Improved EM-Based Tissue Segmentation and Partial Volume Effect Quantification in Multi-sequence Brain MRI

Diffusion-weighted (DW) magnetic resonance imaging (MRI) is a non-invasive imaging method, which can be used to investigate neural tracts in the white matter (WM) of the brain. Significant partial volume effects (PVEs) are present in the DW signal due to relatively large voxel sizes. These PVEs can be caused by both non-WM tissue, such as gray matter (GM) and cerebrospinal fluid (CSF), and by multiple non-parallel WM fiber populations. High angular resolution diffusion imaging (HARDI) methods have been developed to correctly characterize complex WM fiber configurations, but to date, many of the HARDI methods do not account for non-WM PVEs. In this work, we investigated the isotropic PVEs caused by non-WM tissue in WM voxels on fiber orientations extracted with constrained spherical deconvolution (CSD). Experiments were performed on simulated and real DW-MRI data. In particular, simulations were performed to demonstrate the effects of varying the diffusion weightings, signal-to-noise ratios (SNRs), fiber configurations, and tissue fractions. Our results show that the presence of non-WM tissue signal causes a decrease in the precision of the detected fiber orientations and an increase in the detection of false peaks in CSD. We estimated 35–50% of WM voxels to be affected by non-WM PVEs. For HARDI sequences, which typically have a relatively high degree of diffusion weighting, these adverse effects are most pronounced in voxels with GM PVEs. The non-WM PVEs become severe with 50% GM volume for maximum spherical harmonics orders of 8 and below, and already with 25% GM volume for higher orders. In addition, a low diffusion weighting or SNR increases the effects. The non-WM PVEs may cause problems in connectomics, where reliable fiber tracking at the WM–GM interface is especially important. We suggest acquiring data with high diffusion-weighting 2500–3000 s/mm2, reasonable SNR (~30) and using lower SH orders in GM contaminated regions to minimize the non-WM PVEs in CSD.

The correct interpretation of clinical positron emission tomography (PET) data depends largely on the physical limits of the PET scanner. The partial volume effect (PVE) is related to the size of the studied object compared to the spatial resolution. It represents one of the most important limiting factors in quantitative data analysis. This effect is increased in the case of atrophy, as in patients with Alzheimer disease (AD), and it influences measurement of the metabolic reduction generally seen in cerebral degeneration. In this case, interpretation can be biased, because cortical activity will be underestimated due to the atrophy. In general, anatomical images of AD patients have shown diffuse atrophy, while PET studies have found widespread hypometabolism affecting the parietal and temporal lobes. Although hypometabolic areas usually correspond to atrophic regions, they also occur without such changes. Thus, the aim is to differentiate authentic hypometabolism (decrease of glucose consumption per unit volume of gray matter) from that due to PVE from atrophy (cell loss). Consequently, we are using a method for three-dimensional (3D) correction of human PET data with 3D magnetic resonance imaging (MRI). We measured atrophy and metabolism by using both T1-weighted MR images and high and medium resolution PET scans. We injected 12 patients and controls with [18F]fluorodeoxyglucose for glucose consumption measurements. Atrophy was estimated in the following way. We isolated the cerebral structures, using a segmentation technique on the MRI scans, into gray matter (GM), white matter, and cerebrospinal fluid. We superimposed the PET images onto the MR images to obtain anatomo-functional correlations. We degraded the segmented MR images to the resolution of the PET images by a convolution process to create a PET image correction map. We corrected the metabolic PET data for the PVE. We studied the cerebral metabolic rate of glucose in the GM where metabolic variation is the most relevant to AD. By dealing with problems relating to the sensitivity to the segmentation and to the PET-MRI coregistration, computation of MRI convolution processes provided the degree of PVE on a pixel-by-pixel basis, allowing correction of hypometabolisms contained in GM PET values. Global cortical metabolism increased after correction for PVE by, on average, 29 and 24% for tomographs acquired with medium (TTV03 LETI) and high (ECAT 953B CTI/Siemens) resolution, respectively, whereas the cortical metabolism increased by 75 and 65% for the respective tomographs in AD patients. The difference of metabolism between scans after correction for PVE was less than before correction, decreasing from 31 to 17%. This difference was most marked in the frontal and temporal lobes. Fusion imaging allowed correction for PVE in metabolic data using 3D MRI and determination of whether a change in the apparent radiotracer concentration in PET data reflected an alteration in GM volume, a change in radiotracer concentration per unit volume of GM, or both.

