Accurate template-based correction of brain MRI intensity distortion with application to dementia and aging

Breaking barriers: a statistical and machine learning-based hybrid system for predicting dementia

Introduction: Dementia is a condition (a collection of related signs and symptoms) that causes a continuing deterioration in cognitive function, and millions of people are impacted by dementia every year as the world population continues to rise. Conventional approaches for determining dementia rely primarily on clinical examinations, analyzing medical records, and administering cognitive and neuropsychological testing. However, these methods are time-consuming and costly in terms of treatment. Therefore, this study aims to present a noninvasive method for the early prediction of dementia so that preventive steps should be taken to avoid dementia. Methods: We developed a hybrid diagnostic system based on statistical and machine learning (ML) methods that used patient electronic health records to predict dementia. The dataset used for this study was obtained from the Swedish National Study on Aging and Care (SNAC), with a sample size of 43040 and 75 features. The newly constructed diagnostic extracts a subset of useful features from the dataset through a statistical method (F-score). For the classification, we developed an ensemble voting classifier based on five different ML models: decision tree (DT), naive Bayes (NB), logistic regression (LR), support vector machines (SVM), and random forest (RF). To address the problem of ML model overfitting, we used a cross-validation approach to evaluate the performance of the proposed diagnostic system. Various assessment measures, such as accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curve, and Matthew's correlation coefficient (MCC), were used to thoroughly validate the devised diagnostic system's efficiency. Results: According to the experimental results, the proposed diagnostic method achieved the best accuracy of 98.25%, as well as sensitivity of 97.44%, specificity of 95.744%, and MCC of 0.7535. Discussion: The effectiveness of the proposed diagnostic approach is compared to various cutting-edge feature selection techniques and baseline ML models. From experimental results, it is evident that the proposed diagnostic system outperformed the prior feature selection strategies and baseline ML models regarding accuracy.

Bias field correction in hyperpolarized 129 Xe ventilation MRI using templates derived by RF-depolarization mapping

PURPOSE

To correct for RF inhomogeneity for in vivo 129 Xe ventilation MRI using flip-angle mapping enabled by randomized 3D radial acquisitions. To extend this RF-depolarization mapping approach to create a flip-angle map template applicable to arbitrary acquisition strategies, and to compare these approaches to conventional bias field correction.

METHODS

RF-depolarization mapping was evaluated first in digital simulations and then in 51 subjects who had undergone radial 129 Xe ventilation MRI in the supine position at 3T (views = 3600; samples/view = 128; TR/TE = 4.5/0.45 ms; flip angle = 1.5; FOV = 40 cm). The images were corrected using newly developed RF-depolarization and templated-based methods and the resulting quantitative ventilation metrics (mean, coefficient of variation, and gradient) were compared to those resulting from N4ITK correction.

RESULTS

RF-depolarization and template-based mapping methods yielded a pattern of RF-inhomogeneity consistent with the expected variation based on coil architecture. The resulting corrected images were visually similar, but meaningfully distinct from those generated using standard N4ITK correction. The N4ITK algorithm eliminated the physiologically expected anterior-posterior gradient (-0.04 ± 1.56%/cm, P < 0.001). These 2 newly introduced methods of RF-depolarization and template correction retained the physiologically expected anterior-posterior ventilation gradient in healthy subjects (2.77 ± 2.09%/cm and 2.01 ± 2.73%/cm, respectively).

CONCLUSIONS

Randomized 3D 129 Xe MRI ventilation acquisitions can inherently be corrected for bias field, and this technique can be extended to create flip angle templates capable of correcting images from a given coil regardless of acquisition strategy. These methods may be more favorable than the de facto standard N4ITK because they can remove undesirable heterogeneity caused by RF effects while retaining results from known physiology.

