Validation of Registration for Renal Dynamic Contrast Enhanced MRI Imaging
Journal Title: International Journal of Intelligent Systems and Applications in Engineering - Year 2016, Vol 4, Issue 3
Abstract
In Dynamic Contrast Enhanced Resonance Imaging (DCE-MRI), abdomen is scanned repeatedly and rapidly after injection of a contrast agent. During data acquisition, collected images suffer from the motion induced by the patient if he/she moves or breathes heavily during the scan. Therefore, these images should be aligned accurately to correct the motion. Recently, mutual information (MI) registration has become the first tool to register renal DCE-MRI images before any further processing. However, MI registration is sensitive to initial conditions and optimization methods, and it is bound to fail under certain conditions such as extreme movement or noise in the image. Therefore, if automated image analysis for renal DCE-MRI is to enter the clinical settings, it is necessary to have validation strategies that show the limitations of registration models on known datasets. In this study, two methods are introduced for the validation of registration of renal DCE-MRI images. The first method demonstrates how to use the inverse transform to generate realistic looking DCE-MRI kidney images and use them in validation. The second method shows how to generate checkerboard images and how to evaluate the goodness of registration for real DCE-MRI images. These validation methods can be incorporated into the registration studies to quantitatively and qualitatively demonstrate the success and the limitations of registration models.
Authors and Affiliations
Seniha Esen Yuksel *| Hacettepe University, Department of Electrical and Electronics Engineering, Ankara, Turkey.
Keywords
Related Articles
- EP ID EP800
- DOI 10.18201/ijisae.45496
- Views 427
- Downloads 23
Classification of Neurodegenerative Diseases using Machine Learning Methods
In this study, neurodegenerative diseases (Amyotrophic Lateral Sclerosis, Huntington’s disease, and Parkinson’s disease) were diagnosed and classified using force signals. In the classification, five machine learning al...
SVM-Based Sleep Apnea Identification Using Optimal RR-Interval Features of the ECG Signal
Sleep apnea (SA) is the most commonly known sleeping disorder characterized by pauses of airflow to the lungs and often results in day and night time symptoms such as impaired concentration, depression, memory loss, snor...
Epileptic State Detection: Pre-ictal, Inter-ictal, Ictal
Epileptic seizure detection and prediction from electroencephalography (EEG) is a vital area of research. In this study, Second-Order Difference Plot (SODP) is used to extract features based on consecutive difference of...
A highly Reliable and Fully Automated Classification System for Sleep Apnea Detection
Sleep apnea (SA) in the form of Obstructive sleep apnea (OSA) is becoming the most common respiratory disorder during sleep, which is characterized by cessations of airflow to the lungs. These cessations in breathing mus...
SLAM – Map Building and Navigation via ROS#
The presented work describes a ROS based control system of a Turtlebot robot for mapping and navigation in indoor environments. It presents the navigation of Turtlebot in self-created environment. The mapping process is...