Key points are not available for this paper at this time.
Background/Objectives: Image segmentation is one of the fundamental techniques in image processing. During past few years, the image processing mechanisms are extensively used in various medical fields for early stage detection, separation and identification of diseases; in this, the time consumption is an important criteria to discover the diseases for the patient. Methods/Statistical Analysis: This research work analyses about the detection and separation of brain tumor through Magnetic Resonance Imaging (MRI) medical images using Particle Swarm Optimization (PSO), a heuristic global optimization method based on swarm intelligence. The algorithm is widely used and rapidly developed for its ease implementation. This work has four stages that includes conversion, implementation, selection and extraction. Findings: The research work starts with converting the Digital Imaging and Communications in Medicine (DICOM) into image file format which is the first stage. Applying the PSO algorithm with the change in the values of n (segmentation level) is the second stage. Based on the time, selecting the best resultant images is the third stage. The final stage is extraction of tumor affected region with the suitable filtering techniques. The research work takes the axial and coronal plane of the Magnetic Resonance (MRI) images. Finally, this work concludes with the extraction of the resultant image, which is taken as input, and using the best filtering technique the affected region is easily separated and identified efficiently. The work also identifies the best suitable plane for the PSO algorithm. Applications/Improvements: The same PSO algorithm is applied to find the size and the type of calcifications in MRI brain images and are extracted in future. The possibilities of using other algorithms are also considered for further implementation. Keywords: Brain Tumor, MRI Images, PSO Algorithm, Segmentation
Mahalakshmi et al. (Mon,) studied this question.