17-03-2014, 08:16 PM
Abstract Angiography is a widely used procedure for vessel
observation in both clinical routine and medical research. Often
for the subsequent analysis of the vasculature it is needed to
measure the angiogram area covered by vessels and/or the vessel
length. For this purpose we need vessel enhancement and
segmentation. In this paper, we evaluate the performance of a
fuzzy inference system and morphology filters for blood vessel
segmentation in a noise angiograms image.
Keywords- blood vessel segmentation;Image processing;Fuzzy
logic;Mathematical Morphology;Angiography
1. INTRODUCTION
Segmentation of blood vessels is one of the essential
medical computing tools for clinical assessment of vascular
diseases. It is a process of partitioning an angiogram into nonoverlapping
vascular and background regions. Based on the
partitioning results, surfaces of vasculatures can be extracted,
modeled, manipulated, measured and visualized [1]. Edge
detection is an essential task in computer vision. It covers a
wide range of application, from segmentation to pattern
matching. It reduces the complexity of the image allowing
more costly algorithms like object recognition [2],[3],object
matching [4], object registration [5], or surface reconstruction
from stereo images[6],[7] to be used. Their detection is
interesting for different goals. They can be used to measure
parameters related to blood flow or to locate some patterns in
relation to vessels in angiographic images. They can also be
used as a first step before registration [5], [8], [9].
Conventionally edge is detected according to some early
brought forward algorithms like sobel algorithm, prewitt
algorithm and Laplacian of Gaussian operator [10]. But in
theory they belong to the high pass filtering, which are not fit
for noise medical image edge detection because noise and edge
belong to the scope of high frequency. In real world
applications, medical images contain object boundaries and
object shadows and noise. Therefore, they may be difficult to
distinguish the exact edge from noise or trivial geometric
features. In this paper, we novel a fuzzy inference system and
morphology filters for vessel edge detection or vessel
segmentation. Figure1 depicts the applied process.
observation in both clinical routine and medical research. Often
for the subsequent analysis of the vasculature it is needed to
measure the angiogram area covered by vessels and/or the vessel
length. For this purpose we need vessel enhancement and
segmentation. In this paper, we evaluate the performance of a
fuzzy inference system and morphology filters for blood vessel
segmentation in a noise angiograms image.
Keywords- blood vessel segmentation;Image processing;Fuzzy
logic;Mathematical Morphology;Angiography
1. INTRODUCTION
Segmentation of blood vessels is one of the essential
medical computing tools for clinical assessment of vascular
diseases. It is a process of partitioning an angiogram into nonoverlapping
vascular and background regions. Based on the
partitioning results, surfaces of vasculatures can be extracted,
modeled, manipulated, measured and visualized [1]. Edge
detection is an essential task in computer vision. It covers a
wide range of application, from segmentation to pattern
matching. It reduces the complexity of the image allowing
more costly algorithms like object recognition [2],[3],object
matching [4], object registration [5], or surface reconstruction
from stereo images[6],[7] to be used. Their detection is
interesting for different goals. They can be used to measure
parameters related to blood flow or to locate some patterns in
relation to vessels in angiographic images. They can also be
used as a first step before registration [5], [8], [9].
Conventionally edge is detected according to some early
brought forward algorithms like sobel algorithm, prewitt
algorithm and Laplacian of Gaussian operator [10]. But in
theory they belong to the high pass filtering, which are not fit
for noise medical image edge detection because noise and edge
belong to the scope of high frequency. In real world
applications, medical images contain object boundaries and
object shadows and noise. Therefore, they may be difficult to
distinguish the exact edge from noise or trivial geometric
features. In this paper, we novel a fuzzy inference system and
morphology filters for vessel edge detection or vessel
segmentation. Figure1 depicts the applied process.