An Intelligent Learning System for Unbiased Prediction of Dementia Based on Autoencoder and Adaboost Ensemble Learning

Dementia is a neurological condition that primarily affects older adults and there is still no cure or therapy available to cure it. The symptoms of dementia can appear as early as 10 years before the beginning of actual diagnosed dementia. Hence, machine learning (ML) researchers have presented several methods for early detection of dementia based on symptoms. However, these techniques suffer from two major flaws. The first issue is the bias of ML models caused by imbalanced classes in the dataset. Past research did not address this issue well and did not take preventative precautions. Different ML models were developed to illustrate this bias. To alleviate the problem of bias, we deployed a synthetic minority oversampling technique (SMOTE) to balance the training process of the proposed ML model. The second issue is the poor classification accuracy of ML models, which leads to a limited clinical significance. To improve dementia prediction accuracy, we proposed an intelligent learning system that is a hybrid of an autoencoder and adaptive boost model. The autoencoder is used to extract relevant features from the feature space and the Adaboost model is deployed for the classification of dementia by using an extracted subset of features. The hyperparameters of the Adaboost model are fine-tuned using a grid search algorithm. Experimental findings reveal that the suggested learning system outperforms eleven similar systems which were proposed in the literature. Furthermore, it was also observed that the proposed learning system improves the strength of the conventional Adaboost model by 9.8% and reduces its time complexity. Lastly, the proposed learning system achieved classification accuracy of 90.23%, sensitivity of 98.00% and specificity of 96.65%.

A Review on the Rule-Based Filtering Structure with Applications on Computational Biomedical Images

In this paper, we present rule-based fuzzy inference systems that consist of a series of mathematical representations based on fuzzy concepts in the filtering structure. It is crucial for understanding and discussing different principles associated with fuzzy filter design procedures. A number of typical fuzzy multichannel filtering approaches are provided in order to clarify the different fuzzy filter designs and compare different algorithms. In particular, in most practical applications (i.e., biomedical image analysis), the emphasis is placed primarily on fuzzy filtering algorithms, with the main advantages of restoration of corrupted medical images and the interpretation capability, along with the capability of edge preservation and relevant image information for accurate diagnosis of diseases.

Machine Learning Classification Identifies Cerebellar Contributions to Early and Moderate Cognitive Decline in Alzheimer's Disease

Alzheimer's disease (AD) is one of the most common forms of dementia, marked by progressively degrading cognitive function. Although cerebellar changes occur throughout AD progression, its involvement and predictive contribution in its earliest stages, as well as gray or white matter components involved, remains unclear. We used MRI machine learning-based classification to assess the contribution of two tissue components [volume fraction myelin (VFM), and gray matter (GM) volume] within the whole brain, the neocortex, the whole cerebellum as well as its anterior and posterior parts and their predictive contribution to the first two stages of AD and typically aging controls. While classification accuracy increased with AD stages, VFM was the best predictor for all early stages of dementia when compared with typically aging controls. However, we document overall higher cerebellar prediction accuracy when compared to the whole brain with distinct structural signatures of higher anterior cerebellar contribution to mild cognitive impairment (MCI) and higher posterior cerebellar contribution to mild/moderate stages of AD for each tissue property. Based on these different cerebellar profiles and their unique contribution to early disease stages, we propose a refined model of cerebellar contribution to early AD development.

Active contours driven by local and global fitted image models for image segmentation robust to intensity inhomogeneity

This paper presents a region-based active contour method for the segmentation of intensity inhomogeneous images using an energy functional based on local and global fitted images. A square image fitted model is defined by using both local and global fitted differences. Moreover, local and global signed pressure force functions are introduced in the solution of the energy functional to stabilize the gradient descent flow. In the final gradient descent solution, the local fitted term helps extract regions with intensity inhomogeneity, whereas the global fitted term targets homogeneous regions. A Gaussian kernel is applied to regularize the contour at each step, which not only smoothes it but also avoids the computationally expensive re-initialization. Intensity inhomogeneous images contain undesired smooth intensity variations (bias field) that alter the results of intensity-based segmentation methods. The bias field is approximated with a Gaussian distribution and the bias of intensity inhomogeneous regions is corrected by dividing the original image by the approximated bias field. In this paper, a two-phase model is first derived and then extended to a four-phase model to segment brain magnetic resonance (MR) images into the desired regions of interest. Experimental results with both synthetic and real brain MR images are used for a quantitative and qualitative comparison with state-of-the-art active contour methods to show the advantages of the proposed segmentation technique in practical terms.

