Volume and surface coil simultaneous reception (VSSR) method for intensity inhomogeneity correction in MRI

BACKGROUND: Addressing intensity inhomogeneity is critical in magnetic resonance imaging (MRI) because associated errors can adversely affect post-processing and quantitative analysis of images (i.e., segmentation, registration, etc.), as well as the accuracy of clinical diagnosis. Although several prior methods have been proposed to eliminate or correct intensity inhomogeneity, some significant disadvantages have remained, including alteration of tissue contrast, poor reliability and robustness of algorithms, and prolonged acquisition time. OBJECTIVE: In this study, we propose an intensity inhomogeneity correction method based on volume and surface coils simultaneous reception (VSSR). METHODS: The VSSR method comprises of two major steps: 1) simultaneous image acquisition from both volume and surface coils and 2) denoising of volume coil images and polynomial surface fitting of bias field. Extensive in vivo experiments were performed considering various anatomical structures, acquisition sequences, imaging resolutions, and orientations. In terms of correction performance, the proposed VSSR method was comparatively evaluated against several popular methods, including multiplicative intrinsic component optimization and improved nonparametric nonuniform intensity normalization bias correction methods. RESULTS: Experimental results show that VSSR is more robust and reliable and does not require prolonged acquisition time with the volume coil. CONCLUSION: The VSSR may be considered suitable for general implementation.

A weighted region-based level set method for image segmentation with intensity inhomogeneity

Image segmentation is a fundamental task in image processing and is still a challenging problem when processing images with high noise, low resolution and intensity inhomogeneity. In this paper, a weighted region-based level set method, which is based on the techniques of local statistical theory, level set theory and curve evolution, is proposed. Specifically, a new weighted pressure force function (WPF) is first presented to flexibly drive the closed contour to shrink or expand outside and inside of the object. Second, a faster and smoother regularization term is added to ensure the stability of the curve evolution and that there is no need for initialization in curve evolution. Third, the WPF is integrated into the region-based level set framework to accelerate the speed of the curve evolution and improve the accuracy of image segmentation. Experimental results on medical and natural images demonstrate that the proposed segmentation model is more efficient and robust to noise than other state-of-the-art models.

Novel Filtering Methods for Image and Video Processing Applications

During the last few years, digital filtering methods for image/video processing applications have reached a satisfactory level. However, their performance degrades in the presence of noise, trend, motion, shape deformation, intensity inhomogeneity, shadows, or low image quality, to name a few. To cope with these challenges, this dissertation presents novel filtering methods for image/video processing applications that outperform the existing and state-of-the-art methods. The dissertation starts by introducing a novel trend filtering method that transforms the inter-frame registration problem into low complexity trend filtering problem. In the proposed method, Laplacian eigenmaps in conjunction with the modified empirical mode decomposition has been used to suppress the noise artifacts and the trend term. In multi-dimensional signals, the trend term is often referred to as non-uniform illumination or global intensity inhomogeneity. This dissertation presents a new filtering method for estimating the global intensity inhomogeneity in two dimensional and volume images. Global intensity inhomogeneity often arises due to the imperfections of data acquisition device, direction of source light, and properties of the subject under study. The proposed method generates a high-pass filter based on the grey-weighted distance transform of the frequency content of an image/volume. It provides an accurate estimation of global intensity inhomogeneity without any parameter tweaking, which makes it applicable to many imaging modalities. The dissertation also presents a filtering methodology to cope with local intensity inhomogeneity that gives rise to shadow artifacts. These artifacts appear as sharp discontinuities and are often corrected at different scales and orientations. The proposed method makes use of decimation-free directional filter bank to suppress the local intensity inhomogeneity and shadow artifacts irrespective of scale and orientation. In addition to intensity inhomogeneity correction, the dissertation also presents a filtering method that utilizes the Gabor filter bank to generate rotation invariant feature codes. The effectiveness of the proposed method has been evaluated in both identification and verification modes for fingerprint recognition. The uniqueness of the presented filtering methods lies in the fact that they are essentially parameter free and can easily be scaled to higher dimensions. This makes them applicable to many different image/video processing applications with least of effort from the end user, i.e., eliminating the user biases.