MP2RAGE can generate uniform T1 -weighted images, which have been used for brain segmentation. However, there remain concerns about carrying out fast brain segmentation. To propose an acquisition-based method for fast segmentation of gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) of healthy human brains with fluid and white matter suppression (FLAWS) using MP2RAGE. Prospective. 12 volunteers (23-28 years, seven subjects; 51-62 years, five subjects). 3T/3D MPRAGE and FLAWS. The proposed method was evaluated by calculating tissue volumes and the spatial overlap with the segmentation results from FSL and SPM12. The processing time was recorded. A paired t-test was used to compare the tissue volumes of the proposed method with those from other segmentation methods RESULTS: For the 12 subjects, the tissue volume difference between the proposed and SPM12 were 3.2 ± 2.8%, 4.2 ± 2.5%, 18.2 ± 13.1% for GM, WM, and CSF, respectively. The relative difference between the proposed and FSL was over 14% for all tissue classes. The spatial overlap between the proposed and other methods were 87-94% for GM and WM and less than 80% for CSF. The GM and WM volumes of the proposed method were not significantly different from those of SPM12 using MPRAGE as the input (P = 0.5540 and P = 0.3115, respectively). The rest of the comparisons all showed significant differences between the proposed and other methods. Statistical analysis of the two subgroups yielded similar results. The mean processing time of one subject was 6.5, 185, and 165 seconds for the proposed method, FSL, and SPM12, respectively. Our method may be accurate for the segmentation of most brain structures using FLAWS. In addition, the proposed method is fast and applicable to the two distinct age ranges. 2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2018;48:1540-1550.

Segmentation of brain magnetic resonance imaging (MRI) data plays an important role in the computer-aided diagnosis and neuroscience research. Fuzzy c-means (FCM) clustering algorithm is one of the most usually used techniques for brain MRI image segmentation because of its fuzzy nature. However, the conventional FCM method fails to carry out segmentation well enough due to intensity inhomogeneity in MRI data. To overcome this issue, we propose an improved algorithm based on FCM clustering for segmentation of brain MRI data. Specifically, we modify the conventional FCM algorithm to allow for intensity inhomogeneity by introducing the regularization of the neighborhood influence and bias field. Results show that our proposed algorithm obtains reasonable segmentation of white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) from MRI data, which is superior to the expectation-maximization (EM) and conventional FCM methods.

Infant brain tissue segmentation from MRI data is a critical task in medical imaging, particularly challenging due to the evolving nature of tissue contrasts in the early months of life. The difficulty increases as gray matter (GM) and white matter (WM) intensities converge, making accurate segmentation challenging. This study aims to develop an improved U-net-based model to enhance the precision of automatic segmentation of cerebro-spinal fluid (CSF), GM, and WM in 10 infant brain MRIs using the iSeg-2017 dataset. The proposed method utilizes a U-net architecture with (2+1)Dconvolutional layers and skip connections. Preprocessing includes intensity normalization using histogram alignment to standardize MRI data across different records. The model was trained on the iSeg-2017 dataset, which comprises T1-weighted and T2-weighted MRI data from ten infant subjects. Cross-validation was performed to evaluate the model's segmentation performance. The model achieved an average accuracy of 92.2%, improving on previous methods by 0.7%. Sensitivity, precision, and Dice similarity scores were used to evaluate the performance, showing high levels of accuracy across different tissue types. The model demonstrated a slight bias toward misclassifying GM and WM, indicating areas for potential improvement. The results suggest that the U-net architecture is highly effective in segmenting infant brain tissues from MRI data. Future work will explore enhancements such as attention mechanisms and dual-network processing for further improving segmentation accuracy.

MRI & X-ray are the two methodologies widely used to visualize human anatomy. X-ray imaging is used when the details of bones have to be visualized whereas magnetic resonance imaging (MRI) provides rich three dimensional (3D) information about the human soft tissue anatomy. Segmentation of MRI images using intensity values is severely limited owing to in-homogeneities and partial volume effects. Edge based segmentation methods suffer from unsharp edges and gaps in boundaries. A number of other methods are also used. Here a method is presented to segment multidimensional images using a multiscale stacking approach (hyperstack) with either single parent or multiparent linking. A hyperstack is a voxel-based multiscale data structure whose levels are constructed by convolving the original image with a Gaussian kernel of increasing width. Between voxels at adjacent scale levels, child-parent linkages are established according to a model-directed linkage scheme. In the resulting tree-like data structure, roots are formed to indicate the most plausible locations in scale space where segments in the original image are represented by a single voxel. The final segmentation is obtained by tracing all root linkages.This will facilitate segmentation of grey matter, white matter and cerebrospinal fluid with minimum user interaction. Multiscale linking gives a significantly improved segmentation as compared with conventional (single-parent) linking.