Multi-channel registration of fractional anisotropy and T1-weighted images in the presence of atrophy: application to multiple sclerosis

Co-registration of structural T1-weighted (T1w) scans and diffusion tensor imaging (DTI)-derived fractional anisotropy (FA) maps to a common space is of particular interest in neuroimaging, as T1w scans can be used for brain segmentation while DTI can provide microstructural tissue information. While the effect of lesions on registration has been tackled and solutions are available, the issue of atrophy is still open to discussion. Multi-channel (MC) registration algorithms have the advantage of maintaining anatomical correspondence between different contrast images after registration to any target space. In this work, we test the performance of an MC registration approach applied to T1w and FA data using simulated brain atrophy images. Experimental results are compared with a standard single-channel registration approach. Multi-channel registration of fractional anisotropy and T1-weighted images in the presence of atrophy: application to multiple sclerosis Both qualitative and quantitative evaluations are presented, showing that the MC approach provides better alignment with the target while maintaining better T1w and FA co-alignment.

Functional Magnetic Resonance Imaging Methods

Since its inception in 1992, Functional Magnetic Resonance Imaging (fMRI) has become an indispensible tool for studying cognition in both the healthy and dysfunctional brain. FMRI monitors changes in the oxygenation of brain tissue resulting from altered metabolism consequent to a task-based evoked neural response or from spontaneous fluctuations in neural activity in the absence of conscious mentation (the "resting state"). Task-based studies have revealed neural correlates of a large number of important cognitive processes, while fMRI studies performed in the resting state have demonstrated brain-wide networks that result from brain regions with synchronized, apparently spontaneous activity. In this article, we review the methods used to acquire and analyze fMRI signals.

Energy preserved sampling for compressed sensing MRI

The sampling patterns, cost functions, and reconstruction algorithms play important roles in optimizing compressed sensing magnetic resonance imaging (CS-MRI). Simple random sampling patterns did not take into account the energy distribution in k-space and resulted in suboptimal reconstruction of MR images. Therefore, a variety of variable density (VD) based samplings patterns had been developed. To further improve it, we propose a novel energy preserving sampling (ePRESS) method. Besides, we improve the cost function by introducing phase correction and region of support matrix, and we propose iterative thresholding algorithm (ITA) to solve the improved cost function. We evaluate the proposed ePRESS sampling method, improved cost function, and ITA reconstruction algorithm by 2D digital phantom and 2D in vivo MR brains of healthy volunteers. These assessments demonstrate that the proposed ePRESS method performs better than VD, POWER, and BKO; the improved cost function can achieve better reconstruction quality than conventional cost function; and the ITA is faster than SISTA and is competitive with FISTA in terms of computation time.

Differences in prefrontal, limbic, and white matter lesion volumes according to cognitive status in elderly patients with first-onset subsyndromal depression

The purpose of this preliminary study was to test the hypothesis that subsyndromal depression is associated with the volume of medial prefrontal regional gray matter and that of white matter lesions (WMLs) in the brains of cognitively normal older people. We also explored the relationships between subsyndromal depression and medial prefrontal regional gray matter volume, limbic regional gray matter volume, and lobar WMLs in the brains of patients with mild cognitive impairment (MCI) and Alzheimer's disease (AD). We performed a cross-sectional study comparing patients with subsyndromal depression and nondepressed controls with normal cognition (n = 59), MCI (n = 27), and AD (n = 27), adjusting for sex, age, years of education, and results of the Mini-Mental State Examination. Frontal WML volume was greater, and right medial orbitofrontal cortical volume was smaller in cognitively normal participants with subsyndromal depression than in those without subsyndromal depression. No volume differences were observed in medial prefrontal, limbic, or WML volumes according to the presence of subsyndromal depression in cognitively impaired patients. The absence of these changes in patients with MCI and AD suggests that brain changes associated with AD pathology may override the changes associated with subsyndromal depression.

Feasibility of semiautomated MR volumetry using gadoxetic acid-enhanced MRI at hepatobiliary phase for living liver donors

PURPOSE

To assess the feasibility of semiautomated MR volumetry using gadoxetic acid-enhanced MRI at the hepatobiliary phase compared with manual CT volumetry.

