Wyniki wyszukiwania - BazTech

1

Study and adjustment of dermoscopic image processing algorithms for lesion border detection

Borys D., Szeremet M., Psiuk-Maksymowicz K., Ostrowski Z., Frąckiewicz M.

Studia Informatica

|

2016

|

Vol. 37, nr 3B

33-46

EN

The goal of our work was an initial preprocessing of dermoscopic images towards accurate lesion border detection. Four algorithms were proposed and analyzed: MS – algorithm using mean shift clustering, HE – algorithm using histogram equalization, TTH – algorithm using the top-hat transform, PCA – algorithm using principal component analysis. Those algorithms were tested on PH2 images database that contains 200 dermoscopic images, each with a mask of the lesion. Those algorithms were optimized using lesion mask from database and Jaccard index as a measure of similarity of both sets. Simple statistical analysis of indexes was used to compare proposed algorithms in term of their accuracy.

PL

W artykule poruszono problem wstępnego przetwarzania obrazów dermatoskopowych w celu znalezienia konturu znamienia. Zaproponowano i porównano cztery algorytmy: MS – wykorzystujący klasteryzację ‘mean shift’, HE – wykorzystujący wyrównywanie histogramu, TTH – wykorzystujący transformację ‘top-hat’, PCA – wykorzystujący metodę analizy głównych składowych. Algorytmy przetestowano z wykorzystaniem obrazów z bazy PH2, zawierającej 200 obrazów wraz z obrysem ręcznym, a ich parametry dobrano optymalizując indeks Jaccarda. Proste statystyki wyników pozwoliły na porównanie proponowanych algorytmów.

2

Simplification of breast deformation modelling to support breast cancer treatment planning

Danch-Wierzchowska M., Borys D., Bobek-Billewicz B., Jarzab M., Swierniak A.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 4

531--536

EN

The exact delineation of tumour boundaries is of utmost importance in the planning of cancer therapy, either surgery or pre- or post-operative radiation treatment. In the case of breast cancer one of the most advanced modalities is magnetic resonance imaging (MRI). Although MRI scans provide wealth of information about the structure of a tumour and the surrounding tissues, the data obtained represent the patient in a prone position, with breast, in a coil while surgery is performed in a supine position, on lying breast. There is no doubt that a patient's breast in both positions has a different shape and that this influences the intra-breast relations. Our present preliminary study introduces a simple breast model developed from prone images. The model should be built rapidly and by a simple procedure, based only on essential structures, and the goal is to prove its usefulness in treatment planning.

3

System matrix computation for iterative reconstruction algorithms in SPECT based on direct measurements

Borys D., Szczucka-Borys K., Gorczewski K.

International Journal of Applied Mathematics and Computer Science

|

2011

|

Vol. 21, no 1

193-202

EN

A method for system matrix calculation in the case of iterative reconstruction algorithms in SPECT was implemented and tested. Due to a complex mathematical description of the geometry of the detector set-up, we developed a method for system matrix computation that is based on direct measurements of the detector response. In this approach, the influence of the acquisition equipment on the image formation is measured directly. The objective was to obtain the best quality of reconstructed images with respect to specified measures. This is indispensable in order to be able to perform reliable quantitative analysis of SPECT images. It is also especially important in non-hybrid gamma cameras, where not all physical processes that disturb image acquisition can be easily corrected. Two experiments with an 131I point source placed at different distances from the detector plane were performed allowing the detector response to be acquired as a function of the point source distance. An analytical Gaussian function was fitted to the acquired data in both the one- and the two-dimensional case. A cylindrical phantom filled with a water solution of 131I containing a region of 'cold' spheres as well as a uniform solution (without any spheres) was used to perform algorithm evaluation. The reconstructed images obtained by using four different of methods system matrix computation were compared with those achieved using reconstruction software implemented in the gamma camera. The contrast of the spheres and uniformity were compared for each reconstruction result and also with the ranges of those values formulated by the AAPM (American Association of Physicists in Medicine). The results show that the implementation of the OSEM (Ordered Subsets Expectation Maximization) algorithm with a one-dimensional fit to the Gaussian CDR (Collimator-Detector Response) function provides the best results in terms of adopted measures. However, the fit of the two-dimensional function also gives satisfactory results. Furthermore, the CDR function has the potential to be applied to a fully 3D OSEM implementation. The lack of the CDR in system matrix calculation results in a very noisy image that cannot be used for diagnostic purposes.

