Multispectral Magnetic Resonance Research Articles

Iterative normalization method for improved prostate cancer localization with multispectral magnetic resonance imaging

Use of multispectral magnetic resonance imaging has received a great interest for prostate cancer localization in research and clinical studies. Manual extraction of prostate tumors from multispectral magnetic resonance imaging is inefficient and subjective, while automated segmentation is objective and reproducible. For supervised, automated segmentation approaches, learning is essential to obtain the information from training dataset. However, in this procedure, all patients are assumed to have similar properties for the tumor and normal tissues, and the segmentation performance suffers since the variations across patients are ignored. To conquer this difficulty, we propose a new iterative normalization method based on relative intensity values of tumor and normal tissues to normalize multispectral magnetic resonance images and improve segmentation performance. The idea of relative intensity mimics the manual segmentation performed by human readers, who compare the contrast between regions without knowing the actual intensity values. We compare the segmentation performance of the proposed method with that of z-score normalization followed by support vector machine, local active contours, and fuzzy Markov random field. Our experimental results demonstrate that our method outperforms the three other state-of-the-art algorithms, and was found to have specificity of 0.73, sensitivity of 0.69, and accuracy of 0.79, significantly better than alternative methods.

Support vector machine for breast MR image classification

MR images have been used extensively in clinical trials in recent years because they are harmless to the human body and can obtain detailed information by scanning the same slice with various frequencies and parameters. In this paper, we want to detect the breast tissues within multi-spectral MR images. In the image classification, we apply a support vector machine (SVM) to breast multi-spectral magnetic resonance images to classify the tissues of the breast. In order to verify the feasibility and efficiency of this method, evaluations using classification rate and likelihood ratios are adopted based on manifold assessment and a series of experiments are conducted and compared with the commonly used C-means (CM) for performance evaluation. The results show that the SVM method is a promising and effective spectral technique for MR image classification.

Combined multispectral near-infrared optoacoustic tomography and magnetic resonance imaging technique to monitor brain tumor vascularization

Combined multispectral near-infrared optoacoustic tomography and magnetic resonance imaging technique to monitor brain tumor vascularization

Zonal segmentation of prostate using multispectral magnetic resonance images

To investigate the performance of a new method of automatic segmentation of prostatic multispectral magnetic resonance images into two zones: the peripheral zone and the central gland. The proposed method is based on a modified version of the evidential C-means clustering algorithm. The evidential C-means optimization process was modified to introduce spatial neighborhood information. A priori knowledge of the prostate's zonal morphology was modeled as a geometric criterion and used as an additional data source to enhance the differentiation of the two zones. Thirty-one clinical magnetic resonance imaging series were used to validate the method, and interobserver variability was taken into account in assessing its accuracy. The mean Dice Similarity Coefficient was 89% for the central gland and 80% for the peripheral zone, as validated by a consensus from expert radiologist segmentation. The method was statistically insensitive to variations in patient age, prostate volume and the presence of tumors, which increases its feasibility in a clinical context.

Study of carotid arterial plaque stress for symptomatic and asymptomatic patients

Stroke is one of the leading causes of death in the world, resulting mostly from the sudden ruptures of atherosclerosis carotid plaques. Until now, the exact plaque rupture mechanism has not been fully understood, and also the plaque rupture risk stratification. The advanced multi-spectral magnetic resonance imaging (MRI) has allowed the plaque components to be visualized in-vivo and reconstructed by computational modeling. In the study, plaque stress analysis using fully coupled fluid structure interaction was applied to 20 patients (12 symptomatic and 8 asymptomatic) reconstructed from in-vivo MRI, followed by a detailed biomechanics analysis, and morphological feature study. The locally extreme stress conditions can be found in the fibrous cap region, 85% at the plaque shoulder based on the present study cases. Local maximum stress values predicted in the plaque region were found to be significantly higher in symptomatic patients than that in asymptomatic patients (200±43 kPa vs. 127±37 kPa, p=0.001). Plaque stress level, defined by excluding 5% highest stress nodes in the fibrous cap region based on the accumulative histogram of stress experienced on the computational nodes in the fibrous cap, was also significantly higher in symptomatic patients than that in asymptomatic patients (154±32 kPa vs. 111±23 kPa, p<0.05). Although there was no significant difference in lipid core size between the two patient groups, symptomatic group normally had a larger lipid core and a significantly thinner fibrous cap based on the reconstructed plaques using 3D interpolation from stacks of 2D contours. Plaques with a higher stenosis were more likely to have extreme stress conditions upstream of plaque throat. The combined analyses of plaque MR image and plaque stress will advance our understanding of plaque rupture, and provide a useful tool on assessing plaque rupture risk.

