Intensity Inhomogeneity Artifacts Research Articles

A spatially constrained skew Student’s-t mixture model for brain MR image segmentation and bias field correction

Accurate segmentation of brain magnetic resonance images is a key step in quantitative analysis of brain images. Finite mixture model is one of the most widely used methods in brain magnetic resonance image segmentation. However, due to the presence of intensity inhomogeneity artifact and noise, the image histogram distribution of brain MR images may follow a heavy tailed distribution or asymmetric distribution, which makes traditional finite mixture model, such as Gaussian mixture model, hard to achieve accurate segmentation results. To alleviate these problems, a novel spatially constrained finite skew student’s-t mixture model is proposed in this paper. Firstly, we propose anisotropic two-level spatial information, which combines the prior and posterior probabilities, to reduce the impact of noise. The proposed spatial information can preserve rich details, such as edges and corners. Secondly, we couple the anisotropic spatial information into the skew student’s-t distribution to fit the intensity distribution of observation data with heavy tail distribution or asymmetric distribution. Thirdly, we use a linear combination of a set of orthogonal basis functions to model the intensity inhomogeneities. Finally, the objective function integrates both tissue segmentation and the bias field estimation. In the implementation, we used an improved expectation maximization (EM) algorithm to estimate the model parameters. The experimental results of our model on synthetic data and brain magnetic resonance images are better than other state-of-the-art segmentation methods.

Hybrid Learning Model for Metal Artifact Reduction

In today’s healthcare, the human brain imaging is done for finding the tumors and other disorders of the brain. The Magnetic Resonance Imaging (MRI) plays a significant role throughout the complete clinical procedure starting from diagnostics and treatment planning to surgical processes and follow up studies. The MRI of brain allows the clinical expert for the earliest detection and treatment of brain abnormality or any neurological diseases, which is the most treatable stage that gives patients the greatest chance of survival. An artifact is a feature appearing in an image which is not present in the original imaged object. The types of artifacts are herringbone artifact, zipper artifact, motion artifact, aliasing artifact, chemical shift artifact, magnetic susceptibility artifact, central point artifact, Gibbs ringing artifact and intensity inhomogeneity artifact. After segmentation, the features are extracted using Gray level co-occurrence matrix (GLCM) and an CNN, Deep belief network, Proposed hybrid model (Based on CNN and Deep belief network (DBN)) and Morphological Technique with Segmentation Techniques is implemented to classify the brain MRI images as either normal (without tumor) or abnormal (with tumor). Proposed hybrid model for metal artifact reduction and represent though the experiment our proposed model very effective to existing one. Results in Accuracy (in %) Before artifact removal(92.12%), After artifact removal (95.77%)

An unsupervised orthogonal rotation invariant moment based fuzzy C-means approach for the segmentation of brain magnetic resonance images

Brain magnetic resonance images (MRI) suffer from many artifacts such as noise and intensity inhomogeneity. Moreover, they contain an abundant amount of fine image structures, edges, and corners in various areas of the image. These anomalies and structural complexities affect the segmentation process of the brain MRI which is required by physicians for the diagnosis purpose. Recently, we have proposed a local Zernike moment (LZM)-based unbiased nonlocal means fuzzy C-means (LZM-UNLM-FCM) approach that has dealt with the noise artifact in the moment domain using the LZM approach. The method provides high segmentation results for the MR images corrupted with Rician noise. However, the method does not deal with the intensity inhomogeneity artifact effectively. Moreover, the method uses a regularization parameter that needs to be adjusted to obtain effective segmentation results. This paper presents an unsupervised local Zernike moment and unbiased nonlocal means-based bias corrected fuzzy C-means (LZM-UNLM-BCFCM) approach that deals with both noise and intensity inhomogeneity artifacts. The main concept behind the proposed method is to use the attractive properties of the LZMs to effectively filter the image by determining a large number of similar regions in an MR image which is mostly corrupted by Rician noise and intensity inhomogeneity. The ability of the LZMs to determine such regions in MR images consisting of fine tissue structures in any orientation is well utilized for dealing with the high levels of noise. The intensity inhomogeneity is removed by estimating the bias field pixel-by-pixel during the segmentation process using the filtered image without the use of regularization parameter. The bias field is estimated as a linear combination of the orthogonal polynomials in which the weights are obtained by minimizing the fuzzy objective function. Experimental results on both simulated and real MR images show the superiority of the proposed method as compared to other unsupervised state-of-the-art approaches.

Automatic brain tissue segmentation in fetal MRI using convolutional neural networks

