Lesion detection in brain MRI using PSO based segmentation

Abstract In modern clinical diagnosis image processing plays a significant role. Digital imaging of vital organs, their processing and analysis is one of the most important areas of research and development to get maximum accuracy in diagnosis. Especially now a days it is an integral part of medical diagnosis. The different techniques applied is begins with radiology to ultra-sonograph, Magnetic Resonance Imaging (MRI) etc. in many preliminary clinical diagnosis images of the effected organ is the one of effective way of diagnosis-process. The different state of the art digital imaging equipment is introduced to capture and render the images of the internal body organs of the patient to carry the diagnostic process more accurate. To gather more relevant diagnostic data, the electronically captured digitized images need to be fine-tuned digitally. The various methods and techniques involved in fine tuning the images are – cleaning the image by removing the noise, separating different shades by segmenting the image and getting the threshold-point etc. Segmenting an image is a method to separate the marked area of an image from the rest of image to single out the marked-area more conspicuously. There are many unique techniques evolved to execute the segmentation operation, one of them is - Image Thresholding. There are many innovative implements are also introducing to execute the steps of image thresholding. Here we use a recent introduced Particle Swarm Optimization (PSO) tool to segment the brain MRI to detect the brain-lesions using image thresholding technique.