• No results found

Automated segmentation of atherosclerotic arteries in MR Images Adame Valero, I.M.

N/A
N/A
Protected

Academic year: 2021

Share "Automated segmentation of atherosclerotic arteries in MR Images Adame Valero, I.M."

Copied!
2
0
0

Bezig met laden.... (Bekijk nu de volledige tekst)

Hele tekst

(1)

Automated segmentation of atherosclerotic arteries in MR Images

Adame Valero, I.M.

Citation

Adame Valero, I. M. (2007, April 4). Automated segmentation of atherosclerotic arteries in MR

Images. ASCI dissertation series. ASCI graduate school|Laboratory for Clinical en

Experimental Image processing, Faculty of Medicine / Leiden University Medical Center

(LUMC), Leiden University. Retrieved from https://hdl.handle.net/1887/11467

Version: Corrected Publisher’s Version

License: Licence agreement concerning inclusion of doctoral thesis in the

Institutional Repository of the University of Leiden

Downloaded from: https://hdl.handle.net/1887/11467

Note: To cite this publication please use the final published version (if applicable).

(2)

I . M . A D A M E V A L E R O

Automated Segmentation of Atherosclerotic Arteries in MR Images

Stellingen

1. A priori information is crucial to achieve an accurate segmentation. This thesis

2. A model-based approach in combination with dynamic programming is a robust contour detection technique for poorly delineated vascular structures, such as the outer boundary of the vessel wall. This thesis

3. Classification of plaque components requires the use of information from multiple contrast weighted MR images, which can be achieved by means of classification techniques such as fuzzy clustering. This thesis

4. Accurate and precise assessment of the severity of the stenosis and plaque burden permits identification of atherosclerosis at an early stage and monitor its evolution. This thesis

5. MRA demonstrates the severity and distribution of luminal narrowings, while vessel wall MRI characterizes the plaques in the wall. Combination of both modalities reduces user-interaction and permits estimation of the severity of atherosclerosis more accurately. This thesis

6. A 3D segmentation and registration of two serial MR scans of the same patient leads to quantitative and reproducible measurements of the possible changes in plaque burden over time. This thesis

7. The capabilities of MRI to characterize plaque composition are limited by the reduced spatial resolution of the data, fuzzy boundaries and image artifacts. The ongoing investigation of new contrast agents that target specific plaque components opens a whole new range of possibilities for the characterization of the vessel wall in MR. This thesis

8. Greek authors, despite their attempts at objectivity, became slaves of mythical thinking whenever they tried to explain the invisible. Modern medicine also makes use of imagination when faced with the limits of what is available to observation, even though those limits are constantly being extended.

9. Be kind, for everyone you meet is fighting a hard battle. Plato

10. Freedom is not worth having if it does not include the freedom to make mistakes. Mahatma Ghandi.

11. Be yourself, there are plenty of others.

Referenties

GERELATEERDE DOCUMENTEN

In this thesis, novel image processing techniques have been developed based on a-priori knowledge and combination of different imaging modalities, to outline the boundaries of

In dit proefschrift zijn nieuwe beeldverwerkingstechnieken ontwikkeld die op basis van a-priori kennis en middels fusie van verschillende opnametechnieken, in staat zijn om de

Automatic plaque characterization and vessel wall segmentation in Magnetic Resonance images of atherosclerotic carotid arteries, proc.. ƒ Adame IM, van der Geest RJ, Wasserman

To all other colleagues at LKEB: those who had the patience to listen to me during my process of learning Dutch, those who kept offering to bring me coffee during four years,

In October 2002 she joined the Laboratory for Clinical and Experimental Image Processing (Laboratorium for Klinische en Experimentele Beeldverwerking, LKEB) at the Leiden

Feature extraction technique used in digital image processing.. The classical transform identifies lines in the image, but it has been extended to identifying positions of

algorithm. A) Automatic detection of lumen, outer boundary of the vessel wall and plaque (lipid core). B) Contours manually traced by an expert.. Arrows point

automated processing (auto) and those obtained from the two independent standards (exp1 and exp2), for vessel wall thickness (mean), and