|
|
Time development analysis of treated lesion in spinal CT data
Nohel, Michal ; Jan, Jiří (referee) ; Jakubíček, Roman (advisor)
This diploma thesis is focused on time-development analysis of treated lesion in CT data. The theoretical part of the thesis deals with the anatomy, physiology, and pathophysiology of the spine and vertebral bodies. It further describes diagnostic and therapeutic options for the detection and treatment of spinal lesions. It contains an overview of the current state of usage of time-development analysis in oncology. The problems of the available databases are discussed and new databases are created for subsequent analysis. Futhermore, the methodology of time-development analysis according to the shape characterization and the size of the vertebral involvement is proposed. The proposed methodological approaches to feature extraction are applied to the created databases. Their choice and suitability is discussed, including their potential for possible usege in clinical practice of monitoring the development and derivation of characteristic dependences of features on the patient's prognosis.
|
|
|
Removing noise in images using deep learning methods
Strejček, Jakub ; Jakubíček, Roman (referee) ; Vičar, Tomáš (advisor)
This thesis focuses on comparing methods of denoising by deep learning and their implementation. In the last few years, it has become clear that it is not necessary to have paired data, as for noisy and clean pictures, to train convolution neural networks but it is sufficient to have only noisy pictures for denoising in particular cases. By using methods described in this thesis it is possible to effectively remove i.e. additive Gaussian noise and what more, it is possible to achieve better results than by using statistic methods, which are being used for denoising these days.
|
|
|
Analysis of training dataset influence on the efficiency of segmentation
Benešovská, Veronika ; Vičar, Tomáš (referee) ; Jakubíček, Roman (advisor)
Microbial structures are present in every living organism, so it is important to classify them for subsequent research of their origin and function. Bruker, s.r.o is developing the MBT Pathfinder for this purpose, which automates the transfer of colonies to MALDI plates, where the subsequent analysis of the sample takes place. Transferred colonies can be selected manually or using an algorithm that ensures automatic colony segmentation. This algorithm must be learned on a training set, which has huge influence on its accuracy. This work deals with measuring the influence of a dataset on the accuracy of this learning algorithm.
|
|
|
Methods of Segmentation and Identification of Deformed Vertebrae in 3D CT Data of Oncological Patients
Jakubíček, Roman ; Flusser, Jan (referee) ; Kozubek, Michal (referee) ; Jan, Jiří (advisor)
In this doctoral thesis, the design of algorithms enabling the implementation of a fully automatic system for vertebrae segmentation in 3D computed tomography (CT) image data of possibly incomplete spines, in patients with bone metastases and vertebral compressions is presented. The proposed algorithm consists of several fundamental problems: spine detection and its axis determination, individual vertebra localization and identification (labeling), and finally, precise segmentation of vertebrae. The detection of the spine, specifically identifying its ends, and determining the course of the spinal canal, combines several advanced methods, including deep learning-based approaches. A novel growing circle method has been designed for tracing the spinal cord canal. Further, the innovative spatially variant filtering of brightness profiles along the spine axis leading to intervertebral disc localization has been proposed and implemented. The discs thus obtained are subsequently identified via comparing the tested vertebrae and model of vertebrae provided by a machine-learning process and optimized by dynamic programming. The final vertebrae segmentation is provided by the deformation of the complete-spine intensity model, utilizing a proposed multilevel registration technique. The complete proposed algorithm has been validated on testing databases, including also publicly available datasets. This way, it has been proven that the newly proposed algorithms provide results at least comparable to other author’s algorithms, and in some cases, even better. The main strengths of the algorithms lie in high reliability of the results and in the robustness to even strongly distorted vertebrae of oncological patients and to the occurrence of artifacts in data; moreover, they are capable of identifying the vertebra labels even in incomplete spinal CT scans. The strength is also in the complete automation of the processing and in its relatively low computational complexity enabling implementation on standard PC hardware. The system for fully automatic localization and labeling of distorted vertebrae in possibly incomplete spinal CT data is presented in this doctoral thesis. The design of algorithms enabling the implementation utilizes several novel approaches, which were presented at international conferences and published in the journal Jakubicek et al. (2020). Based on the results of the experimental validation, the proposed algorithms seem to be routinely usable and capable of providing fully acceptable input data (identified and precisely segmented vertebrae) as needed in the subsequent automatic spine bone lesion analysis.
|
|
|
Segmentation of bone lesions in spinal CT data
Zaťko, Martin ; Chmelík, Jiří (referee) ; Jakubíček, Roman (advisor)
The aim of the bachelor thesis was to get acquainted with the anatomy and oncological diseases of spine. Search for segmentation techniques and implement my chosen machine learning technique for the task of segmenting bone lesions of vertebral bodies. The U-net architecture of convolutional neural networks, which is generally widely used in the segmentation of biomedical images, was selected and implemented. The results obtained are high enough for the network to be used for initial rough detection and segmentation, but its use in the clinical world is not recommended.
|
|
| |
|
|
Estimation of bone mineral density of cancellous vertebral bone in multi-energy CT data
Líška, Martin ; Jakubíček, Roman (referee) ; Chmelík, Jiří (advisor)
The principle of the BMD estimation method presented in this thesis consists in the tomographic scanning of the axial skeleton by a CT system with two different energies. The BMD estimation method was applied to acquisitions scanned by CT system IQon Spectral CT (Philips) on seven patients, two men and five women, in the lumbo-sacral region. For the functionality of the method, it is necessary to know the standardized amounts of selected elemental components contained in a given tissue, specifically in the cancellous bone of the vertebra. In the first part, the thesis deals with the theoretical part of solving the estimation of BMD from dual-energy CT data, two equations with several unknowns and their modification. The practical part deals with the program solution of the method of calculating the estimation of bone minerals in dual-energy CT data. The outputs of the presented BMD estimation method were processed and statistically compared with the other two phantom-less BMD estimation methods. The functionality of the method and statistical processing were solved in MATLAB and STATISTICA softwares.
|
|
|
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.
|
|
|
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.
|
|
| |
guest ::
