Characterization of Hepatic Lesions Using Grid Computing (Globus) and Neural Networks
Sheng Hung, Ean Teng Khor · InTech eBooks · 2012
Magnetic Resonance Imaging (MRI) images have been widely used for liver disease diagnosis.Designing and developing computer-assisted image processing techniques to help doctors improve their diagnosis has received considerable interest over the past years.In this paper, a computer-aided diagnostic (CAD) system for the characterization of hepatic lesions, specifically cyst and tumor as well as healthy liver, from MRI images using texture features and implementation of grid computing (Globus approach) and neural networks (NN) is presented.Texture analysis is used to determine the changes in functional characteristics of organs at the onset of a liver disease, Region of interest (ROI) extracted from MRI images are used as the input to characterize different tissue, namely liver cyst and healthy liver using first-order statistics.The results for first-order statistics are given and their potential applicability in grid computing is discussed.The measurements extracted from First-order statistic include entropy and correlation achieved obvious classification range in detecting different tissues in this work.In this chapter, texture analysis of liver MRI images based on the Spatial Grey Level Cooccurrence Matrix (SGLCM) [3] is proposed to discriminate normal, malignant hepatic tissue (i.e.liver tumor) and cysts in MRI images of the abdomen.SGLCM, also known as Grey Tone Spatial Dependency Matrix [3], is a tabulation of how often different combinations of pixel brightness values (i.e.grey-level) occur in an image.Regions of interest (ROI) from cysts, tumor and healthy liver were used as input for the SGLCM calculation.Second order statistical texture features estimated from the SGLCM are then applied to a Feed-forward Neural Network (FNN) and Globus toolkit for the characterization of suspected liver tissue from MRI images for hepatic lesions classification.This project proposed an automated distributed processing framework for high-throughput, large-scale applications targeted for characterization of liver texture statistical measurements mainly healthy liver, fatty liver, liver cyst for MRI (Magnetic Resonance Imaging) images.Table 1 lists eight second-order statistical calculations based on SGLCM, namely, contrast, entropy, correlation, homogeneity, cluster tendency, inverse difference moment, energy, and angular second moment, which have shown useful results in hepatic lesions classification for liver tumor using Computed Tomography (CT), Ultrasonography (US) and www.intechopen.com