Download or read book Malignancy Classification with Parallel 4-D Co-occurrence Texture Analysis of Dynamic Contrast Enhanced Magnetic Resonance Image Data written by Brent James Woods and published by . This book was released on 2005 with total page 366 pages. Available in PDF, EPUB and Kindle. Book excerpt: Abstract: Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) is consider to have great potential in cancer diagnosis and monitoring. During the DCE-MRI procedure, repeated MRI scans are used to monitor contrast agent movement through the vascular system and into tissue. By observing the vascular permeability characteristics, radiologists can detect and classify malignant tissues. When used for diagnostic purposes, the DCE-MRI procedure often requires manual detection, classification, and marking of tumor tissues. This process can be time consuming and fatiguing especially when multiple DCE-MRI procedures must be processed to monitor the progress of a cancer therapy. Texture analysis is one possible method to detect features in biomedical images. During texture analysis, texture related information is found by examining local variations in image brightness. 4-dimensional (4-D) Haralick texture analysis is a method that extracts local variations along space and time dimensions and represents them as a collection of fourteen statistical parameters. However, the application of the 4D Haralick method on large time-dependent image datasets (such as DCE-MRI datasets) is hindered by computation and memory requirements. However, if the DCE-MRI dataset is distributed to many computers, portions of the dataset may be processed simultaneously. In this way, inexpensive supercomputing is achieved. This study presents a parallel implementation of 4-D Haralick texture analysis on PC clusters. We present a performance evaluation of our implementation on a cluster of PCs. Our results show that good performance can be achieved for this application via combined use of task- and data-parallelism. Using the results of texture analysis, a tissue classification may be used to differentiate tissues in DCE-MRI studies. This study presents a pattern recognition system that uses a neural network to classify malignant and non-malignant tissues. For several DCE-MRI studies, we perform malignancy classification and compare the neural network results with images where the tumor is marked by a radiologist. Our results show that the classification system performs well and has adjustable sensitivity. In addition, our results show that classification results are influenced by factors such as patient motion, contrast agent amount, and contrast agent type.