Fully Automatic method to Identify Abnormal MRI Head Scans using Fuzzy Segmentation and Fuzzy Symmetric Measure

In this work we have proposed an automatic method to analyze the MRI head scans and detect abnormality in brain due to tumors. We make use of the bilateral symmetry of the human brain. We use T2 axial scans as they are highly sensitive to pathological process. Tumors appear as hyper intense in T2 scans and have intensity close to that of cerebrospinal fluid (CSF). For normal slices, CSF is symmetrical about the vertical central line. So the presence of abnormal tissues in the CSF class can be detected by measuring the vertical symmetry of the CSF image. Our method has four parts. First, the brain is extracted from head using brain extraction algorithm (BEA) and used to detect the boundary between the cerebral hemispheres (CH). Next a slice transformation has been done to align it with the world space for bilateral symmetry checking. Then, a fuzzy segmentation is done to generate a CSF image. Finally a fuzzy symmetric measure (FSM) is calculated for CSF image to discriminate between normal and abnormal scans. Experiments using our method were done on 20 volumes of normal and abnormal datasets. Two measures, false alarm (FA) and missed alarm (MA) were used to quantify the performance of our method and found to be very less, 3% and 6% respectively. These measures were also used to compare our method with that of existing methods. The mean FA is lower than the existing methods. However the MA is higher, and is due to the tumors present symmetrically about the vertical central line.