A Computational Segmentation Tool for Processing Patient Brain MRI Image Data to Automatically Extract Gray and White Matter Regions

Brain MRI imaging is necessary to screen and detect diseases in the brain, and this requires processing, extracting, and analyzing a patient’s MRI medical image data. Neurologists and neurological clinicians, technicians, and researchers would be greatly facilitated and benefited by a graphical user interface-based computational tool that could perform all the required medical MRI image processing functions automatically, thus minimizing the cost, effort, and time required in screening disease from the patient’s MRI medical image data. Thus, there is a need for automatic medical image processing software platforms and for developing tools with applications in the medical field to assist neurologists, scientists, doctors, and academicians to analyze medical image data automatically to obtain patient-specific clinical parameters and information. This research develops an automatic brain MRI segmentation computational tool with a wide range of neurological applications to detect brain patients’ disease by analyzing the special clinical parameters extracted from the images and to provide patient-specific medical care, which can be especially helpful at early stages of the disease. The automatic brain MRI segmentation is performed based on modified pixel classification technique called fuzzy c-means followed by connected component labeling.