Segmentation and extraction of brain injury lesions from MRI images: Matlab implementation

Several approaches have been developed to process and analyze medical images, extract meaningful information, detect abnormalities, and quantify changes in follow-up studies. For the MRI brain image analysis and pattern identification, the lesion and tumor detection are essential for enhancing the diagnostic and therapeutic procedures of brain diseases and injuries. While image segmentation plays a very significant role in MRI image analysis; on the other hand it is considered a challenging process. The objective of this study is to create a segmentation program to extract an injured area in the brain with minimal user contribution. A Matlab algorithm was developed with a graphical user interface (GUI) to easily identify a lesion, highlight a voxel in it and choose to extract it and display it as a three dimensional image. The algorithm uses a sequence of morphological image processing steps (contour closing) followed by region growing segmentation. The results of the developed program demonstrated successful extraction of lesion from MRI data of patient with ischemic stroke; the process is simple, quick, effective, and accurate.