19-03-2011, 04:51 PM
PRESENTED BY:
K.Somasundaram
S.Sheela
[attachment=10603]
ABSTRACT- in this paper we present a technique to extract the brain from magnetic resonance images of head scans. The similarity of intensity values in the brain and non-brain tissues makes skull stripping a challenging process. In the paper, we propose a new skull stripping method for magnetic resonance images (MRI) of human head scans. Initially our method extracts the brain by removing the unwanted non-brain regions like skull, scalp, fat and muscles. The methods first preprocess the image by edge detection to obtain a rough image contour. The rough contour is further processed using morphological dilation and erosion extracted brain accurately.
KEYWORDS: skull stripping, contour, brain extraction, MRI brain scans, edge detection, morphological operations dilation, erosion.
I. INTRODUCTION
Magnetic Resonance Imaging is an important technique used primarily in medical images. Intracranial segmentation, commonly referred to as a Skull Stripping aims to segment the brain tissue (cortex and cerebellum) from the skull and non brain intracranial tissues in Magnetic Resonance (MR) images of the brain skull stripping is an important preprocessing in neuroimaging analyse.
The tedious and expensive nature of manual outlining of the brain provided the impetus for the development of several automated and semi automated Skull Stripping systems. To extract brain in MRI scan using edge detection and morphological process. These methods are capable of removing noise and clutter as well as the ability to edit an image based on the size and shape of the object.
The remaining part of the paper is organized as follows. In section II we briefly explained the basic principles and methods. That is used in the proposed method. In section III the experimental results and discussion are given, in section IV, the conclusion is given.
I. METHODS
Several methods have been developed and are widely used to extract brain in MRI scan. Edge detection and Morphological processes to separate the brain from non-brain portions. The diffusion process is used highlight the brain from MRI scan. Then an intensity threshold is computed using which a rough binary brain portion is generated. The Morphological operations erosion and dilation, and connected component analysis are then performed on the rough brain portion to produce the brain mask. Finally the brain mask is used to extract the brain from MRI scan
A. Edge Detection of brain in MRI scan
Edge pixels are pixels at which the intensity of an image function changes abruptly. Edges are sets of connected edge pixels. Edge detectors are local image processing methods designed to detect edge pixels.
Some edge detection operators that are used in our work are Roberts, Prewitt, and Sobel.
Roberts operator
First order derivative that satisfy the conditions gx and gy. This can be implemented using the above two linear filter masks are referred to as Roberts operator.
Prewitt Operator
Sobel Operator
The Sobel operator performs a 2-D spatial gradient measurement on an image. Typically it is used to find the approximate absolute gradient magnitude at each point in an input grayscale image. The Sobel edge detector uses a pair of 3x3 convolution masks, one estimating the gradient in the x-direction (columns) and the other estimating the gradient in the y-direction (rows). A convolution mask is usually much smaller than the actual image. As a result, the mask is slid over the image, manipulating a square of pixels at a time. The actual Sobel masks are shown below:
K.Somasundaram
S.Sheela
[attachment=10603]
ABSTRACT- in this paper we present a technique to extract the brain from magnetic resonance images of head scans. The similarity of intensity values in the brain and non-brain tissues makes skull stripping a challenging process. In the paper, we propose a new skull stripping method for magnetic resonance images (MRI) of human head scans. Initially our method extracts the brain by removing the unwanted non-brain regions like skull, scalp, fat and muscles. The methods first preprocess the image by edge detection to obtain a rough image contour. The rough contour is further processed using morphological dilation and erosion extracted brain accurately.
KEYWORDS: skull stripping, contour, brain extraction, MRI brain scans, edge detection, morphological operations dilation, erosion.
I. INTRODUCTION
Magnetic Resonance Imaging is an important technique used primarily in medical images. Intracranial segmentation, commonly referred to as a Skull Stripping aims to segment the brain tissue (cortex and cerebellum) from the skull and non brain intracranial tissues in Magnetic Resonance (MR) images of the brain skull stripping is an important preprocessing in neuroimaging analyse.
The tedious and expensive nature of manual outlining of the brain provided the impetus for the development of several automated and semi automated Skull Stripping systems. To extract brain in MRI scan using edge detection and morphological process. These methods are capable of removing noise and clutter as well as the ability to edit an image based on the size and shape of the object.
The remaining part of the paper is organized as follows. In section II we briefly explained the basic principles and methods. That is used in the proposed method. In section III the experimental results and discussion are given, in section IV, the conclusion is given.
I. METHODS
Several methods have been developed and are widely used to extract brain in MRI scan. Edge detection and Morphological processes to separate the brain from non-brain portions. The diffusion process is used highlight the brain from MRI scan. Then an intensity threshold is computed using which a rough binary brain portion is generated. The Morphological operations erosion and dilation, and connected component analysis are then performed on the rough brain portion to produce the brain mask. Finally the brain mask is used to extract the brain from MRI scan
A. Edge Detection of brain in MRI scan
Edge pixels are pixels at which the intensity of an image function changes abruptly. Edges are sets of connected edge pixels. Edge detectors are local image processing methods designed to detect edge pixels.
Some edge detection operators that are used in our work are Roberts, Prewitt, and Sobel.
Roberts operator
First order derivative that satisfy the conditions gx and gy. This can be implemented using the above two linear filter masks are referred to as Roberts operator.
Prewitt Operator
Sobel Operator
The Sobel operator performs a 2-D spatial gradient measurement on an image. Typically it is used to find the approximate absolute gradient magnitude at each point in an input grayscale image. The Sobel edge detector uses a pair of 3x3 convolution masks, one estimating the gradient in the x-direction (columns) and the other estimating the gradient in the y-direction (rows). A convolution mask is usually much smaller than the actual image. As a result, the mask is slid over the image, manipulating a square of pixels at a time. The actual Sobel masks are shown below: