Authors :
Dhanya G S, Sam Silva.A.
Volume/Issue :
Volume 2 - 2017, Issue 3 - March
Google Scholar :
https://goo.gl/r6dPIV
Scribd :
https://goo.gl/sRaAGI
Thomson Reuters ResearcherID :
https://goo.gl/3bkzwv
Abstract :
Image processing involves the management of images to remove information to highlight or suppress certain phases of the information, contained in the image or perform image analysis to extract hidden information. The recent imaging modalities in medicine, such as Magnetic Resonance Imaging (MRI) generate images directly in digital form. Estimation of the size of the whole organ, portions of the organ and/or objects surrounded by an organ i.e. tumors is clinically important in the analysis of medical image. The relative change in size, shape and the spatial relations among anatomical structures attained from intensity scatterings offer important data in clinical diagnosis for monitoring disease progression for the radiologist. Imprecise, computer algorithms for the description of anatomical structures and other regions of interest play a vital role in numerous biomedical imaging applications. There is no single algorithm which provides the best effects for segmentation of every medical image. Every imaging classification has its own open limits. Here it is primarily focused on Hybrid Genetic Algorithm- Neural Network (HGNN) and Improved PSO Neural Network (IPSONN) and a concise comparison between these two.
Keywords :
Biomedical imaging, HGNN, IPSONN, MRI, Neural Network.
Image processing involves the management of images to remove information to highlight or suppress certain phases of the information, contained in the image or perform image analysis to extract hidden information. The recent imaging modalities in medicine, such as Magnetic Resonance Imaging (MRI) generate images directly in digital form. Estimation of the size of the whole organ, portions of the organ and/or objects surrounded by an organ i.e. tumors is clinically important in the analysis of medical image. The relative change in size, shape and the spatial relations among anatomical structures attained from intensity scatterings offer important data in clinical diagnosis for monitoring disease progression for the radiologist. Imprecise, computer algorithms for the description of anatomical structures and other regions of interest play a vital role in numerous biomedical imaging applications. There is no single algorithm which provides the best effects for segmentation of every medical image. Every imaging classification has its own open limits. Here it is primarily focused on Hybrid Genetic Algorithm- Neural Network (HGNN) and Improved PSO Neural Network (IPSONN) and a concise comparison between these two.
Keywords :
Biomedical imaging, HGNN, IPSONN, MRI, Neural Network.