Background noise removal in cardiac magnetic resonance images using Bayes classifier

Imaging of the heart anatomy and function using magnetic resonance imaging (MRI) is a powerful tool for diagnosing a number of heart diseases. Recently, a technique was developed to acquire cine sequence of the heart that generates a null (black) signal intensity for the blood aiming to increase the image contrast-to-noise ratio between the myocardium and the background. Nevertheless, the technique inherently suffers from elevated noise level which limits the contrast-to-noise ratio. In this work, a probabilistic model for blood and tissue signals is developed and used to build a Bayes decision function. The Bayes classifier is then used to identify and filter out the background signal. Numerical simulation and real MRI data are used to test and validate the proposed method. The results show that the proposed method can increase the contrast-to-noise ratio by a factor of four.