Use of Multispectral MRI to Monitor Aneurysm Sac Contents After Endovascular Abdominal Aortic Aneurysm Repair

To validate a newly developed semi-automatic multispectral magnetic resonance imaging (MRI) tool for quantitatively monitoring aneurysm sac contents in patients after endovascular aneurysm repair (EVAR). MRI studies from 24 EVAR patients were retrospectively analyzed. The precontrast T₁-weighted and T₂-weighted and the postcontrast T₁-weighted images were displayed simultaneously. Two independent observers classified the aneurysm sac voxels into categories for endoleak, unorganized thrombus, or organized thrombus by interactively thresholding the multispectral images relative to the signal intensity of fat. Voxel classification was visualized as a color overlay on the MR images; when the observer changed the thresholds, the color overlay was updated immediately. The volumes of the voxels in each category were calculated and expressed in milliliters. The intra- and interobserver variability for measuring the volumes of endoleak and unorganized and organized thrombus were calculated; a Bland and Altman analysis was applied to determine the mean differences and the repeatability coefficient (RC). Mean aneurysm sac volume was 78 ± 42 mL. The intraobserver mean difference for the endoleak volume was 0.5 ± 1.9 mL with an RC of 3.7 mL; the interobserver mean difference was -0.8 ± 3.6 mL (RC 7.1 mL). The intraobserver mean difference for unorganized thrombus volume was -1.2 ± 4.4 mL (RC 8.6 mL); the interobserver mean difference was 0.3 ± 6.3 mL with an RC of 12.3 mL. The intraobserver mean difference for organized thrombus volume was 0.8 ± 5.0 mL (RC 9.7 mL); the interobserver mean difference was 0.4 ± 6.3 mL (RC 12.4 mL). Reproducible monitoring of aneurysm sac contents in EVAR patients is feasible with multispectral MRI in combination with our semi-automatic post-processing tool.

Automatic MR brain image segmentation using a multiseed based multiobjective clustering approach

In this paper, the automatic segmentation of a multispectral magnetic resonance image of the brain is posed as a clustering problem in the intensity space. The automatic clustering problem is thereafter modelled as solving a multiobjective optimization (MOO) problem, optimizing a set of cluster validity indices simultaneously. A multiobjective clustering technique, named MCMOClust, is used to solve this problem. MCMOClust utilizes a recently developed simulated annealing based multiobjective optimization method as the underlying optimization strategy. Each cluster is divided into several small hyperspherical subclusters and the centers of all these small sub-clusters are encoded in a string to represent the whole clustering. For assigning points to different clusters, these local sub-clusters are considered individually. For the purpose of objective function evaluation, these sub-clusters are merged appropriately to form a variable number of global clusters. Two cluster validity indices, one based on the Euclidean distance, XB-index, and another recently developed point symmetry distance based cluster validity index, Sym-index, are optimized simultaneously to automatically evolve the appropriate number of clusters present in MR brain images. A semi-supervised method is used to select a single solution from the final Pareto optimal front of MCMOClust. The present method is applied on several simulated T1-weighted, T2-weighted and proton density normal and MS lesion magnetic resonance brain images. Superiority of the present method over Fuzzy C-means, Expectation Maximization clustering algorithms and a newly developed symmetry based fuzzy genetic clustering technique (Fuzzy-VGAPS), are demonstrated quantitatively. The automatic segmentation obtained by multiseed based multiobjective clustering technique (MCMOClust) is also compared with the available ground truth information.

Automated classification of multispectral MR images using unsupervised constrained energy minimization based on fuzzy logic

Constrained energy minimization (CEM) has proven highly effective for hyperspectral (or multispectral) target detection and classification. It requires a complete knowledge of the desired target signature in images. This work presents "Unsupervised CEM (UCEM)," a novel approach to automatically target detection and classification in multispectral magnetic resonance (MR) images. The UCEM involves two processes, namely, target generation process (TGP) and CEM. The TGP is a fuzzy-set process that generates a set of potential targets from unknown information and then applies these targets to be desired targets in CEM. Finally, two sets of images, namely, computer-generated phantom images and real MR images, are used in the experiments to evaluate the effectiveness of UCEM. Experimental results demonstrate that UCEM segments a multispectral MR image much more effectively than either Functional MRI of the Brain's (FMRIB's) automated segmentation tool or fuzzy C-means does.

