Detection and GTV Definition of Brain Tumors in MRI Images Using Image Processing Technique

This was experimental study conducted to detect and determination of the GTV for radiotherapy planning in brain tumor in MRI images using edge detection and image processing techniques. For brain MRI images was done using GE MR Scanner (1.5 tessla) then treated as dicom format preparing for image processing program (IDL), where the region of interest segmentation was studied. The scanned image was saved in a TIFF file format to preserve the quality of the image in order to segment the background from the foreground brain tissue. Brain tissue can be easily detected in MRI image because it has better image contrast and resolution. T1 weighted images with gadolinium contrast enhancement where used in this study. We use the histogram equalization function for more uniform pixel distribution and differentiation, edge detection and basic morphology tools to detect a tumor margin using laplacian filter, Roberts and sobel function of edge detection and label region segmentation after thresholding process of tumors intensities. The results of this study were that it showed an alternate method for displaying, detection and tumor delineation accurately, where the outline was drown around the irregular tumor margin accurately and the GTV was identified for radiotherapy further planning. Those processing approaches can help in achieving of radiotherapy goals and for better diagnosis also by increase diagnostic information of Brain tumors in MRI.