Brain MR image restoration using an automatic trilateral filter with GPU-based acceleration
Journal
IEEE Transactions on Biomedical Engineering
Journal Volume
65
Journal Issue
2
Pages
400-413
Date Issued
2018
Author(s)
Abstract
Objective: Noise reduction in brain magnetic resonance (MR) images has been a challenging and demanding task. This study develops a new trilateral filter that aims to achieve robust and efficient image restoration. Methods: Extended from the bilateral filter, the proposed algorithm contains one additional intensity similarity funct-ion, which compensates for the unique characteristics of noise in brain MR images. An entropy function adaptive to intensity variations is introduced to regulate the contributions of the weighting components. To hasten the computation, parallel computing based on the graphics processing unit (GPU) strategy is explored with emphasis on memory allocations and thread distributions. To automate the filtration, image texture feature analysis associated with machine learning is investigated. Among the 98 candidate features, the sequential forward floating selection scheme is employed to acquire the optimal texture features for regularization. Subsequently, a two-stage classifier that consists of support vector machines and artificial neural networks is established to predict the filter parameters for automation. Results: A speedup gain of 757 was reached to process an entire MR image volume of 256 × 256 × 256 pixels, which completed within 0.5 s. Automatic restoration results revealed high accuracy with an ensemble average relative error of 0.53 ± 0.85% in terms of the peak signal-to-noise ratio. Conclusion: This self-regulating trilateral filter outperformed many state-of-the-art noise reduction methods both qualitatively and quantitatively. Significance: We believe that this new image restoration algorithm is of potential in many brain MR image processing applications that require expedition and automation. ? 1964-2012 IEEE.
Subjects
Automation; GPU; image restoration; MRI; neural networks; SVM; texture feature; trilateral filter
Other Subjects
Automation; Bandpass filters; Computer graphics; Computer graphics equipment; Graphics processing unit; Image coding; Image segmentation; Image texture; Magnetic resonance; Magnetic resonance imaging; Neural networks; Program processors; Restoration; Signal to noise ratio; Support vector machines; Automatic restorations; Graphics Processing Unit (GPU); Image restoration algorithms; Noise reduction methods; Peak signal to noise ratio; Texture features; Trilateral filter; Two-stage classifiers; Image reconstruction; acceleration; accuracy; algorithm; Article; artificial neural network; automation; entropy; image reconstruction; machine learning; mathematical model; neuroimaging; nuclear magnetic resonance imaging; qualitative analysis; quantitative analysis; signal noise ratio; support vector machine; Alzheimer disease; brain; diagnostic imaging; human; image processing; male; nuclear magnetic resonance imaging; procedures; Algorithms; Alzheimer Disease; Brain; Humans; Image Processing, Computer-Assisted; Magnetic Resonance Imaging; Male; Signal-To-Noise Ratio
Type
journal article