New multispectral MRI data fusion technique for white matter lesion segmentation: method and comparison with thresholding in FLAIR images

ObjectiveBrain tissue segmentation by conventional threshold-based techniques may have limited accuracy and repeatability in older subjects. We present a new multispectral magnetic resonance (MR) image analysis approach for segmenting normal and abnormal brain tissue, including white matter lesions (WMLs).MethodsWe modulated two 1.5T MR sequences in the red/green colour space and calculated the tissue volumes using minimum variance quantisation. We tested it on 14 subjects, mean age 73.3 ± 10 years, representing the full range of WMLs and atrophy. We compared the results of WML segmentation with those using FLAIR-derived thresholds, examined the effect of sampling location, WML amount and field inhomogeneities, and tested observer reliability and accuracy.ResultsFLAIR-derived thresholds were significantly affected by the location used to derive the threshold (P = 0.0004) and by WML volume (P = 0.0003), and had higher intra-rater variability than the multispectral technique (mean difference ± SD: 759 ± 733 versus 69 ± 326 voxels respectively). The multispectral technique misclassified 16 times fewer WMLs.ConclusionInitial testing suggests that the multispectral technique is highly reproducible and accurate with the potential to be applied to routinely collected clinical MRI data.Electronic supplementary materialThe online version of this article (doi:10.1007/s00330-010-1718-6) contains supplementary material, which is available to authorized users.

A multiobjective approach to MR brain image segmentation

This article proposes a novel multiobjective real coded genetic fuzzy clustering scheme for segmentation of multispectral magnetic resonance image (MRI) of the human brain. The proposed technique is able to automatically evolve the number of clusters along with the clustering result. The multiobjective variable string length clustering technique encodes the cluster centers in its chromosomes and simultaneously optimizes the global fuzzy compactness and fuzzy separation among the clusters. In the final generation, it produces a set of non-dominated solutions, from which the best solution in terms of a recently proposed validity index I is chosen to be the final clustering solution. The corresponding chromosome length provides the number of clusters. The proposed method is applied on many simulated T1-weighted, T2-weighted and proton density-weighted normal and MS lesion MRI brain images. Superiority of the proposed method over K-means, Fuzzy C-means, Expectation Maximization, hierarchical clustering, Single Objective Genetic clustering and other recent multiobjective clustering algorithms has been demonstrated quantitatively. The automatic segmentation obtained by the proposed clustering technique is also compared with the available ground truth information.

An improved lesion detection approach based on similarity measurement between fuzzy intensity segmentation and spatial probability maps

The application of automatic segmentation methods in lesion detection is desirable. However, such methods are restricted by intensity similarities between lesioned and healthy brain tissue. Using multi-spectral magnetic resonance imaging (MRI) modalities may overcome this problem but it is not always practicable. In this article, a lesion detection approach requiring a single MRI modality is presented, which is an improved method based on a recent publication. This new method assumes that a low similarity should be found in the regions of lesions when the likeness between an intensity based fuzzy segmentation and a location based tissue probabilities is measured. The usage of a normalized similarity measurement enables the current method to fine-tune the threshold for lesion detection, thus maximizing the possibility of reaching high detection accuracy. Importantly, an extra cleaning step is included in the current approach which removes enlarged ventricles from detected lesions. The performance investigation using simulated lesions demonstrated that not only the majority of lesions were well detected but also normal tissues were identified effectively. Tests on images acquired in stroke patients further confirmed the strength of the method in lesion detection. When compared with the previous version, the current approach showed a higher sensitivity in detecting small lesions and had less false positives around the ventricle and the edge of the brain.

Carotid arterial plaque stress analysis using fluid–structure interactive simulation based on in-vivo magnetic resonance images of four patients

The rupture of atherosclerotic plaques is known to be associated with the stresses that act on or within the arterial wall. The extreme wall tensile stress (WTS) is usually recognized as a primary trigger for the rupture of vulnerable plaque. The present study used the in-vivo high-resolution multi-spectral magnetic resonance imaging (MRI) for carotid arterial plaque morphology reconstruction. Image segmentation of different plaque components was based on the multi-spectral MRI and co-registered with different sequences for the patient. Stress analysis was performed on totally four subjects with different plaque burden by fluid–structure interaction (FSI) simulations. Wall shear stress distributions are highly related to the degree of stenosis, while the level of its magnitude is much lower than the WTS in the fibrous cap. WTS is higher in the luminal wall and lower at the outer wall, with the lowest stress at the lipid region. Local stress concentrations are well confined in the thinner fibrous cap region, and usually locating in the plaque shoulder; the introduction of relative stress variation during a cycle in the fibrous cap can be a potential indicator for plaque fatigue process in the thin fibrous cap. According to stress analysis of the four subjects, a risk assessment in terms of mechanical factors could be made, which may be helpful in clinical practice. However, more subjects with patient specific analysis are desirable for plaque-stability study.

