Download or read book Multispectral Co-occurrence Analysis for Automated Tumor Detection in Metastatic Medullary Thyroid Carcinoma written by Ryan D. Griffin and published by . This book was released on 2010 with total page 127 pages. Available in PDF, EPUB and Kindle. Book excerpt: Abstract: Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE MRI) has been shown to be capable of revealing local microvascular and perfusion properties of tissues. Tumor growth is dependent on local angiogenesis and is often characterised by an increased microvascular density and vascular leakiness. Because of this, DCE MRI has been established as a noninvasive tool for the diagnosis of many types of tumors and is also used to improve the radiologist's ability to delineate tumor from benign tissue. Co-occurrence analysis is a form of statistical analysis that is used to look for patterns in the co-occurrence of local values of different quantitative parameters. By performing a co-occurrence analysis of the data in the different spectral planes, statistical features can be determined that are descriptive of specific regions within the the volume. This thesis investigates the usefulness and robustness of using co-occurrence based analysis of calculated voxelwise pharmacokinetic parameters calculated from volume sets of DCE MRI data to generate inputs to an ANN classfier for identification and deliniation of cancerous lesions.