|
|
Methods of Detection, Segmentation and Classification of Difficult to Define Bone Tumor Lesions in 3D CT Data
Chmelík, Jiří ; Flusser,, Jan (referee) ; Kozubek, Michal (referee) ; Jan, Jiří (advisor)
The aim of this work was the development of algorithms for detection segmentation and classification of difficult to define bone metastatic cancerous lesions from spinal CT image data. For this purpose, the patient database was created and annotated by medical experts. Successively, three methods were proposed and developed; the first of them is based on the reworking and combination of methods developed during the preceding project phase, the second method is a fast variant based on the fuzzy k-means cluster analysis, the third method uses modern machine learning algorithms, specifically deep learning of convolutional neural networks. Further, an approach that elaborates the results by a subsequent random forest based meta-analysis of detected lesion candidates was proposed. The achieved results were objectively evaluated and compared with results achieved by algorithms published by other authors. The evaluation was done by two objective methodologies, technical voxel-based and clinical object-based ones. The achieved results were subsequently evaluated and discussed.
|
|
|
Acquisition, Modeling and Signal Processing in Ultrasound Perfusion Imaging
Mézl, Martin ; Kozubek, Michal (referee) ; Flusser,, Jan (referee) ; Jiřík, Radovan (advisor)
This work deals with possibilities of ultrasound perfusion analysis for the absolute quantification of perfusion parameters. In the theoretical part of this work are discussed possibilities of using of the ultrasound contrast agents and approaches for the perfusion analysis. New methods for the perfusion analysis are suggested and tested in the practical part of this work. The methods are based on convolutional model in which the concentration of the contrast agent is modeled as aconvolution of the arterial input function and the tissue residual function. The feasibility of these methods for the absolute quantification of perfusion parameters is shown on data from phantom studies, simulations and also preclinical and clinical studies. The software for the whole process of the perfusion analysis was developed for using in hospitals.
|
|
|
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.
|
|
|
Analysing Videokymograms Using Classical and Deep Learning Methods
Zita, Aleš ; Flusser, Jan (advisor) ; Aichinger, Philipp (referee) ; Jiřík, Radovan (referee)
Title: Analysing Videokymograms Using Classical and Deep Learning Methods Author: RNDr. Aleš Zita Institute: Institute of Information Theory and Automation, the Czech Academy of Sciences Supervisor: Prof. Ing. Jan Flusser, DrSc., Department of Image Processing Abstract: Videokymography (VKG) belongs to a family of medical imaging techniques capable of human larynx function visualization. Images produced by this method are ideal for automatic processing. In the last few years, the performance of deep learning systems increased significantly. In some areas, the machine learning approach exceeds the human experts in speed and accuracy. This doctoral thesis focuses on the continuous development of VKG image automatic analysis and touches on the possibility of con- necting the classical approach to Videokymographic image processing with the modern computer vision approach. Keywords: Videokymography, Medical Imaging, Digital Image Processing, Computer Vision, Machine Learning 1
|
|
|
Recognition of Partially Occluded Objects
Krolupper, Filip ; Flusser, Jan (advisor) ; Sojka, Eduard (referee) ; Peters, Gabriele (referee)
In this thesis we focus on partially occluded object recognition under geometric transformations. Objects are represented by their contours. Depending on the kind of geometric transformation and robustness to occlusion we introduce different solutions. Our results are applicable in industry, robotics, 3D vision, forensics, etc. We propose three novel methods for partially occluded object recognition. The major contribution of all our methods is a creation of features. Features are designed to be local and invariant to appropriate geometric transformations. We use mostly standard feature matching to prove properties of designed features. The first method deals only with translation, rotation and scaling (Euclidian transformation) and is based on contour approximation by circle arcs. The parameters of the circle arcs seem to be suitable features. The second method deals with affine transformation and is based on polygonal approximation of contours and, moreover, is robust to additive noise. The second method splits the contour into parts using inflexion points and transforms every part into both normalized shape and position. The parameters of standard shapes of every part are the desired features. The third method deals also with affine transformation. It splits the object into parts using a novel, cutting...
|
|
|
Advanced Moment-Based Methods for Image Analysis
Höschl, Cyril ; Flusser, Jan (advisor) ; Papakostas, George (referee) ; Jiřík, Radovan (referee)
The Thesis consists of an introduction and four papers that contribute to the research of image moments and moment invariants. The first two papers focus on rectangular decomposition algorithms that rapidly speed up the moment calculations. The other two papers present a design of new moment invariants. We present a comparative study of cutting edge methods for the decomposition of 2D binary images, including original implementations of all the methods. For 3D binary images, finding the optimal decomposition is an NP-complete problem, hence a polynomial-time heuristic needs to be developed. We propose a sub-optimal algorithm that outperforms other state of the art approximations. Additionally, we propose a new form of blur invariants that are derived by means of projection operators in a Fourier domain, which improves mainly the discrimination power of the features. Furthermore, we propose new moment-based features that are tolerant to additive Gaussian image noise and we show by extensive image retrieval experiments that the proposed features are robust and outperform other commonly used methods.
|
|
|
Zpracování digitálních snímků videokymografických záznamů jako podpůrný nástroj pro diagnostiku hlasivek
Hauzar, David ; Flusser, Jan (advisor) ; Jiřík, Radovan (referee)
Videokymography is a medical imaging method of revealing and diagnosing vocal cords vibrations in voice disorders. Manual data extraction is problematic while automatic extraction can facilitate and re ne the diagnostic process. However, automatic processing is hampered by signal noise and considerable variability in vocal cords vibrations of individual patients. The objective of the present study is to identify typical characteristics of vocal cords vibrations suitable for automatic extraction and diagnostic interpretation and to implement such automatic extraction. The automatic extraction tool that was implemented reects specifi c features of viodeokymographic images. The system for interpretation of automatic extraction results was developed and tested against manually extracted vibrations data and images. The tool can support kymographic diagnosis of vocal cords disorders.
|
|
| |
|
|
Computational complexity in Graph Theory
Herman, Jan ; Kratochvíl, Jan (advisor) ; Flusser, Jan (referee)
Seidel's switching is a graph operation , which for a given graph G and one of its vertices v gives the graph derived from G by replacing edges adjacent to v by non-edges and vice-versa. A graph H is called a switch of G, if H can be obtained from G by a sequence of switches of its vertices. In the thesis we introduce known results ab out computational complexity of problems if for a given graph G t here exists its switching lying in a given graph class (}. For different graph classes g, we later study a characterization of the class of all graphs, which can be switched into g, in terms of minimal forbidden induced subgraphs. We introduce a full characterization of a class of graphs switchable to a disjoint union af cutworms, respectively partial pairings by forbidden subgraphs. We also prove that a class of graphs switchable to chordal has infinit ely many non-isomorphic forbidden subgraphs. At the end we deal with the relationship between swit ching and other graph operations and graph classes operations.
|
|
| |
guest ::
RSS feed.