Design and fabrication of a micromachined multispectral magnetic resonance imaging agent

This paper describes the fabrication details of magnetic nano- and microstructures that enable a new class of multispectral magnetic resonance imaging agents. Magnetic field and associated geometrical fabrication constraints particular to these new multispectral contrast agents are described, and fabrication schemes based on both electrochemical deposition and thermal evaporation are presented. Relative advantages and disadvantages of top-down microfabrication approaches versus traditional bottom-up chemical synthesis routes are discussed with a focus on trade-offs between resulting microparticle functionality and fabrication process economy. It is shown that large numbers of contrast agent nano- or microstructures can be simultaneously fabricated, suggesting that top-down microfabricated contrast agents may represent an economical, attractive alternative to those based on chemically synthesized molecules or nanoparticles.

MR Brain Image Segmentation Using A Multi-seed Based Automatic Clustering Technique

In this paper, the automatic segmentation of multispectral magnetic resonance image of the brain is posed as a clustering problem in the intensity space. Thereafter an automatic clustering techniqu...

MR Brain Image Segmentation Using A Multi-seed Based Automatic Clustering Technique

In this paper, the automatic segmentation of multispectral magnetic resonance image of the brain is posed as a clustering problem in the intensity space. Thereafter an automatic clustering technique is proposed to solve this problem. The proposed real-coded variable string length genetic clustering technique (MCVGAPS clustering) is able to evolve the number of clusters present in the data set automatically. Each cluster is divided into several small hyperspherical subclusters and the centers of all these small sub-clusters are encoded in a string to represent the whole clustering. For assigning points to different clusters, these local sub-clusters are considered individually. For the purpose of objective function evaluation, these sub-clusters are merged appropriately to form a variable number of global clusters. A recently developed point symmetry distance based cluster validity index, Sym-index, is optimized to automatically evolve the appropriate number of clusters present in an MR brain image. The proposed method is applied on several simulated T1-weighted, T2- weighted and proton density normal and MS lesion magnetic resonance brain images. Superiority of the proposed method over Fuzzy C-means, Expectation Maximization clustering algorithms are demonstrated quantitatively. The automatic segmentation obtained by multiseed based multiobjective clustering technique (MCVGAPS) is also compared with the available ground truth information.

Basic helix–loop–helix transcription factor NEUROG1 and schizophrenia: Effects on illness susceptibility, MRI brain morphometry and cognitive abilities

Transcription factors, including the basic helix–loop–helix (bHLH) family, regulate numerous genes and play vital roles in controlling gene expression. Consequently, transcription factor mutations can lead to phenotypic pleiotropy, and may be a candidate mechanism underlying the complex genetics and heterogeneous phenotype of schizophrenia. Neurogenin1 ( NEUROG1; a.k.a. Ngn1 or Neurod3), a bHLH transcription factor encoded on a known schizophrenia linkage region in 5q31.1, induces glutamatergic and suppresses GABAergic neuronal differentiation during embryonic neurodevelopment. The goal of this study is to investigate NEUROG1 effects on schizophrenia risk and on phenotypic features of schizophrenia. We tested 392 patients with schizophrenia or schizoaffective disorder and 226 healthy normal volunteers for association with NEUROG1. Major alleles on two NEUROG1-associated SNPs (rs2344484-C-allele and rs8192558-G-allele) were significantly more prevalent among patients ( p ≤ .0018). Approximately 80% of the sample also underwent high-resolution, multi-spectral magnetic resonance brain imaging and standardized neuropsychological assessment. There were significant rs2344484 genotype main effects on total cerebral gray matter (GM) and temporal GM volumes ( p ≤ .05). C-allele-carrier patients and healthy volunteers had smaller total cerebral GM and temporal GM volumes than their respective T-homozygous counterparts. rs2344484-C-allele was further associated with generalized cognitive deficits among schizophrenia patients but not in healthy volunteers. Our findings replicate previous association between NEUROG1 and schizophrenia. More importantly, this is the first study to examine brain morphological and neurocognitive correlates of NEUROG1. rs2344484-C-allele may affect NEUROG1's role in transcription regulation such that brain morphology and cognitive abilities are altered resulting in increased susceptibility to develop schizophrenia.