METHODS

Forty potential live liver donor candidates who underwent MR and CT on the same day, were included in our study. Semiautomated MR volumetry was performed using gadoxetic acid-enhanced MRI at the hepatobiliary phase. We performed the quadratic MR image division for correction of the bias field inhomogeneity. With manual CT volumetry as the reference standard, we calculated the average volume measurement error of the semiautomated MR volumetry. We also calculated the mean of the number and time of the manual editing, edited volume, and total processing time.

RESULTS

The average volume measurement errors of the semiautomated MR volumetry were 2.35% ± 1.22%. The average values of the numbers of editing, operation times of manual editing, edited volumes, and total processing time for the semiautomated MR volumetry were 1.9 ± 0.6, 8.1 ± 2.7 s, 12.4 ± 8.8 mL, and 11.7 ± 2.9 s, respectively.

CONCLUSION

Semiautomated liver MR volumetry using hepatobiliary phase gadoxetic acid-enhanced MRI with the quadratic MR image division is a reliable, easy, and fast tool to measure liver volume in potential living liver donors.

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.

Different associations of white matter lesions with depression and cognition

Background

To test the hypothesis that white matter lesions (WML) are primarily associated with regional frontal cortical volumes, and to determine the mediating effects of these regional frontal cortices on the associations of WML with depressive symptoms and cognitive dysfunction.

Methods

Structural brains MRIs were performed on 161 participants: cognitively normal, cognitive impaired but not demented, and demented participants. Lobar WML volumes, regional frontal cortical volumes, depressive symptom severity, and cognitive abilities were measured. Multiple linear regression analyses were used to identify WML volume effects on frontal cortical volume. Structural equation modeling was used to determine the MRI-depression and the MRI-cognition path relationships.

Results

WML predicted frontal cortical volume, particularly in medial orbirtofrontal cortex, irrespective of age, gender, education, and group status. WML directly predicted depressive score, and this relationship was not mediated by regional frontal cortices. In contrast, the association between WML and cognitive function was indirect and mediated by regional frontal cortices.

Conclusions

These findings suggest that the neurobiological mechanisms underpinning depressive symptoms and cognitive dysfunction in older adults may differ.

MRI non-uniformity correction through interleaved bias estimation and B-spline deformation with a template

We propose a template-based method for correcting field inhomogeneity biases in magnetic resonance images (MRI) of the human brain. At each algorithm iteration, the update of a B-spline deformation between an unbiased template image and the subject image is interleaved with estimation of a bias field based on the current template-to-image alignment. The bias field is modeled using a spatially smooth thin-plate spline interpolation based on ratios of local image patch intensity means between the deformed template and subject images. This is used to iteratively correct subject image intensities which are then used to improve the template-to-image deformation. Experiments on synthetic and real data sets of images with and without Alzheimer's disease suggest that the approach may have advantages over the popular N3 technique for modeling bias fields and narrowing intensity ranges of gray matter, white matter, and cerebrospinal fluid. This bias field correction method has the potential to be more accurate than correction schemes based solely on intrinsic image properties or hypothetical image intensity distributions.

Template-based B₁ inhomogeneity correction in 3T MRI brain studies

Low noise, high resolution, fast and accurate T₁ maps from MRI images of the brain can be performed using a dual flip angle method. However, B₁ field inhomogeneity, which is particularly problematic at high field strengths (e.g., 3T), limits the ability of the scanner to deliver the prescribed flip angle, introducing errors into the T₁ maps that limit the accuracy of quantitative analyses based on those maps. A dual repetition time method was used for acquiring a B₁ map to correct that inhomogeneity. Additional inaccuracies due to misregistration of the acquired T₁-weighted images were corrected by rigid registration, and the effects of misalignment on the T₁ maps were compared to those of B₁ inhomogeneity in 19 normal subjects. However, since B₁ map acquisition takes up precious scanning time and most retrospective studies do not have B₁ map, we designed a template-based correction strategy. B₁ maps from different subjects were aligned using a twelve-parameter affine registration. Recomputed T₁ maps showed an important improvement with respect to the noncorrected maps: histograms of all corrected maps exhibited two peaks corresponding to white and gray matter tissues, while unimodal histograms were observed in all uncorrected maps because of the inhomogeneity. A method to detect the best nonsubject-specific B₁ correction based on a set of features was designed. The optimum set of weighting factors for those features was computed. The best available B₁ correction was detected in almost all subjects while corrections comparable to the T₁ map corrected using the B₁ map from the same subject were detected in the others.