This article proposes the distribution similarity measure–based Gaussian mixtures model for the contact-state (CS) modelling in force-guided robotic assembly processes of flexible rubber parts. The wrench (Cartesian force and torque) signals of the manipulated object are captured for different states of the given assembly process. The distribution similarity measure–based Gaussian mixtures model CS modelling scheme is employed in modelling the captured wrench signals for different CSs. The proposed distribution similarity measure–based Gaussian mixtures model CS modelling scheme uses the Gaussian mixtures model in modelling the captured signals. The parameters of the Gaussian mixtures models are computed using expectation maximisation. The optimal number of Gaussian mixtures model components for each CS model is determined by considering the classification success rate as an index for the similarity measure between the distribution of the captured signals and the developed models. The optimal number of Gaussian mixtures model components corresponds to the highest classification success rate; hence, object elasticity variation would be accommodated by properly choosing the optimal number of Gaussian mixtures model components. The performance of the proposed distribution similarity measure–based Gaussian mixtures model CS modelling strategy is evaluated by a test stand composed of a KUKA lightweight robot doing peg-in-hole assembly processes for flexible rubber objects. Two rubber objects with different elasticity are considered for two experiments; in the first experiment, an elastic peg of 30 Shore A hardness is considered and that of the second experiment has hardness of 6 Shore A which is even softer than the one used in experiment 1. Employing the proposed distribution similarity measure–based Gaussian mixtures model CS modelling strategy excellent classification success rate was obtained for both experiments. However, more Gaussian mixtures model components are required for the softer one that gives a strong impression of the non-stationarity behaviour increment for softer materials. Comparison is performed with the available CS modelling schemes and the distribution similarity measure–based Gaussian mixtures model is shown to provide the best classification success rate performance with a reduced computational time.

A method for quantitative analysis of multiple sclerosis (MS) was presented. An automatic self-adaptive image segmentation algorithm was first employed to classify voxels in multi- spectral magnetic resonance (MR) images. The segmentation results from multi-spectral MR images were then combined to obtain reliable results. The volumes of brain tissues and cerebral spinal fluid (CSF) were finally extracted. Since it is fully automated, the results of the segmentation algorithm are completely reproducible. The repeatability of the presented method was evaluated on volunteer data sets. The variation is less than 0.2% for the intra-cranial volume, the whole brain volume, the central CSF, the white matter (WM) and the gray matter (GM). The variation of 3% for the entire CSF is mainly due to the peripheral CSF part, which has more partial volume effect and is less important than the central one. Methods for minimizing this variation are under investigation. These measurements demonstrate the potential for study on whole brain atrophy and cerebral atrophy. Feasibility studies on 14 MS patients were performed. The results are promising.

The accurate modeling of uncertain variables, such as wind power and load uncertainty, is an essential foundation for the planning operation and scheduling decisions in power systems. Currently, Gaussian mixture model (GMM) and Dirichlet process mixture model (DPMM) are the primary techniques used to characterize uncertainties in power systems, which are commonly solved by expectation-maximization (EM) algorithm. However, for the massive data of uncertain variables, the algorithm encounters challenges in accurately obtaining GMM and DPMM with a lower time consumption. To address this issue, we propose a method for GMM uncertainty modeling in power systems considering the mutual assistance of latent variables. Specifically, the GMM of uncertain variables is first constructed, and the conditional probability is employed to characterize the mutual assistance of latent variables. Then, an improved EM algorithm is developed to obtain the optimal GMM parameters, in which the expectation step (E-step) and maximization step (M-step) of the algorithm are revised using the conditional probability. Importantly, the closed-form solutions for GMM parameters are rederived in the revised E-step and M-step. Finally, the proposed uncertainty modeling method is compared with the traditional GMM and DPMM on actual wind power and load data from Australia. The proposed method performs the efficiency and accuracy in characterizing uncertainty.

