Developement of a Neurological Disease Prediction Framework for Assisting Neurologits to Automatically Segment Gray and White Matter Regions in Brain MRI Images of Patients

There is a need for computational tools for processing medical patient data and extracting clinically relevant information from patient images for providing patient-specific personalized treatment. Tools have been and are actively being developed by software engineers and programmers in the field of bio-medical image processing for assisting doctors, scientists and researchers. This paper presents an independent stand-alone software application that is a graphical computational tool with a user interface for automatic segmentation of brain MRI images. The same software tool subsequently functions as a neurological disease prediction framework for detection of disease, dementia, impairment, injury, lesions, or tumors in brain MRI images. Brain MRI image segmentation techniques have become an important tool for neurologists to detect disease and cure patients in their early stages of the disease so detected. The tool presented in this paper facilitates the user to automatically segment the regions of brain MRI images using an algorithm called adapted fuzzy c-means (FCM). This methodology for segmentation is based on pixel classification technique, in conjunction with connected region analysis.