Evidence of neurodegeneration in brains of older adults who do not yet fulfill MCI criteria

We sought to determine whether there are structural and metabolic changes in the brains of older adults with cognitive complaints yet who do not meet MCI criteria (i.e., preMCI). We compared the volumes of regional lobar gray matter (GM) and medial temporal lobe structures, including the hippocampus, entorhinal cortex (ERC), fusiform and parahippocampal gyri, and metabolite ratios from the posterior cingulate in individuals who had a Clinical Demetia Rating (CDR) of 0.5, but who did not meet MCI criteria (preMCI, N=17), patients with mild cognitive impairment (MCI, N=13), and cognitively normal controls (N=18). Controls had more ERC, fusiform, and frontal gray matter volume than preMCI and MCI subjects and greater parahippocampal volume and more posterior cingulate N-acetylaspartate (NAA)/myoinosotil (mI) than MCI. There were no significant differences between MCI and preMCI subjects on any of these measures. These findings suggest there are neurodegenerative changes in the brains of older adults who have cognitive complaints severe enough to qualify for CDR=0.5 yet show no deficits on formal neuropsychological testing. The results further support the hypothesis that detection of individuals with very mild forms of Alzheimer's disease (AD) may be facilitated by use of the CDR, which emphasizes changes in cognition over time within individuals rather than comparison with group norms.

Influences of lobar gray matter and white matter lesion load on cognition and mood

Depressed mood is a frequent co-morbidity of dementia suggesting that they might share a common neuropathological substrate. Gray matter (GM) atrophy and white matter lesions (WML) have been described in both conditions. Our aims were to determine the relationship of GM and WML with cognition and depressed mood in the same population. Structural brain images were obtained from 42 controls, 20 Alzheimer's disease (AD) patients and 32 subjects with cognitive impairment/dementia due to subcortical cerebrovascular disease (vascCIND/IVD). Images were segmented to obtain lobar GM, white matter and WML volumes. Lobar WML had a negative effect on GM in all lobes in controls, on frontal, parietal and occipital GM in AD and on frontal GM in vascCIND/IVD. Frontal, temporal and hippocampal GM were associated with cognitive functions and frontal WML load with depressed mood. Cognitive function is associated with GM atrophy and depressed mood is associated with frontal WML. This indicates that although both often occur together, depressed mood and cognitive impairment have different pathological correlates.

Fast and robust multi-atlas segmentation of brain magnetic resonance images

We introduce an optimised pipeline for multi-atlas brain MRI segmentation. Both accuracy and speed of segmentation are considered. We study different similarity measures used in non-rigid registration. We show that intensity differences for intensity normalised images can be used instead of standard normalised mutual information in registration without compromising the accuracy but leading to threefold decrease in the computation time. We study and validate also different methods for atlas selection. Finally, we propose two new approaches for combining multi-atlas segmentation and intensity modelling based on segmentation using expectation maximisation (EM) and optimisation via graph cuts. The segmentation pipeline is evaluated with two data cohorts: IBSR data (N=18, six subcortial structures: thalamus, caudate, putamen, pallidum, hippocampus, amygdala) and ADNI data (N=60, hippocampus). The average similarity index between automatically and manually generated volumes was 0.849 (IBSR, six subcortical structures) and 0.880 (ADNI, hippocampus). The correlation coefficient for hippocampal volumes was 0.95 with the ADNI data. The computation time using a standard multicore PC computer was about 3-4 min. Our results compare favourably with other recently published results.

