Automatic CT Image Segmentation of the Lungs with Region

Growing Algorithm

this algorithm is images from the Picture Archiving and Communication System (PACS), a
system that is used for transferring the images from the modalities directly to servers, and is
available immediately to users, regardless to their location. Our segmentation algorithm is
composed of six main steps.
A. Preprocessing step for the Segmentation of CT image
The first step was to convert the image to gray scale. So by converting the image to gray
scale, the processing time is reduced and a faster algorithm is produced. level set method and
a rapid change in gradient magnitude for the segmentation.
B. Histogram Thresholding
Histogram thresholding is used for determination of the actual binary masks for the lung area.
a better method than the conventional thresholding algorithm, in which the threshold is
simply chosen as the minimum between the two maxima of the gray level histogram.
C. R Region growing algorithm
starts with a seed pixel, examines other pixels that surrounds it, determines the most similar one, and, if it meets
certain criteria, it is included in the region.egion Growing Algorithm. The pixel with the smallest difference
measured this way is allocated to the iteratively grown region. This process is finished when the intensity
difference between region mean and new pixel is larger than a certain threshold. Essentially, a seed pixel must
be selected from which the region growing may commence. Since the aim of the lung segmentation process is
the removal of the dark areas that does not belong to the actual lungs, a seed pixel must be selected from the
dark region.
D. Edge we applied the
edge detector on the image, to create a mask for the extraction of the lungs. An edge operator is a neighborhood
operation which determines the extent to which each pixel's neighborhood can be partitioned by a simple arc
passing through the pixel where pixels in the neighborhood on one side of the arc have one predominant value
and pixels in the neighborhood on the other side of the arc have a different predominant value.Detection.
E. Binary Mask and Image Filling

A Computer Based Feature Extraction of Lung Nodule in Chest XRay Image

CAD system performs two main tasks namely detection task and classification task.
Detection task further classified as image acquisition, enhancement and segmentation. In
image acquisition all the scanned images are resized to the standard size.
Second task of CAD system is classification task. In this task feature extraction and
classification is done. In feature extraction mathematical, textural and geometrical properties
are calculated from the segmented region.
Method : CAD system with the help of high resolution scanner (Scanjet 2400, HP India)and
stored in 256 gray levels (8 bit). Imported images are resized to 800 1200 pixels and stored
in bmp format. Preprocessing algorithm is applied to remove irrelevant information (noise).
For removing noise (Gaussian and salt & pepper noise) low pass filters are used. To remove
the blurring, which is introducing during the low pass filtering is removed by using high
boost filter. Contrast, brightness and intensity problems are removed by using contrast
stretching, histogram equalization, negativity and power law transformation etc. Using
modified thresholding, labeling algorithm and edge detection, segmentation of the lung
nodule X-ray image is carried out.
FEATURE EXTRACTION: Feature extraction provides certain parameters, on the basis of
which computer system takes decision. After the segmentation is performed on lung region,
the features can be obtained from it and the diagnosis rule can be designed to detect nodules
in the lung.
A. Area
Area of the segmented tumor is computed by counting the number of pixels which have the
value 1in the image array. A n [1] where, n [ ] represents the count of number of the
patterns within the parenthesis.
B. Perimeter
Perimeter property is calculating the distance between each adjoining pair of pixels around
the border of the region. If the image contains discontinuous regions, then it returns
unexpected results.

C. Irregularity Index
Lung cancer is characterized partially by the irregularity in its tumor border.
Here it has been assumed that, more circularity of the object, the probability of
the object being nodule is high
D. Gray-Level Co-Occurrence Matrix Properties
The GLCM functions characterize the texture of an image by calculating how often pairs of
pixel with specific values and in a specified spatial relationship occur in an image, creating a
GLCM and then extracting statistical measures from this matrix.

Neural Network Based Approach for Detection of Abnormal Regions

of Lung Cancer in X-Ray Image

rule-based category , where a progression of phase, tests and rules are used in the extraction
process. Techniques make use of thresholding, region growing, edge detection and ridge
detection, morphological operations, fitting a geometrical models or functions are dynamic
programming. On the other hand, there is one more approach employed in lung regions
extraction process based on pixel classifications, where each pixel in the X-Ray is classified
into lung or its background. Classifiers are several types of neural networks, trained with a
variety of local features including intensity, location and texture measures.
The approach starts by extracting the lung regions from lung X-Ray image using several
image processing techniques in MATLAB including binary image, erosion, dilation, gaussian
filter and median filter. Start with binary image including of thresholding technique that is
used in the initial steps in the extraction process to convert X-Ray image into binary image,
which is faster and user-independent. After the extraction step, the region growing
segmentation algorithm is applied on extracted lung regions.

Image Pre-processing
It is necessary step to improve quality of X-Ray image by denoising, enhancement of
structure and its contrast. The process is adopted to enhancing the edge of image structure
include unsharping and enhancing image contrast by histogram equalization
Denoising
The input X-Ray is a normal RGB image that is not supported in MATLAB and convert it in
grey scale. Then the grey scale image contain noises such as white noise, salt and pepper
noise etc. White noise is the most common problems in image processing. The main idea of
any filter is to calculate pixel weights depending on how similar their colors are.

Image Filtering
Median filtering is a nonlinear common enhancement digital filtering technique for removing
noise without reducing the sharpness of the image [6]. It is usually applied in digital image
processing for smoothing of the lung boundaries in thresholding. Author applied filtering by
assigning 5X5 pixel.