MR images of fetuses allow clinicians to detect brain abnormalities in an early stage of development. The cornerstone of volumetric and morphologic analysis in fetal MRI is segmentation of the fetal brain into different tissue classes. Manual segmentation is cumbersome and time consuming, hence automatic segmentation could substantially simplify the procedure. However, automatic brain tissue segmentation in these scans is challenging owing to artifacts including intensity inhomogeneity, caused in particular by spontaneous fetal movements during the scan. Unlike methods that estimate the bias field to remove intensity inhomogeneity as a preprocessing step to segmentation, we propose to perform segmentation using a convolutional neural network that exploits images with synthetically introduced intensity inhomogeneity as data augmentation. The method first uses a CNN to extract the intracranial volume. Thereafter, another CNN with the same architecture is employed to segment the extracted volume into seven brain tissue classes: cerebellum, basal ganglia and thalami, ventricular cerebrospinal fluid, white matter, brain stem, cortical gray matter and extracerebral cerebrospinal fluid. To make the method applicable to slices showing intensity inhomogeneity artifacts, the training data was augmented by applying a combination of linear gradients with random offsets and orientations to image slices without artifacts. To evaluate the performance of the method, Dice coefficient (DC) and Mean surface distance (MSD) per tissue class were computed between automatic and manual expert annotations. When the training data was enriched by simulated intensity inhomogeneity artifacts, the average achieved DC over all tissue classes and images increased from 0.77 to 0.88, and MSD decreased from 0.78 mm to 0.37 mm. These results demonstrate that the proposed approach can potentially replace or complement preprocessing steps, such as bias field corrections, and thereby improve the segmentation performance.

Rough Sets and Stomped Normal Distribution for Simultaneous Segmentation and Bias Field Correction in Brain MR Images.

The segmentation of brain MR images into different tissue classes is an important task for automatic image analysis technique, particularly due to the presence of intensity inhomogeneity artifact in MR images. In this regard, this paper presents a novel approach for simultaneous segmentation and bias field correction in brain MR images. It integrates judiciously the concept of rough sets and the merit of a novel probability distribution, called stomped normal (SN) distribution. The intensity distribution of a tissue class is represented by SN distribution, where each tissue class consists of a crisp lower approximation and a probabilistic boundary region. The intensity distribution of brain MR image is modeled as a mixture of finite number of SN distributions and one uniform distribution. The proposed method incorporates both the expectation-maximization and hidden Markov random field frameworks to provide an accurate and robust segmentation. The performance of the proposed approach, along with a comparison with related methods, is demonstrated on a set of synthetic and real brain MR images for different bias fields and noise levels.

An Example-Based Brain MRI Simulation Framework.

The simulation of magnetic resonance (MR) images plays an important role in the validation of image analysis algorithms such as image segmentation, due to lack of sufficient ground truth in real MR images. Previous work on MRI simulation has focused on explicitly modeling the MR image formation process. However, because of the overwhelming complexity of MR acquisition these simulations must involve simplifications and approximations that can result in visually unrealistic simulated images. In this work, we describe an example-based simulation framework, which uses an "atlas" consisting of an MR image and its anatomical models derived from the hard segmentation. The relationships between the MR image intensities and its anatomical models are learned using a patch-based regression that implicitly models the physics of the MR image formation. Given the anatomical models of a new brain, a new MR image can be simulated using the learned regression. This approach has been extended to also simulate intensity inhomogeneity artifacts based on the statistical model of training data. Results show that the example based MRI simulation method is capable of simulating different image contrasts and is robust to different choices of atlas. The simulated images resemble real MR images more than simulations produced by a physics-based model.

Rough Sets for Bias Field Correction in MR Images Using Contraharmonic Mean and Quantitative Index

One of the challenging tasks for magnetic resonance (MR) image analysis is to remove the intensity inhomogeneity artifact present in MR images, which often degrades the performance of an automatic image analysis technique. In this regard, the paper presents a novel approach for bias field correction in MR images. It judiciously integrates the merits of rough sets and contraharmonic mean. While the contraharmonic mean is used in low-pass averaging filter to estimate the bias field in multiplicative model, the concept of lower approximation and boundary region of rough sets deals with vagueness and incompleteness in filter structure definition. A theoretical analysis is presented to justify the use of both rough sets and contraharmonic mean for bias field estimation. The integration enables the algorithm to estimate optimum or near optimum bias field. Some new quantitative indexes are introduced to measure intensity inhomogeneity artifact present in a MR image. The performance of the proposed approach, along with a comparison with other approaches, is demonstrated on both simulated and real MR images for different bias fields and noise levels.

Symmetric diffeomorphic modeling of longitudinal structural MRI.

This technology report describes the longitudinal registration approach that we intend to incorporate into SPM12. It essentially describes a group-wise intra-subject modeling framework, which combines diffeomorphic and rigid-body registration, incorporating a correction for the intensity inhomogeneity artifact usually seen in MRI data. Emphasis is placed on achieving internal consistency and accounting for many of the mathematical subtleties that most implementations overlook. The implementation was evaluated using examples from the OASIS Longitudinal MRI Data in Non-demented and Demented Older Adults.

A Generalized Finite Sized Dipole Model for Radar and Medical Imaging Part Ii: Near Field Formulation for Magnetic Resonance Imaging

This paper presents a magnetic dipole-based formulation of near-electromagnetic field magnetic resonance imaging (MRI) problem and the development of an algorithm to perform correct medical diagnosis and image reconstruction from near-field measurements of radio frequency pulses in MRI. Magnetic resonance imaging uses electromagnetic signals to obtain high-resolution images of the human biological structure. This information is represented by color coded images, where the intensity of the color shows the concentration of the different constituent matter present. The constituent matter, have different chemical and electromagnetic properties and these properties define the nature of the electromagnetic signals radiated from these regions. The radiating regions in the biological structure are modeled by discrete magnetic dipoles and a more complete time-domain signal, encompassing the near electromagnetic fields. Using this new signal model, intensity inhomogeneity artifact in MR images is explained and corrected.