Evaluation of correction methods for coil-induced intensity inhomogeneities and their influence on trabecular bone structure parameters from MR images

Magnetic resonance (MR) imaging-based quantitative trabecular bone structure analysis has gained increasing interest in osteoporotic fracture risk assessment and treatment evaluation related to osteoporosis. In vivo MR images of anatomic regions such as the proximal femur and distal tibia are generally acquired with a surface coil in order to obtain sufficient sensitivity and resolution for quantification of the trabeculae. However, these coils introduce intensity inhomogeneities which affect the trabecular bone structure analysis. This work evaluates the applicability of a fully automatic coil correction by nonparametric nonuniform intensity normalization (N3) in the analysis of trabecular bone parameters. The ability to correct for coil-induced intensity inhomogeneity was evaluated ex vivo on proximal femur specimens scanned with both a surface coil and a volume coil, which allowed for a direct evaluation of the performance of the coil correction methods without any major confounding factors. In addition, trabecular bone parameter values were correlated with values from high-resolution peripheral computed tomography (HR-pQCT) scans, and the reproducibility of trabecular bone parameters was evaluated in an in vivo study of repeat hip MR scans. The trabecular bone parameters determined from MR surface coil scans processed with the N3 coil correction method showed significant correlation (p < 0.05) with corresponding values from homogeneous intensity data in the ex vivo study. This can be compared to the correlation without coil correction (p < 0.5), and coil correction using low-pass filtering (LPF) (p < 0.53). The in vivo interscan variability was reduced from 8.9% to 12.8% using LPF-based to 3.6%-8.4% (CV) using N3 coil correction; hence the results showed that N3 is advantageous to LPF-based coil correction. No significant differences in correlation to HR-pQCT data were found for the coil correction methods. The significant correlations with volume coil data and high reproducibility of the N3 processed data imply that N3 coil correction preserve image information while accurately correcting for coil-induced intensity inhomogeneities, which makes it suitable for quantitative analysis of trabecular bone structure from MR images acquired with surface coils.

Restoration of MRI data for intensity non-uniformities using local high order intensity statistics

MRI at high magnetic fields (>3.0 T) is complicated by strong inhomogeneous radio-frequency fields, sometimes termed the "bias field". These lead to non-biological intensity non-uniformities across the image. They can complicate further image analysis such as registration and tissue segmentation. Existing methods for intensity uniformity restoration have been optimized for 1.5 T, but they are less effective for 3.0 T MRI, and not at all satisfactory for higher fields. Also, many of the existing restoration algorithms require a brain template or use a prior atlas, which can restrict their practicalities. In this study an effective intensity uniformity restoration algorithm has been developed based on non-parametric statistics of high order local intensity co-occurrences. These statistics are restored with a non-stationary Wiener filter. The algorithm also assumes a smooth non-uniformity and is stable. It does not require a prior atlas and is robust to variations in anatomy. In geriatric brain imaging it is robust to variations such as enlarged ventricles and low contrast to noise ratio. The co-occurrence statistics improve robustness to whole head images with pronounced non-uniformities present in high field acquisitions. Its significantly improved performance and lower time requirements have been demonstrated by comparing it to the very commonly used N3 algorithm on BrainWeb MR simulator images as well as on real 4 T human head images.

A framework for in vivo quantification of regional brain folding in premature neonates

This paper describes and compares novel approaches to in vivo 3D measurement of brain surface folding in clinically acquired neonatal MR image data, which allows regional folding evaluation. Most of the current measures of folding are not independent of the area of the surface they are derived from. Therefore, applying them to whole-brain surfaces or subregions of different sizes results in differences which may or may not reflect true differences in folding. We address this problem by proposing new measures to quantify gyrification and two approaches to normalize previously defined measures. The method was applied to twelve premature infants (age 28-37 weeks) from which cerebrospinal fluid/gray matter and gray matter/white matter interface surfaces were extracted. Experimental results show that previous folding measures are sensitive to the area of the surface of analysis and that the area-independent measures proposed here provide significant improvements. Such a system provides a tool that facilitates the study of structural development in the neonatal brain within specific functional subregions, which may be critical in identifying later neurological impairment.

Population based analysis of directional information in serial deformation tensor morphometry

Deformation morphometry provides a sensitive approach to detecting and mapping subtle volume changes in the brain. Population based analyses of this data have been used successfully to detect characteristic changes in different neurodegenerative conditions. However, most studies have been limited to statistical mapping of the scalar volume change at each point in the brain, by evaluating the determinant of the Jacobian of the deformation field. In this paper we describe an approach to spatial normalisation and analysis of the full deformation tensor. The approach employs a spatial relocation and reorientation of tensors of each subject. Using the assumption of small changes, we use a linear modeling of effects of clinical variables on each deformation tensor component across a population. We illustrate the use of this approach by examining the pattern of significance and orientation of the volume change effects in recovery from alcohol abuse. Results show new local structure which was not apparent in the analysis of scalar volume changes.

