The role of filtration in this case is to suppress noise and strong structures to enhance vessel anatomy. Real patient data obtained using a computed tomography system are available for this purpose. In this work, the emphasis is mainly on noise suppression. Individual filtration techniques were implemented in MATLAB. The work further acquaints the reader with the theory of vascular supply to the brain, its imaging methods and the description of filters as discrete operators.
|
|
|
Intracranial hemorrhage localization in axial slices of head CT images
Kopečný, Kryštof ; Chmelík, Jiří (referee) ; Nemček, Jakub (advisor)
This thesis is focused on detection of intracranial hemorrhage in CT images using both one-stage and two-stage object detectors based on convolutional neural networks. The fundamentals of intracranial hemorrhage pathology and CT imaging as well as essential insight into computer vision and object detection are listed in this work. The knowledge of these fields of studies is a starting point for the implemenation of hemorrhage detector. The use of open-source CT image datasets is also discussed. The final part of this thesis is a model evaluation on a test dataset and results examination.
|
|
|
Segmentation and morphological analysis of mouse embryo choroid plexus
Parobková, Viktória ; Jakubíček, Roman (referee) ; Chmelík, Jiří (advisor)
Choroidálny plexus je regulovanou bránou medzi krvou a mozgovomiechovým mokom a má niekoľko funkcií spojených s nervovým systémom. Mnohé funkcie sú však stále neznáme, čo je spôsobené krehkosťou, umiestnením a tvarom plexu. Preto sa na prístup k tejto kľúčovej súčasti mozgu, ktorá sa nachádza v komorách, používajú neinvazívne techniky. Okrem toho existuje súvislosť medzi jeho tvarom a patologickými stavmi mozgu. Cieľom tohto projektu bolo extrahovať ChP 4. komory implementáciou segmentačných metód a následnou morfologickou analýzou s cieľom odhaliť zákonitosti medzi tvarom a ochorením.
|
|
|
Thrombi detection in main brain arteries in CT image data
Líška, Martin ; Nemček, Jakub (referee) ; Chmelík, Jiří (advisor)
The master’s thesis deals with automatic preprocessing, segmentation and consecutive analysis of volume data of anonymized patient CTA acquisitions with an indication of stroke. Preprocessing of volume data is an essential step for proper vascular tree segmentation and analysis. The region growing method was used to segment the vascular tree of the brain. After extracting the vascular tree, the labeling of individual branches was applied in the algorithm and the appropriate features were extracted. The analysis examined the features of vessel lengths, their diameter and local brightness profiles, which are important indicators of possible stenosis or occlusion of the main vessels of the brain. The output of the algorithm are various modalities of diagnostic, assisted visualizations of the segmented vascular tree. The segmentation and analysis algorithm of cerebrovascular system was created in the MATLAB programming environment.
|
|
|
Cell segmentation using convolutional neural networks
Hrdličková, Alžběta ; Chmelík, Jiří (referee) ; Vičar, Tomáš (advisor)
This work examines the use of convolutional neural networks with a focus on semantic and instance segmentation of cells from microscopic images. The theoretical part contains a description of deep neural networks and a summary of widely used convolutional architectures for image segmentation. The practical part of the work is devoted to the creation of a convolutional neural network model based on the U-Net architecture. It also contains cell segmentation of predicted images using three methods, namely thresholding, the watershed and the random walker.
|
|
|
Artificial intelligence for predicting sepsis from clinical signals
Šidlo, David ; Chmelík, Jiří (referee) ; Vičar, Tomáš (advisor)
This bachelor thesis deals with the issue of predicting sepsis from clinical data using artificial intelligence methods. In the theoretical part, a literature research is made on the basic principles and functioning of various methods of artificial intelligence. Greater emphasis was placed on recurrent neural networks. The aim of the practical part was to implement a suitable method in the chosen programming environment. The LSTM network and the temporal convolutional network TCN were chosen as suitable methods. The best results of the normalized value of the utility score were achieved by TCN, namely 0.377 and seven-layer LSTM 0.356.
|
|
|
Meta-analysis of bone tumorous lesions in spinal CT data using convolutional neural networks
Nantl, Ondřej ; Jakubíček, Roman (referee) ; Chmelík, Jiří (advisor)
This bachelor thesis deals with the use of convolutional neural networks in the meta-analysis of bone tumor lesions in CT image data. The theoretical part describes the anatomy and pathology of bone tissue, machine learning, discusses the functionality of convolutional neural networks and summarizes selected existing methods for computer-aided diagnosis of vertebra bone lesions. In the practical part, various types of models using convolutional neural networks were implemented and the networks were trained on an available augmented dataset. Finally, the results of various types of models were statistically evaluated, compared with available articles 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.
|
|
|
Method for Extending the Field of View for X-ray Computed Tomography with Submicron Resolution
Zemek, Marek ; Chmelík, Jiří (referee) ; Mézl, Martin (advisor)
Výpočetní tomografie je nástroj pro nedestruktivní inspekci vzorků, který je běžně používán v mnoha oblastech průmyslu a výzkumu. Některé tomografické přístroje umožňují snímání obrazů s prostorovým rozlišením pod jeden mikrometr. Zorné pole takovýchto přístrojů bývá malé, v rozsahu jednotek milimetrů či méně. Tím jsou omezeny rozměry vzorků, což je značně limitující. Toto omezení lze překonat pomocí různých technik pro rozšíření zorného pole. Jedna takováto dříve publikovaná metoda byla v této práci upravena a implementována pro přístroj Rigaku Nano3DX. Tato technika téměř zdvojnásobuje zorné pole přístroje bez nutnosti většího detektoru. Implementovaný přístup byl testován pomocí umělých i skutečných dat, a jeho účinnost byla zhodnocena subjektivně i objektivně, pomocí vizuální kontroly a metrik kvality obrazu. Hodnocení je převážně založeno na srovnání obrazů rekonstruovaných pomocí této metody s obrazy získanými pomocí většího detektoru. Implementovaná technika rozšíření zorného pole poskytuje věrné rekonstrukce vzorku, srovnatelné se zmíněnými protějšky.
|
guest ::
