%0 Journal Article
%T MR Image Segmentation of PatientsĄŻ Brain Using Disease Specific a Priori Knowledge
%A Hassan Tavakkoli & Ali Sadeqi
%J International Journal of Biometric and Bioinformatics
%D 2012
%I Computer Science Journals
%X Segmentation of high quality brain MR images using a priori knowledge about brain structuresenables a more accurate and comprehensive interpretation. Benefits of applying a prioriknowledge about the brain structures may also be employed for image segmentation of specificbrain and neural patients. Such procedure may be performed to determine the disease stage ormonitor its gradual progression over time. However segmenting brain images of patients usinggeneral a priori knowledge which corresponds to healthy subjects would result in inaccurate andunreliable interpretation in the regions which are affected by the disease. In this paper, atechnique is proposed for extracting a priori knowledge about structural distribution of differentbrain tissues affected by a specific disease to be applied for accurate segmentation of thepatientsĄŻ brain images. For this purpose, extracted a priori knowledge is gradually represented asdisease specific probability maps throughout an iterative process, and then is utilized in astatistical approach for segmentation of new patientsĄŻ images. Experiments conducted on a largeset of images acquired from patients with a similar neurodegenerative disease implied success ofthe proposed technique for representing meaningful a priori knowledge as disease specificprobability maps. Promising results obtained also indicated an accurate segmentation of brainMR images of the new patients using the represented a priori knowledge, into three tissueclasses of gray matter, white matter, and cerebrospinal fluid. This enables an accurate estimationof tissuesĄŻ thickness and volumes and can be counted as a substantial forward step for morereliable monitoring and interpretation of progression in specific brain and neural diseases.
%K Brain MR Images
%K Segmentation
%K Tissue Classification
%K Image Registration
%K A Priori Knowledge
%K Brain Tissue Probability Maps
%K Neurodegenerative Disease.
%U http://cscjournals.org/csc/manuscript/Journals/IJBB/volume6/Issue1/IJBB-141.pdf