Wyniki wyszukiwania - BazTech

1

New deformable models development using the MESA environment

Bołdak C., Reska D., Krętowski M.

Journal of Applied Computer Science

|

2014

|

Vol. 22, nr 1

29--48

EN

In this work we present capabilities of a new environment called Medical Segmentation Arena (MESA) in developing new segmentation methods based on the deformable models. The MESA environment was created in frame of the project “Information Platform TEWI” to facilitate researches in the medical image processing domain. The operator can formulate new segmentation algorithms based on the deformable models theory (active contours - snakes) by composing them from ready-to-use blocks. He can also develop new blocks with a simple Java-based programming mechanism. Then he can easily evaluate these algorithms with many o ﬀ ered tools (image management and visualization, batch experiment planning and running, parametric studies, virtual phantom generation, segmentation quality assessment, distributing of computations). We give also some examples of the snake energies and models implemented in the MESA environment presenting its capabilities in practice.

2

MESA: Complete approach for design and evaluation of segmentation methods using real and simulated tomographic images

Reska D., Jurczuk K., Boldak C., Kretowski M.

Biocybernetics and Biomedical Engineering

|

2014

|

Vol. 34, no. 3

146--158

EN

In this paper we present MESA: a platform for design and evaluation of medical image segmentation methods. The platform offers a complete approach for the method creation and validation using simulated and real tomographic images. The system consists of several modules that provide a comprehensive workflow for generation of test data, segmentation method development as well as experiment planning and execution. The test data can be created as a virtual scene that provides an ideal reference segmentation and is also used to simulate the input images by a virtual magnetic resonance imaging (MRI) scanner. Both ideal reference segmentation and simulated images could be utilized during the evaluation of the segmentation methods. The platform offers various experimental capabilities to measure and compare the performance of the methods on various data sets, parameters and initializations. The segmentation framework, currently based on deformable models, uses a template solution for dynamical composition and creation of two- and three-dimensional methods. The platform is based on a client–server architecture, with computational and data storage modules deployed on the server and with browser-based client applications. We demonstrate the platform capabilities during the design of segmentation methods with the use of simulated and actual tomographic images.

3

Aplikacja wspierająca proces konturowania organów w danych medycznych

Flis E., Socha M., Skalski A.

Pomiary Automatyka Kontrola

|

2012

|

R. 58, nr 4

323-326

PL

Ze względu na coraz częstsze wykorzystanie danych obrazowych w medycynie, a bardzo często wiążąca się z tym konieczność wykonywania obrysów struktur anatomicznych pojawiła się potrzeba tworzenia aplikacji skracających i ułatwiających ten proces. W artykule przedstawiono aplikację wspierającą ten proces. Aplikacja umożliwia automatyczną segmentację struktur, korekcję wyników przez użytkownika, dokonywanie pomiarów jak i obsługę typowego formatu zapisu danych DICOM.

EN

New and accessible imaging methods, ranging from Computed Tomography (CT), Magnetic Resonance Imaging (MRI) to Positron Emission Tomography (PET) allow medical doctors to obtain non-invasively potentially life-saving information about patient condition and body. This information is usually used to improve diagnostic accuracy and give more information during treatment. However, the purpose of recent medical imaging is not only to obtain simple visualization and insight into human anatomic structures, but also as a powerful tool for CAD, radiotherapies, surgical operation planning and simulation. This is exactly the field where image segmentation methods can play a key role. In this work, a cross-platform application software equipped with an algorithm for segmentation of anatomical structures (region growing and deformable models), manual contouring and medical data visualization was developed. Results from the region growing algorithm can be a final outcome with or without user's corrections or can be a transform to the initial surface for deformable models technique. The software application was written in C++ language with Qt, VTK, ITK and GDCM toolkits [13-16]. Graphic User Interface is shown in Fig. 1. The application works with medical data in DICOM [2] and DICOM RT [3] standard. The exemplary segmentation results are presented in Figs. 3 and 4.

4

Models, algorithms and applications in vascular image segmentation

Orkisz M., Valencia L. F., Hoyos M. H.

Machine Graphics and Vision

|

2008

|

Vol. 17, No. 1/2

5-33

EN

A synthesis of the authors' projects in the field of 3D vascular image processing in the last decadeis provided. This work was motivated by the following applications: display improvement, extraction of geometrical measurements, acquisition optimization, stent-pose planning, phantom generation, blood-flow simulations. The methods are often dependent on the imaging modality and/or on the anatomic region. They involve both: low-level models of intensity patterns and profiles, and higher-level models of cylindrical shapes. Amongst the various algorithms used, recursive tracking and fast-marching level-sets are emphasized. Critical analysis of each model and algorithm is carried out. Problems that remain open, and perspectives associated with the progress of the image acquisition techniques, are listed.