Image Processing Reference
In-Depth Information
(3)
where X ij is obtained by applying a Gaussian low-pass filter, with order 3 and σ = 0.5, to the
original image. The parameters a and b control the radial contrast gain and were empirically
determined to improve the CRN, Figure 4(b) .
The parameter k is a simple gain and the term
control the edge emphasis.
2.7 Postprocessing
This step in the rebuilding process aims to expand the gray level dynamic band, in term of sat-
uration of the image. It was obtained applying a gamma correction intensity transformation to
the image [ 15 ] .
After this, the image was converted and interpolated to cartesian form, resulting in an image
with 512 × 512 pixels and 256 gray levels.
Finally, a two-dimensional (2D) Gabor filter was applied to the image to enhancing the
changes streaming from texture and to evidence the edges.
A 2D Gabor filter is a complex field sinusoidal, modulated by a 2D gaussian function in the
spatial domain [ 16 ] .
3 Experimental results
The results of the rebuilding process of the IVUS images are shown in Figure 5 , which the ma-
jor structures visible in an IVUS examination are identified.
FIGURE 5 Nine images from the reconstruction process showing different regions (a) lumen-
adventitia borders, (b) stent, (c) calcification, (d) stent, (e) bifurcation region, (f) pericardium
shadow, (g) calcification, (h) bifurcation, and (i) malposition stent.
Figure 5(a) shows the segmentation of lumen and the media-adventitia borders and Figure
5(b) shows the stent and an artifact generated by the wire guide. Figure 5(c) shows a region
with calcification and the acoustic shadow behind it, with an arrow pointing to an artifact gen-
erated by the wire guide.
 
 
Search WWH ::




Custom Search