A Platform Design For Acute Stroke Ischemia Brain Detection in Magnetic Resonance Imaging
Public health is one of the major concerns at the international level. Stroke is an acute cerebral vascular disease, which is likely to cause long-term disabilities and death. Every year, 12 million people are affected by stroke brain in worldwide and the value is increasing. Acute ischemia lesions occur in most stroke patients. These lesions are treatable under accurate diagnosis and treatments. Brain Magnetic Resonance Imaging (MRI) brain is one of the essential non-invasive modalities for the diagnostic of this diseases. Indeed, diffusion weighted (DW) and perfusion weighted (PW) imaging are very helpful to detect acute stroke in early stages. This is a survery paper which presents a platform design of an automated segmentation using benchmark methods (Fuzzy C-Means (FCM), Otsu, Regions growing and Spatial FCM) in order to obtain a robust, rapid, efficient and precocious system detection of acute stroke lesions from MR images obtained from diffusion-weighted imaging (DWI) and perfusion-weighted imaging (PWI). The validation purposes was performed by comparing resulting segmentation to the manual contours traced by an expert. Results show that the SFCM appeared in the plateform is efficient in detection of acute with a accuracy value of 99.1% in PWI-MTT and of 47.44% in DWI and an timing average about one second.
Keywords - Brain MRI, Acute Stroke Ischemia Brain, Automatic Segmentation, FCM, SFCM, Diffusion Weight Imaging, Perfusion Weight Imaging, Neuroimaging.