segmentation is
slow and lacks of objectivity.[10]Consequently, automatic segmentation and tracking of thevessel inner wall in IVUS images has been approached inseveral recent works.[8] The poor quality of the imagessuggests the use of techniques such as probabilities or fuzzy
logic
guiding an active contour to adjust the inner wall.
II. Materials and MethodsII. Materials and MethodsII. Materials and MethodsII. Materials and MethodsProblem DefinitionProblem DefinitionProblem DefinitionProblem Definition
The noise created during ultrasound scanningleads to difficulty in defining the boundary of the vessel.The image is further deteriorated by the occurrence of lipidrich plaque a poorly angled transducer during imageacquisition. Difficult in highlighting plaque region.
BOUNDARY DETECTIONBOUNDARY DETECTIONBOUNDARY DETECTIONBOUNDARY DETECTION
Ultrasonic Artery Images
Figure 1Figure 1Figure 1Figure 1(a) Carotid artery image. (b) Definition of echo zones and(a) Carotid artery image. (b) Definition of echo zones and(a) Carotid artery image. (b) Definition of echo zones and(a) Carotid artery image. (b) Definition of echo zones andinterfaces.interfaces.interfaces.interfaces.
Figure. 1(a) shows a representative image of a carotid artery.The femoral artery has a similar appearance. The echoes inthe region of interest can be schematically grouped intoseven echo zones Z1–Z7 [Figure. 1(b)]. Previous studies[12], [13] have shown that the leading edge (upper side) of Z3, Z5, and Z7, denoted as I3, I5, and I7, can be mapped tothe near-wall intima–lumen interface, the far-wall lumen–intima interface, and the far-wall media–adventitia interface,respectively. Consequently, the distancebetween I3 and I5represents the LD and the distance between I5 and I7 is thefar-wall IMT.With this understanding, the determination of ultrasonic measurement of the artery becomes equivalent toaccurately detecting the echo boundaries I3, I5, and I7.[14]The femoral artery has a similar appearance.The echoes in the region of interest can be schematicallygrouped into seven echo zones Z1–Z7 .[15][16] Previousstudies have shown that the leading edge (upper side) of Z3,Z5, and Z7, denoted as I3, I5, and I7, can be mapped to thenear-wall intima–lumen interface, the far-wall lumen–intimainterface, and the far-wall media–adventitia interface,respectively. Consequently, the distance between I3 and I5represents the LD and the distance between I5 and I7 is thefar-wall IMT. With this understanding,[14 the determinationof ultrasonic measurement of the artery becomes equivalentto accurately detecting the echo boundaries.
III. IEEM programming procedureIII. IEEM programming procedureIII. IEEM programming procedureIII. IEEM programming procedure
Image Enhancement:Image Enhancement:Image Enhancement:Image Enhancement:
Histogram equalization provides more visuallypleasing results across a wider range of images.Image brightness[11] may be improved by modifyingthe histogram of the image.
Image Denoising:Image Denoising:Image Denoising:Image Denoising:
An image is often corrupted by noise in its acquisition ortransmission. Noise is any undesired information thatcontaminates an image. Noise appears in images from avariety of sources. The goal of denoising is to remove thenoise while retaining as much as possible the importantsignal features. Denoising can be done through filtering.Filters reduces noise. Gaussian highpass filter helps toreduces a noise.
% H = guassian_filter(co,ro,fo);% H = guassian_filter(co,ro,fo);% H = guassian_filter(co,ro,fo);% H = guassian_filter(co,ro,fo);H = 1H = 1H = 1H = 1 –––– H;H;H;H;Out = Zeros(co,ro);Out = Zeros(co,ro);Out = Zeros(co,ro);Out = Zeros(co,ro);Outf = imf. * H;Outf = imf. * H;Outf = imf. * H;Outf = imf. * H;Out = abs ( ifft2(outf));Out = abs ( ifft2(outf));Out = abs ( ifft2(outf));Out = abs ( ifft2(outf));Imshow(im), title (‘Original image’), figure,Imshow(im), title (‘Original image’), figure,Imshow(im), title (‘Original image’), figure,Imshow(im), title (‘Original image’), figure,Imshow((out)), title (‘Filtered Image’) figure,Imshow((out)), title (‘Filtered Image’) figure,Imshow((out)), title (‘Filtered Image’) figure,Imshow((out)), title (‘Filtered Image’) figure,Imshow (H), titImshow (H), titImshow (H), titImshow (H), title(‘2D view of B’), figure, surf(H),le(‘2D view of B’), figure, surf(H),le(‘2D view of B’), figure, surf(H),le(‘2D view of B’), figure, surf(H),Title (‘3D view of H’)Title (‘3D view of H’)Title (‘3D view of H’)Title (‘3D view of H’)
Edge Detection:Edge Detection:Edge Detection:Edge Detection:
The IEEM defines edges as Zero-crossings of secondderivatives in the direction of the greatest first derivate. Thisworks in multistage process (i) image is smoothed byGaussian convolution (ii) 2D first derivate operator isapplied to the smoothed image to highlight region of theimage with high spatial derivatives. The effectiveness of this algorithm is determined by three parameters (i) width of the Gaussian kernel (ii) upper threshold (iii) lower thresholdused by tracker.
Morphological operations for Boundary detection:Morphological operations for Boundary detection:Morphological operations for Boundary detection:Morphological operations for Boundary detection:
Morphological operations are very effective in the detectionof boundaries in a binary image X. The following boundarydetectors are widely used:Y = X – ( X
B )Y = ( X B ) = X orY = (X B) - ( X
B )where Y is the boundary image, operator
denotes erosionoperator denotes dilation ‘ – ‘ denotes set theoreticalsubtraction.%Boundary detectorClose all;Clear all;Clc;a=imread(‘carotid.jpg’);b=[010;111;010];a1=imdilate(a,b);a2=imerode(a,b);a3=a-a2;a4=a1-a;a5=a1-a2;imshow(a)figure,imshow(a1),title(‘Dilated Image’)figure, imshow(a2),title(‘Eroded Image’)
(IJCSIS) International Journal of Computer Science and Information Security,Vol. 8, No. 5, August 201086http://sites.google.com/site/ijcsis/ISSN 1947-5500