Pre-Segmentation for the Computer Aided Diagnosis System

This paperaims to introduce the method fordetectionand classification ofan abnormalityof the brainregioninto infarct,haemorrhage. Initially, the image is pre-processed to remove film artifact, noiseusingmorphological operations.And the brain image is cropped to eliminate the extra parts.Before theabnormality region(infarct,haemorrhage)is segmented, the image is pre-segmented.In this stage, theimage is subdivided into four quadrantsusing split and merge techniqueto find the regionthat has thepossibility for inclusion of abnormal areas. Thus, the unnecessary regions are no need to search andsegment.This paper proposespre-processing andpre-segmentation steps for the detection of abnormalregion inthebrain image.Then,abnormalities can be segmented by grouping homogeneous regionsaccording to the predefined criteria. The accuracy of the segmentation results can be assessed by thespecialist.