Abstract
With the wide application of nuclear magnetic resonance imaging, the multiplicative bias field in nuclear magnetic resonance images has created great difficulties for doctors in reading diagnostics and for computers in autoprocessing. Most previous methods eliminate the bias field in the image by estimating a single unknown bias field. An improved method that uses the nonparametric maximum likelihood to jointly eliminate bias from multiple magnetic resonance imaging (MRI) images is proposed in this paper. The method uses the statistics from the same location across different patient images, rather than within an image, and builds a “multiresolution” nonparametric tissue model conditioned on image location. We use a separate and nonparametric model to consider the intensity values at each pixel and utilize nonparametric maximum likelihood distance measures to simultaneously eliminate the bias of magnetic resonance (MR) images from different patients. Finally, the performance of the same was tested on a synthetic MRI dataset and a real MRI dataset and is found that the proposed algorithm provides better performance than the method of using entropy minimization across images and the most popular and widely used method, N4.
Highlights
With the rapid development of medical imaging technology as a non-invasive, non-ionizing radiation diagnostic tool, magnetic resonance imaging (MRI) has increasingly become a commonly used detection method in clinical practice
PROBLEM DESCRIPTION AND IMAGE MODEL It is assumed that each image I i (1 ≤ i ≤ N ) in a brain MR image set I I 1, I 2, . . . , I N contaminated by a bias field obtained from a fixed population can be approximated by a multiplicative field [6], which can be expressed by the following mathematical model: I i (x, y) = Li (x, y)∗ Bi (x, y) + NO (x, y), (1)
The problem of bias field exists in an MR image because it is contaminated by the multiplicative bias field
Summary
With the rapid development of medical imaging technology as a non-invasive, non-ionizing radiation diagnostic tool, magnetic resonance imaging (MRI) has increasingly become a commonly used detection method in clinical practice. Viola [14] proposed a nonparametric method, which assumes that he bias correction field would be estimated by minimizing the distribution entropy of pixel brightness This method solves several problems of the fixed tissue parameter model, the statistical model only comes from the data of a single image, which is weak, and no mechanism exists to distinguish selected low-frequency image components from the bias field. The algorithm utilizes data from multiple MR images of different patients to provide improved distribution estimation, establishes a ‘‘multiresolution’’ nonparametric tissue model based on image position, and uses entropy minimization measures to remove bias across images. This approach reduces the need for unbiased images in model creation. The improved method can greatly reduce the calculation amount and enhance the calculation speed in the case of a large number of images, and can achieve a better bias removal effect when the number of images is small and the image corruption is serious
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
