|
|
Deep-learning-based pattern detection in medical images
Koščová, Zuzana ; Vičar, Tomáš (referee) ; Jakubíček, Roman (advisor)
This Bachelor thesis deals with Deep-learning-based pattern detection in medical images. For better understanding of a subject artificial neural network and convolutional neural network (CNN) are described at first. Next chapter is focused on specific detection methods which use CNN. Within a bachelor thesis a dataset of abdominal CT a MRI scans was created. Faster R-CNN and YOLO algorithms were trained and tested on acquired scans for liver detection. Implementation of chosen methods took place in Python programming language using the Pytorch library. Finally, detection results and possible use in medicine are discussed.
|
|
|
Reduction of metal artifacts in CT data with submicron resolution
Víteček, Jiří ; Mézl, Martin (referee) ; Jakubíček, Roman (advisor)
This diploma thesis deals with reduction of metal artifacts in CT data with submicron resolution. The first part of this thesis briefly describes x-ray computed tomography followed by the description of artifacts of tomographic images and existing approaches of the reduction of metal artifacts. In the second part proposed methods of reduction of metal artifacts and their implementation in Matlab programming environment are described. Finally functionality of algorithms is tested on a newly created database and the results are compared, evaluated and discussed.
|
|
|
Calculation of advanced diffusion parameters in brain grey matter from DKI MRI images
Pánková, Olga ; Jakubíček, Roman (referee) ; Minsterová, Alžběta (advisor)
Thesis named Calculation of advanced diffusion parameters in brain grey matter from DKI MRI images deals with processing of diffusion-weighted images from DKI. The thesis contains review of literature on principle of diffusion, influence of diffusion on MRI, calculation of DTI and DKI parameters and clinical application of diffusion-weighted maps with focus on grey matter. The thesis focuses on software tools for processing and pre-processing DTI and DKI. The practical part consisted of two sections. Two different softwares were used to calculate maps of diffusion parameters. Diffusion parameters from anatomical structure sunstantia nigra were compared between group of healthy controls and patients with Parkinson’s disease. This comparison did not show any statisticaly significant difference. In the second step, a script for creating diffusion maps in software Diffusinal Kurtosis Estimator was made.
|
|
|
Anatomy based landmark detection in brain CT scans
Krajčiová, Alexandra ; Harabiš, Vratislav (referee) ; Jakubíček, Roman (advisor)
Manual detection of anatomical landmarks from head CT (Computed Tomography) scans is time-consuming task prone to observer errors. In addition, the accuracy of the detection correlates with image quality. The aim of this work is to create an algorithm that will perform automatic detection of anatomical landmarks. These landmarks can be later used to form radiological lines, which finds its application in CT scanning. SVM (Support Vector Machines) and HOG (Histograms of Oriented Gradients) features was chosen for anatomical landmark detection. The achieved results, possibilities of further progress and improvement of detection are summarized in the conclusion.
|
|
|
Automatic smoothing 3D models of cranial embryonic mouse cartilage
Kočendová, Kateřina ; Harabiš, Vratislav (referee) ; Jakubíček, Roman (advisor)
The focus of this thesis is the smoothing of manually segmented 3D models of mouse embryo craniofacial cartilege. During the process of manual segmentation, artefacts and other imperfections appear in the final models and need to be repaired. Firstly, manual segmentation is corrected using gradients and thresholding. Subsequent smoothing methods are constructed based on theoretical research. Algorithmizing is executed in the MATLAB environment. All the designed algorithms are then tested on selected models. Statistical evaluation is determined using the Srensen–Dice coefficient, where manually smoothened models cleared of all artefacts are used as the gold standard.
|
|
|
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.
|
|
|
Image recognition for robotic hand
Labudová, Kristýna ; Jakubíček, Roman (referee) ; Harabiš, Vratislav (advisor)
This thesis concerns with processing of embedded terminals’ images and their classification. There is problematics of moire noise reduction thought filtration in frequency domain and the image normalization for further processing analyzed. Keypoints detectors and descriptors are used for image classification. Detectors FAST and Harris corner detector and descriptors SURF, BRIEF and BRISK are emphasized as well as their evaluation in terms of potential contribution to this work.
|
|
|
Vertebra detection and identification in CT oncological data
Věžníková, Romana ; Harabiš, Vratislav (referee) ; Jakubíček, Roman (advisor)
Automated spine or vertebra detection and segmentation from CT images is a difficult task for several reasons. One of the reasons is unclear vertebra boundaries and indistinct boundaries between vertebra. Next reason is artifacts in images and high degree of anatomical complexity. This paper describes the design and implementation of vertebra detection and classification in CT images of cancer patients, which adds to the complexity because some of vertebrae are deformed. For the vertebra segmentation, the Otsu’s method is used. Vertebra detection is based on search of borders between individual vertebra in sagittal planes. Decision trees or the generalized Hough transform is applied for the identification whereas the vertebra searching is based on similarity between each vertebra model shape and planes of CT scans.
|
|
|
Segmentation of cranial bone after craniectomy
Vavřinová, Pavlína ; Chmelík, Jiří (referee) ; Jakubíček, Roman (advisor)
This thesis deals with the segmentation of cranial bone in CT patient’s data after craniectomy. The U-Net architecture in 2D and 3D variant were selected for the intention of solving this problem. Jaccard index for 2D U-Net was evaluate as 89,4 % and for 3D U-Net it was 67,1 %. In the area after surgical intervention evaluating index has smaller difference between both variant, the average success rate of skull classification was 98,4 % for 2D U-Net and 97,0 % for 3D U-Net.
|
|
|
Detection of intracranial hemorrhages in head CT data
Nemček, Jakub ; Jan, Jiří (referee) ; Jakubíček, Roman (advisor)
This thesis deals with the detection of intracranial haemorrhages and their type classification in head CT images. The method of haemorrhages detection is based on a series of classifiers of the presence and type of haemorrhages in 2D CT slices in axial, sagittal and coronal plane, that may localise the bleedings and determine their types. The classifiers are based on the convolutional neural network architecture Inception-ResNet-v2. The head CT dataset CQ500 which is made available for public access, is used for the experiments. The thesis describes an additional manual annotation of the data, as the available annotations are insufficient for the purposes of the experiments. This thesis includes a theoretical basis of the essential medical knowledge, machine learning based classification and detection methods, and the detection algorithm proposal, realisation and testing. The algorithm performance is evaluated and discussed together with the potential implementation of the algorithm in computer-aided diagnosis systems.
|
guest ::
RSS feed.