Event Abstract Back to Event Study of cerebral asymmetry in schizophrenia based on an novel automatic cerebral hemisphere segmentation method for MRI Lu Zhao1*, Ulla Ruotsalainen1, Jussi Hirvonen2, Jarmo Hietala3 and Jussi Tohka1 1 Tampere University of Technology, Finland 2 Turku PET Centre, Finland 3 University of Turku, Finland In this work, we statistically analyzed the cerebral volume asymmetry for schizophrenic and healthy populations by employing a novel and completely automatic cerebral hemisphere segmentation method for MRI. The segmentation method is based on the information of partial volume effect (PVE) and the partial differential equations based shape bottlenecks (PDE-SB) algorithm [1]. PVE is an inevitable problem of MRI, but it is rarely taken into account by the existing automatic MR brain image segmentation techniques. The PDE-SB algorithm can detect the bottlenecks connecting two parts of a complex object by simulating a steady state of the information transmission process between the two parts with partial differential equations. Our method consists of two major stages: compartmental brain decomposition [2] and cerebral hemisphere segmentation [3]. Firstly, a partial volume estimation approach [4] is used to obtain the partial volume voxel classification [into grey matter (GM), white matter (WM), cerebrospinal fluid (CSF), CSF/GM, GM/WM and CSF/background] and estimate the amount of each tissue type in each brain voxel. Then the WM+GM/WM region is split into compartmental seeds corresponding to cerebrum, cerebellum and brainstem utilizing the PDE-SB algorithm. The brain volume is compartmentally decomposed by reconstructing the original shapes of the three compartments from the compartmental seeds according to the compartmental boundary knowledge defined with partial volume information. The cerebrum portion is extracted from the decomposed brain volume, and the cerebral hemispheres are segmented with the PDE-SB algorithm and the partial volume estimation results. In this work, this method was applied to a set of clinical T1-weighted MR images of 18 schizophrenic (11 males, 7 females) and 19 healthy (12 males, 7 females) subjects. All subjects were right-handed, and the schizophrenic patients were never medicated. With the obtained PVE information and cerebral hemisphere segmentation, the asymmetry index (AI) was calculated for cerebrum, cerebral GM and cerebral WM. AI was defined as (VR-VL)/[1/2(VR+VL)]×100, where VR and VL were the volume sizes of the right and left hemispheres respectively. The permutation test was conducted to evaluate the statistical significance of the difference of acquired AIs between schizophrenic and healthy populations. Here, the null hypothesis was defined as that AIs of schizophrenic and healthy populations had identical probability distribution, and the significance level was selected as 0.05. According to the statistical analysis results, the cerebral GM volume asymmetry of female schizophrenic population had significantly different probability distribution from the female healthy population's (p=0.002). There were no significant difference between schizophrenic and healthy populations with regard to volume asymmetry in the other cases (p>0.05). Conference: Neuroinformatics 2008, Stockholm, Sweden, 7 Sep - 9 Sep, 2008. Presentation Type: Poster Presentation Topic: Neuroimaging Citation: Zhao L, Ruotsalainen U, Hirvonen J, Hietala J and Tohka J (2008). Study of cerebral asymmetry in schizophrenia based on an novel automatic cerebral hemisphere segmentation method for MRI. Front. Neuroinform. Conference Abstract: Neuroinformatics 2008. doi: 10.3389/conf.neuro.11.2008.01.069 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 28 Jul 2008; Published Online: 28 Jul 2008. * Correspondence: Lu Zhao, Tampere University of Technology, Tampere, Finland, lu.zhao@tut.fi Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Lu Zhao Ulla Ruotsalainen Jussi Hirvonen Jarmo Hietala Jussi Tohka Google Lu Zhao Ulla Ruotsalainen Jussi Hirvonen Jarmo Hietala Jussi Tohka Google Scholar Lu Zhao Ulla Ruotsalainen Jussi Hirvonen Jarmo Hietala Jussi Tohka PubMed Lu Zhao Ulla Ruotsalainen Jussi Hirvonen Jarmo Hietala Jussi Tohka Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

To develop a tissue correction for GABA-edited magnetic resonance spectroscopy (MRS) that appropriately addresses differences in voxel gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) fractions. Simulations compared the performance of tissue correction approaches. Corrections were then applied to in vivo data from 16 healthy volunteers, acquired at 3T. GM, WM, and CSF fractions were determined from T1 -weighted images. Corrections for CSF content, GM/WM GABA content, and water relaxation of the three compartments are combined into a single, fully corrected measurement. Simulations show that CSF correction increases the dependence of GABA measurements on GM/WM fraction, by an amount equal to the fraction of CSF. Furthermore, GM correction substantially (and nonlinearly) increases the dependence of GABA measurements on GM/WM fraction, for example, by a factor of over four when the voxel GM tissue fraction is 50%. At this tissue fraction, GABA is overestimated by a factor of 1.5. For the in vivo data, correcting for voxel composition increased measured GABA values (P < 0.001 for all regions), but did not reduce intersubject variance (P > 0.5 for all regions). Corrected GABA values differ significantly based on the segmentation procedure used (P < 0.0001) and tissue parameter assumptions made (P < 0.0001). We introduce a comprehensive tissue correction factor that adjusts GABA measurements to correct for different voxel compositions of GM, WM, and CSF.