Novel Filtering Methods for Image and Video Processing Applications

During the last few years, digital filtering methods for image/video processing applications have reached a satisfactory level. However, their performance degrades in the presence of noise, trend, motion, shape deformation, intensity inhomogeneity, shadows, or low image quality, to name a few. To cope with these challenges, this dissertation presents novel filtering methods for image/video processing applications that outperform the existing and state-of-the-art methods. The dissertation starts by introducing a novel trend filtering method that transforms the inter-frame registration problem into low complexity trend filtering problem. In the proposed method, Laplacian eigenmaps in conjunction with the modified empirical mode decomposition has been used to suppress the noise artifacts and the trend term. In multi-dimensional signals, the trend term is often referred to as non-uniform illumination or global intensity inhomogeneity. This dissertation presents a new filtering method for estimating the global intensity inhomogeneity in two dimensional and volume images. Global intensity inhomogeneity often arises due to the imperfections of data acquisition device, direction of source light, and properties of the subject under study. The proposed method generates a high-pass filter based on the grey-weighted distance transform of the frequency content of an image/volume. It provides an accurate estimation of global intensity inhomogeneity without any parameter tweaking, which makes it applicable to many imaging modalities. The dissertation also presents a filtering methodology to cope with local intensity inhomogeneity that gives rise to shadow artifacts. These artifacts appear as sharp discontinuities and are often corrected at different scales and orientations. The proposed method makes use of decimation-free directional filter bank to suppress the local intensity inhomogeneity and shadow artifacts irrespective of scale and orientation. In addition to intensity inhomogeneity correction, the dissertation also presents a filtering method that utilizes the Gabor filter bank to generate rotation invariant feature codes. The effectiveness of the proposed method has been evaluated in both identification and verification modes for fingerprint recognition. The uniqueness of the presented filtering methods lies in the fact that they are essentially parameter free and can easily be scaled to higher dimensions. This makes them applicable to many different image/video processing applications with least of effort from the end user, i.e., eliminating the user biases.

Multi-Feature Driven Active Contour Segmentation Model for Infrared Image With Intensity Inhomogeneity

Active contour model (ACM) is one of the most widely used image segmentation tools at present, but the existing methods only utilize single feature information of image to minimize the energy function, which is easy to cause false segmentations in infrared (IR) images. In this paper, we propose a multi-feature driven active contour segmentation model to handle IR images with intensity inhomogeneity. Firstly, an especially-designed signed pressure force (SPF) function is constructed by combining the global information calculated by global average gray information and the local multi-feature information calculated by local entropy, local standard deviation and gradient information. Then, we draw upon adaptive weight coefficient computed by local range to incorporate the afore-mentioned global term and local term. Next, the SPF function is substituted into the level set formulation (LSF) for further evolution. Finally, the LSF converges after a finite number of iterations and the IR image segmentation result is obtained from the corresponding convergence result. Experimental results demonstrate that the presented method outperforms typical models in terms of precision rate and overlapping rate in IR test images.

A Fully Automatic Procedure for Brain Tumor Segmentation from Multi-Spectral MRI Records Using Ensemble Learning and Atlas-Based Data Enhancement

The accurate and reliable segmentation of gliomas from magnetic resonance image (MRI) data has an important role in diagnosis, intervention planning, and monitoring the tumor’s evolution during and after therapy. Segmentation has serious anatomical obstacles like the great variety of the tumor’s location, size, shape, and appearance and the modified position of normal tissues. Other phenomena like intensity inhomogeneity and the lack of standard intensity scale in MRI data represent further difficulties. This paper proposes a fully automatic brain tumor segmentation procedure that attempts to handle all the above problems. Having its foundations on the MRI data provided by the MICCAI Brain Tumor Segmentation (BraTS) Challenges, the procedure consists of three main phases. The first pre-processing phase prepares the MRI data to be suitable for supervised classification, by attempting to fix missing data, suppressing the intensity inhomogeneity, normalizing the histogram of observed data channels, generating additional morphological, gradient-based, and Gabor-wavelet features, and optionally applying atlas-based data enhancement. The second phase accomplishes the main classification process using ensembles of binary decision trees and provides an initial, intermediary labeling for each pixel of test records. The last phase reevaluates these intermediary labels using a random forest classifier, then deploys a spatial region growing-based structural validation of suspected tumors, thus achieving a high-quality final segmentation result. The accuracy of the procedure is evaluated using the multi-spectral MRI records of the BraTS 2015 and BraTS 2019 training data sets. The procedure achieves high-quality segmentation results, characterized by average Dice similarity scores of up to 86%.