A system for measuring regional surface folding of the neonatal brain from MRI

This paper describes a novel approach to in-vivo measurement of brain surface folding in clinically acquired neonatal MR image data, which allows evaluation of surface curvature within subregions of the cortex. This paper addresses two aspects of this problem. Firstly: normalization of folding measures to provide area-independent evaluation of surface folding over arbitrary subregions of the cortex. Secondly: automated parcellation of the cortex at a particular developmental stage, based on an approximate spatial normalization of previously developed anatomical boundaries. The method was applied to seven premature infants (age 28-37 weeks) from which gray matter and gray-white matter interface surfaces were extracted. Experimental results show that previous folding measures are sensitive to the size of the surface of analysis, and that the area independent measures proposed here provide significant improvements. Such a system provides a tool to allow the study of structural development in the neonatal brain within specific functional subregions, which may be critical in identifying later neurological impairment.

Brain functional localization: a survey of image registration techniques

Functional localization is a concept which involves the application of a sequence of geometrical and statistical image processing operations in order to define the location of brain activity or to produce functional/parametric maps with respect to the brain structure or anatomy. Considering that functional brain images do not normally convey detailed structural information and, thus, do not present an anatomically specific localization of functional activity, various image registration techniques are introduced in the literature for the purpose of mapping functional activity into an anatomical image or a brain atlas. The problems addressed by these techniques differ depending on the application and the type of analysis, i.e., single-subject versus group analysis. Functional to anatomical brain image registration is the core part of functional localization in most applications and is accompanied by intersubject and subject-to-atlas registration for group analysis studies. Cortical surface registration and automatic brain labeling are some of the other tools towards establishing a fully automatic functional localization procedure. While several previous survey papers have reviewed and classified general-purpose medical image registration techniques, this paper provides an overview of brain functional localization along with a survey and classification of the image registration techniques related to this problem.

Restoration of MRI Data for Field Nonuniformities using High Order Neighborhood Statistics

MRI at high magnetic fields (> 3.0 T ) is complicated by strong inhomogeneous radio-frequency fields, sometimes termed the "bias field". These lead to nonuniformity of image intensity, greatly complicating further analysis such as registration and segmentation. Existing methods for bias field correction are effective for 1.5 T or 3.0 T MRI, but are not completely satisfactory for higher field data. This paper develops an effective bias field correction for high field MRI based on the assumption that the nonuniformity is smoothly varying in space. Also, nonuniformity is quantified and unmixed using high order neighborhood statistics of intensity cooccurrences. They are computed within spherical windows of limited size over the entire image. The restoration is iterative and makes use of a novel stable stopping criterion that depends on the scaled entropy of the cooccurrence statistics, which is a non monotonic function of the iterations; the Shannon entropy of the cooccurrence statistics normalized to the effective dynamic range of the image. The algorithm restores whole head data, is robust to intense nonuniformities present in high field acquisitions, and is robust to variations in anatomy. This algorithm significantly improves bias field correction in comparison to N3 on phantom 1.5 T head data and high field 4 T human head data.

A review of methods for correction of intensity inhomogeneity in MRI

Medical image acquisition devices provide a vast amount of anatomical and functional information, which facilitate and improve diagnosis and patient treatment, especially when supported by modern quantitative image analysis methods. However, modality specific image artifacts, such as the phenomena of intensity inhomogeneity in magnetic resonance images (MRI), are still prominent and can adversely affect quantitative image analysis. In this paper, numerous methods that have been developed to reduce or eliminate intensity inhomogeneities in MRI are reviewed. First, the methods are classified according to the inhomogeneity correction strategy. Next, different qualitative and quantitative evaluation approaches are reviewed. Third, 60 relevant publications are categorized according to several features and analyzed so as to reveal major trends, popularity, evaluation strategies and applications. Finally, key evaluation issues and future development of the inhomogeneity correction field, supported by the results of the analysis, are discussed.

The fast automatic algorithm for correction of MR bias field

PURPOSE

To develop a method for efficient automatic correction of slow-varying nonuniformity in MR images.