In this study, we proposed ameliorated method for region of interest (ROI) study to improve its accuracy using partial volume effect (PVE). PVE which arose in volumetric images when more than one tissue type occur in a voxel, could be used to reduce an amount of gray matter and cerebrospinal fluid within ROI of diffusion tensor image (DTI). In order to define ROIs, individual b0 image was spatially aligned to the JHU DTI-based atlas using linear and non-linear registration (http://cmrm.med.jhmi.edu/). Fractional anisotropy (FA) and mean diffusivity (MD) maps were estimated by fitting diffusion tensor model to each image voxel, and their mean values were computed within each ROI with PVE threshold. Participants of this study consisted of 20 healthy controls, 27 Alzheimer's disease and 27 normal-pressure hydrocephalus patients. The result showed that the mean FA and MD of each ROI were increased and decreased respectively, but standard deviation was significantly decreased when PVE was applied. In conclusion, the proposed method suggested that PVE was indispensable to improve an accuracy of DTI ROI study.

We describe a Bayesian PET reconstruction method that incorporates anatomical information extracted from a partial volume segmentation of a co-registered magnetic resonance (MR) image. For the purposes of this paper we concentrate on imaging the brain which we assume can be partitioned into four tissue classes: gray matter, white matter, cerebral spinal fluid, and partial volume. The PET image is then modeled as a piece-wise smooth function through a Gibbs prior. Within homogeneous tissue regions the image intensity is assumed to be governed by a thin plate energy function. Rather than use the anatomical information to guide the formation of a binary process representing region boundaries, we use the segmented anatomical image as a template to customize the Gibbs energy in such a way that we apply thin-plate smoothing within homogeneous tissue regions while enforcing zeroth corder continuity as we transition from homogeneous to partial volume regions. Discontinuities in intensity are allowed only at transitions between two different homogeneous regions. We refer to this model as segmented thin-plate regression with controlled continuities. We present the results of a detailed computer simulated phantom study in which partial volume effects are explicitly modeled. Results indicate that we obtain superior region of interest quantitation using this approach in comparison to a 2D partial volume correction method that has previously been proposed for quantitation using filtered backprojection images.

The aim of this study was to present and evaluate a standardized technique for brain segmentation of cranial computed tomography (CT) using probabilistic partial volume tissue maps based on a database of high resolution T1 magnetic resonance images (MRI). Probabilistic tissue maps of white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF) were derived from 600 normal brain MRIs (3.0 Tesla, T1-3D-turbo-field-echo) of 2 large community-based population studies (BiDirect and SEARCH Health studies). After partial tissue segmentation (FAST 4.0), MR images were linearly registered to MNI-152 standard space (FLIRT 5.5) with non-linear refinement (FNIRT 1.0) to obtain non-binary probabilistic volume images for each tissue class which were subsequently used for CT segmentation. From 150 normal cerebral CT scans a customized reference image in standard space was constructed with iterative non-linear registration to MNI-152 space. The inverse warp of tissue-specific probability maps to CT space (MNI-152 to individual CT) was used to decompose a CT image into tissue specific components (GM, WM, CSF). Potential benefits and utility of this novel approach with regard to unsupervised quantification of CT images and possible visual enhancement are addressed. Illustrative examples of tissue segmentation in different pathological cases including perfusion CT are presented. Automated tissue segmentation of cranial CT images using highly refined tissue probability maps derived from high resolution MR images is feasible. Potential applications include automated quantification of WM in leukoaraiosis, CSF in hydrocephalic patients, GM in neurodegeneration and ischemia and perfusion maps with separate assessment of GM and WM.

This chapter discusses multi-fractal texture estimation and characterization of brain lesions (necrosis, edema, enhanced tumor, non-enhanced tumor, etc.) in magnetic resonance (MR) images. This work formulates the complex texture of tumor in MR images using a stochastic model known as multi-fractional Brownian motion (mBm). Mathematical derivations of the mBm model and corresponding algorithm to extract the spatially varying multi-fractal texture feature are discussed. Extracted multi-fractal texture feature is fused with other effective features to enhance the tissue characteristics. Segmentation of the tissues is performed by using a feature-based classification method. The efficacy of the mBm texture feature in segmenting different abnormal tissues is demonstrated using a large-scale publicly available clinical dataset. Experimental results and performance of the methods confirm the efficacy of the proposed technique in an automatic segmentation of abnormal tissues in multimodal (T1, T2, Flair, and T1contrast) brain MRIs.