Multiple Sclerosis Detection in Multispectral Magnetic Resonance Images with Principal Components Analysis.

This paper presents a local feature vector based method for automated Multiple Sclerosis (MS) lesion segmentation of multi spectral MRI data. Twenty datasets from MS patients with FLAIR, T1,T2, MD and FA data with expert annotations are available as training set from the MICCAI 2008 challenge on MS, and 24 test datasets. Our local feature vector method contains neighbourhood voxel intensities, histogram and MS probability atlas information. Principal Component Analysis(PCA) with log-likelihood ratio is used to classify each voxel. MRI suffers from intensity inhomogenities. We try to correct this ‘’bias field’’ with 3 methods: a genetic algorithm, edge preserving filtering and atlas based correction. A large observer variability exist between expert classifications, but the similarity scores between model and expert classifications are often lower. Our model gives the best classification results with raw data, because bias correction gives artifacts at the edges and flatten large MS lesions.

Generalized fuzzy clustering for segmentation of multi-spectral magnetic resonance images

An integrated approach for multi-spectral segmentation of MR images is presented. This method is based on the fuzzy c-means (FCM) and includes bias field correction and contextual constraints over spatial intensity distribution and accounts for the non-spherical cluster's shape in the feature space. The bias field is modeled as a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of intensity are added into the FCM cost functions. To reduce the computational complexity, the contextual regularizations are separated from the clustering iterations. Since the feature space is not isotropic, distance measure adopted in Gustafson–Kessel (G–K) algorithm is used instead of the Euclidean distance, to account for the non-spherical shape of the clusters in the feature space. These algorithms are quantitatively evaluated on MR brain images using the similarity measures.

Technical aspects and evaluation methodology for the application of two automated brain MRI tumor segmentation methods in radiation therapy planning

The purpose of this study was to design the steps necessary to create a tumor volume outline from the results of two automated multispectral magnetic resonance imaging segmentation methods and integrate these contours into radiation therapy treatment planning. Algorithms were developed to create a closed, smooth contour that encompassed the tumor pixels resulting from two automated segmentation methods: k-nearest neighbors and knowledge guided. These included an automatic three-dimensional (3D) expansion of the results to compensate for their undersegmentation and match the extended contouring technique used in practice by radiation oncologists. Each resulting radiation treatment plan generated from the automated segmentation and from the outlining by two radiation oncologists for 11 brain tumor patients was compared against the volume and treatment plan from an expert radiation oncologist who served as the control. As part of this analysis, a quantitative and qualitative evaluation mechanism was developed to aid in this comparison. It was found that the expert physician reference volume was irradiated within the same level of conformity when using the plans generated from the contours of the segmentation methods. In addition, any uncertainty in the identification of the actual gross tumor volume by the segmentation methods, as identified by previous research into this area, had small effects when used to generate 3D radiation therapy treatment planning due to the averaging process in the generation of margins used in defining a planning target volume.

A framework of fuzzy information fusion for the segmentation of brain tumor tissues on MR images

A framework of fuzzy information fusion is proposed in this paper to automatically segment tumor areas of human brain from multispectral magnetic resonance imaging (MRI) such as T1-weighted, T2-weighted and proton density (PD) images. A priori knowledge about tumors described by radiology experts for different types of MRI are very helpful to guide a automatic and a precise segmentation. However, the terminology used by radiology experts are variable in term of image signal. In order to benefit of these descriptions, we propose to modellize them by fuzzy models. One fuzzy model is built for one type of MRI sequence. The segmentation is finally based on a fusion of different fuzzy information obtained from different types of MRI images. Our algorithm consists of four stages: the registration of multispectral MR images, the creation of fuzzy models describing the characteristics of tumor, the fusion based on fuzzy fusion operators and the adjustment by fuzzy region growing based on fuzzy connecting. The comparison between the obtained results and the hand-tracings of a radiology expert shows that the proposed algorithm is efficient. An average probability of correct detection 96% and an average probability of false detection 5% are obtained through studies of four patients.