MATERIALS AND METHODS

The original MR image is represented by a piecewise constant function, and the bias (nonuniformity) field of an MR image is modeled as multiplicative and slow varying, which permits to approximate it with a low-order polynomial basis in a "log-domain." The basis coefficients are determined by comparing partial derivatives of the modeled bias field with the original image.

RESULTS

We tested the resulting algorithm named derivative surface fitting (dsf) on simulated images and phantom and real data. A single iteration was sufficient in most cases to produce a significant improvement to the MR image's visual quality. dsf does not require prior knowledge of intensity distribution and was successfully used on brain and chest images. Due to its design, dsf can be applied to images of any modality that can be approximated as piecewise constant with a multiplicative bias field.

CONCLUSION

The resulting algorithm appears to be an efficient method for fast correction of slow varying nonuniformity in MR images.

A Review on MR Image Intensity Inhomogeneity Correction

Intensity inhomogeneity (IIH) is often encountered in MR imaging, and a number of techniques have been devised to correct this artifact. This paper attempts to review some of the recent developments in the mathematical modeling of IIH field. Low-frequency models are widely used, but they tend to corrupt the low-frequency components of the tissue. Hypersurface models and statistical models can be adaptive to the image and generally more stable, but they are also generally more complex and consume more computer memory and CPU time. They are often formulated together with image segmentation within one framework and the overall performance is highly dependent on the segmentation process. Beside these three popular models, this paper also summarizes other techniques based on different principles. In addition, the issue of quantitative evaluation and comparative study are discussed.

Deformation-based mapping of volume change from serial brain MRI in the presence of local tissue contrast change

This paper is motivated by the analysis of serial structural magnetic resonance imaging (MRI) data of the brain to map patterns of local tissue volume loss or gain over time, using registration-based deformation tensor morphometry. Specifically, we address the important confound of local tissue contrast changes which can be induced by neurodegenerative or neurodevelopmental processes. These not only modify apparent tissue volume, but also modify tissue integrity and its resulting MRI contrast parameters. In order to address this confound we derive an approach to the voxel-wise optimization of regional mutual information (RMI) and use this to drive a viscous fluid deformation model between images in a symmetric registration process. A quantitative evaluation of the method when compared to earlier approaches is included using both synthetic data and clinical imaging data. Results show a significant reduction in errors when tissue contrast changes locally between acquisitions. Finally, examples of applying the technique to map different patterns of atrophy rate in different neurodegenerative conditions is included.

Unified segmentation

A probabilistic framework is presented that enables image registration, tissue classification, and bias correction to be combined within the same generative model. A derivation of a log-likelihood objective function for the unified model is provided. The model is based on a mixture of Gaussians and is extended to incorporate a smooth intensity variation and nonlinear registration with tissue probability maps. A strategy for optimising the model parameters is described, along with the requisite partial derivatives of the objective function.

Deformation tensor morphometry of semantic dementia with quantitative validation

High-resolution structural MRI scans of 20 subjects diagnosed with semantic dementia were compared against scans of 20 cognitively normal control subjects using whole brain deformation tensor morphometry to study spatially consistent differences in local anatomical size. A fine lattice free-form volume registration algorithm was used to estimate a continuous mapping from a reference MRI to each individual subject MRI. The Jacobian of these transformations at each voxel were used to quantitatively map relative anatomical size in each individual brain. Intensity consistent filtering was applied to the determinant of these Jacobians. A careful validation using manually traced gyral anatomy was carried out and used to select an optimal deformation tensor filter scale at which to examine the anatomical size maps. General linear modeling at each voxel was used to decompose the influence of age and head size from the primary diagnosis. Maps of the T statistic of the diagnosis across the 40 subjects highlighted significant (P < 0.01 Bonferroni corrected) focal tissue contraction effects related to dementia diagnosis in the left temporal pole extending into the hippocampus, occipitotemporal gyrus and parahippocampal gyrus. Some evidence of greater focal contraction in gray over white matter was also apparent. Contraction effects were also seen, but with reduced significance in the right temporal anatomy, focused toward the temporal pole and hippocampal regions. Additional lower significance findings (P < 0.05 permutation corrected) were detected in the left superior frontal gyrus, left orbital gyrus and left parietal lobe.