4

E.Cam DUET gamma camera model validation in GATE

Borys D., Szczucka K., Gorczewski K., Bekman B.

Journal of Medical Informatics & Technologies

|

2007

|

Vol. 11

245--252

EN

Monte Carlo simulations are more and more popular trend in nuclear medicine imaging. They were also widely used in radiotherapy and brachytherapy with use of more general simulation software. GATE (Geant4 Application for Tomographic Emission) is a platform developed on general Monte Carlo code designed for simulating and tracking the passage of particles through matter (Geant4) but is specifically designed for nuclear medicine imaging purposes. The aim of this work was to create and validate a model of specific gamma-camera (E.Cam DUET), used in our department, for further use in image analysis and dosimetry field, with GATE simulation platform. We have modeled in first step a point source in the air in three configurations of gamma camera (without collimator, with low-energy high-resolution (LEHR) collimator and with high-energy (HE collimator)), then we have created a phantom with three spherical sources of different sizes but with the same concentration of the radiopharmaceutical. Simulation results were compared to the measured values of the energy spectrum and images obtained on the detectors, and show a good agreement for the point source experiments and revealed some differences for the phantom studies. This results shows that some additional tests and refinements are required but also allows us to study the image degrading quality factors, such as septal penetration and to work towards eliminating them from the pictures.

5

Node assignment problem in Bayesian networks

Polańska J., Borys D., Polański A.

International Journal of Applied Mathematics and Computer Science

|

2006

|

Vol. 16, no 2

233-240

EN

This paper deals with the problem of searching for the best assignments of random variables to nodes in a Bayesian network (BN) with a given topology. Likelihood functions for the studied BNs are formulated, methods for their maximization are described and, finally, the results of a study concerning the reliability of revealing BNs’ roles are reported. The results of BN node assignments can be applied to problems of the analysis of gene expression profiles.

6

Evaluation of SPECT-CT image fusion quality control

Borys D., Panek R., Gorczewski K., d'Amico A., Steinhof K., Psiuk-Maksymowicz K.

Biocybernetics and Biomedical Engineering

|

2006

|

Vol. 26, no. 4

79-90

EN

Co-registration of different types of studies into one multimodal image is a very powerful tool which provides more (complementary) information than both studies analyzed separately. The aim of this paper is to demonstrate the importance and to provide a measure of quality control in SPECT-CT studies. The resuIt of image fusion has a diagnostic value only when precision of co-registration is known and falls below an acceptable level. It is very important to evaluate an error of each fusion result. This parameter, while unknown, may lead to incorrect diagnostic decisions, especially when none of the anatomical structures are visualized, like in case of imaging iodine-131 patients.

7

CT/SPECT image fusion in patients treated with iodine-131

Psiuk-Maksymowicz K., Borys D., Gorczewski K., Steinhof K., d'Amico A.

Journal of Medical Informatics & Technologies

|

2004

|

Vol. 8

II7--12

EN

Computer tomography gives visualization of anatomical structures and abnormalities, but it lacks of functional information. On the other hand, single photon emission tomography provides the missing information about the tumour function, but it has relative low resolution and the localization of the visible focus may be difficult, especially when iodine ¹³¹I is used. Thus, several methods of image fusion are applied. We present an algorithm of image fusion based on affine transformation. On the base of a phantom study, we showed that the created program can be a useful tool to fuse CT and SPECT images and then applied to patients' datasets. External marker method was used to align patient functional and anatomical data. Image alignment quality depends on appropriate marker placement and acquisition protocol. The program estimates maximal misalignment in a volume between the markers. Created acquisition protocol minimizes misalignment of patient placement on both CT and gamma camera, however misalignment derived from respiratory movements cannot be avoided. The proposed technique is simple, low-cost and can be easily adopted in any hospital or diagnostic centre equipped with gamma camera and CT. Fusion of morphology and function can improve diagnostic accuracy in many clinical circumstances.