Title :
Masking Based Segmentation of Diseased MRI Images
Author :
De, Arunava ; Das, Rajib Lochan ; Bhattacharjee, Anup Kumar ; Sharma, Deepak
Author_Institution :
Dept. of Electron. & Commun. Eng., Dr. B.C. RoyEngg Coll., Durgapur, India
Abstract :
We have devised a new technique to segment an diseased MRI image wherein the diseased part is segregated using a masking based thresholding technique together with entropy maximization. The particle swarm optimization technique (PSO) is used to get the region of interest (ROI) of the MRI image. The mask used is a variable mask. The rectangular mask is grown using an algorithm provided in the subsequent sections using similarity of neighbourhood pixels. Tests on various diseased MRI images show that small diseased objects are successfully extracted irrespective of the complexity of the background and difference in intensity levels and class sizes. Previous works are based on bimodal images whereas our work is based on multimodal images.
Keywords :
biomedical MRI; image segmentation; medical image processing; particle swarm optimisation; diseased MRI image masking; entropy maximization; image segmentation; multimodal images; particle swarm optimization technique; rectangular mask; region of interest; thresholding technique; variable mask; Computed tomography; Educational institutions; Entropy; Gaussian distribution; Histograms; Image segmentation; Jamming; Magnetic resonance imaging; Particle swarm optimization; Testing;
Conference_Titel :
Information Science and Applications (ICISA), 2010 International Conference on
Conference_Location :
Seoul
Print_ISBN :
978-1-4244-5941-4
Electronic_ISBN :
978-1-4244-5943-8
DOI :
10.1109/ICISA.2010.5480274