COMPUTERIZED SEGMENTATION OF SINUS IMAGES

Sinusitis is currently diagnosed with techniques such as endoscopy,
ultrasound. X-ray. Computed Tomography (CT) scan and Magnetic Resonance
Imaging (MIZI ). Out of these techniques, imaging techniques are less invasive while
being able to show blockage of sinus cavities. However, the potential of these
techniques have not been fully realized as the images obtained are still bound to
misinterpretations. This work attempts to solve this problem by developing an
algorithm for the computerized segmentation of sinus images for the detection and
grading of' sinusitis. The image enhancement techniques used were median filtering
and the Contrast Limited Adapted Histogram Equalisation (CLAI-IE). These
techniques applied on input images managed to reduce noise and smoothen the image
histogram. Multilevel thresholding algorithms were developed to segment the images
into meaningful regions for the detection of sinusitis. These algorithms were able to
extract important features from the images. The simulations were performed on
images of healthy sinuses and sinuses with sinusitis. The algorithms are found to be
able to detect and grade sinusitis. In addition, a 3-D model of the sinuses was
constructed from the segmentation to facilitate in surgical planning of sinusitis.