Multispectral Magnetic Resonance Imaging Research Articles

Shaped Magnetogel Microparticles for Multispectral Magnetic Resonance Contrast and Sensing.

Multispectral magnetic resonance imaging (MRI) contrast agents are microfabricated three-dimensional magnetic structures that encode nearby water protons with discrete frequencies. The agents have a unique radiofrequency (RF) resonance that can be tuned by engineering the geometric parameters of these microstructures. Multispectral contrast agents can be used as sensors by incorporating a stimulus-driven shape-changing response into their structure. These geometrically encoded magnetic sensors (GEMS) enable MRI-based sensing via environmentally induced changes to their geometry and their corresponding RF resonance. Previously, GEMS have been made using thin-film lithography techniques in a cleanroom environment. While these approaches offer precise control of the microstructure, they can be a limitation for researchers who do not have cleanroom access or microfabrication expertise. Here, an alternative approach for GEMS fabrication based on soft lithography is introduced. The fabrication scheme uses cheap, accessible materials and simple chemistry to produce shaped magnetic hydrogel microparticles with multispectral MRI contrast properties. The microparticles can be used as sensors by fabricating them out of shape-reconfigurable, "smart" hydrogels. The change in shape causes a corresponding shift in the resonance of the GEMS, producing an MRI-addressable readout of the microenvironment. Proof-of-principle experiments showing a multispectral response to pH change with cylindrical shell-shaped magnetogel GEMS are presented.

Multiacquisition Variable-Resonance Image Combination Magnetic Resonance Imaging to Study Detailed Bone Apposition and Fixation of Cementless Knee System Compared to Cemented Total Knee Replacements

BackgroundThe ability to utilize magnetic resonance imaging (MRI) to assess bony fixation may allow a better understanding of implant design and longevity. A new cementless total knee arthroplasty (TKA) was introduced, and we hypothesized that this cementless system would show similar fixation compared to a cemented system as assessed by multispectral MRI. MethodsMultiacquisition variable-resonance image combination selective MRI was performed in 20 patients implanted with a cementless TKA. A matched control group of 20 patients who had a cemented TKA was also evaluated. Each patellar, femoral, and tibial component was graded globally as well as by specific zones. The patella zones were medial, lateral, superior, and inferior. The femoral and tibial components were divided into 4 zones: anteromedial, anterolateral, posteromedial, and posterolateral. Integration grades were performed for each zone as follows: (1) normal, (2) fibrous tissue, (3) fluid interface, (4) osteolysis. A Chi-square test was performed to detect differences in level of integration grades between patients with cemented and those with cementless TKA. ResultsAt average 16-month follow-up, the cementless group grading noted 0/80 (0%) vs 2/76 (2.63%) patellar zones with fluid interface, 0/80 (0%) vs 26/80 (32.5%) femoral zones with fibrous tissue, and 10/80 (12.5%) vs 17/80 (21.25%) tibial zones with fibrous tissue. The analysis showed patellar (P < .001), femoral (P < .001), and tibial (P < .001) components had improved fixation and less percentage of fibrous tissue and fluid present in the cementless TKA. ConclusionsUtilizing metal suppression MRI, a newer cementless knee implant demonstrated excellent biologic fixation and improved fixation compared to the cemented group.

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

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

Delineation of ischemic lesion from brain MRI using attention gated fully convolutional network.

Precise delineation of the ischemic lesion from unimodal Magnetic Resonance Imaging (MRI) is a challenging task due to the subtle intensity difference between the lesion and normal tissues. Hence, multispectral MRI modalities are used for characterizing the properties of brain tissues. Traditional lesion detection methods rely on extracting significant hand-engineered features to differentiate normal and abnormal brain tissues. But the identification of those discriminating features is quite complex, as the degree of differentiation varies according to each modality. This can be addressed well by Convolutional Neural Networks (CNN) which supports automatic feature extraction. It is capable of learning the global features from images effectively for image classification. But it loses the context of local information among the pixels that need to be retained for segmentation. Also, it must provide more emphasis on the features of the lesion region for precise reconstruction. The major contribution of this work is the integration of attention mechanism with a Fully Convolutional Network (FCN) to segment ischemic lesion. This attention model is applied to learn and concentrate only on salient features of the lesion region by suppressing the details of other regions. Hence the proposed FCN with attention mechanism was able to segment ischemic lesion of varying size and shape. To study the effectiveness of attention mechanism, various experiments were carried out on ISLES 2015 dataset and a mean dice coefficient of 0.7535 was obtained. Experimental results indicate that there is an improvement of 5% compared to the existing works.

Multiacquisition Variable-Resonance Image Combination Magnetic Resonance Imaging Used to Study Detailed Bone Apposition and Fixation of an Additively Manufactured Cementless Acetabular Shell

BackgroundThe ability to utilize magnetic resonance imaging (MRI) to assess bony fixation in 3 dimensions may allow a better understanding of the implant design and bony integration. We hypothesized that a new 3-dimensionally printed cementless highly porous acetabular component (Stryker Trident II TritaniumTM) would show better fixation than an earlier cup from the same manufacturer as assessed by the noninvasive technique of multispectral MRI. MethodsMultiacquisition variable-resonance image combination selective metal suppression MRI was performed in 19 patients implanted with a new 3-dimensionally printed cup and 20 patients who had received a previous-generation cup from the same manufacturer at 1-year follow-up. Each cup was graded globally as well as by 9 specific zones. Integration grades were performed for each zone: 0, full bone integration; 1, fibrous membrane present; 2, osteolysis; and 3, fluid present. A mixed-effects logistic regression model was used to compare fixation between the 2 groups. ResultsAll cups in both cohorts showed greater than 90% radiographically estimated global bony integration (3-dimensionally printed cups, 99.4%; regular cups 91.6%) with no osteolysis or fluid observed in any cup. The 3-dimensionally printed cup had 1 of 171 zones (0.6%) graded as fibrous membrane present, while the 2-dimensional group had 15 of 180 zones (8.3%) graded as fibrous. Of note, screw hole regions were omitted but may be read as fibrous membrane areas. ConclusionUsing multiacquisition variable-resonance image combination selective MRI, our analysis showed greater biologic fixation and less fibrous membrane formation in the 3-dimensionally printed cups than the control group at 1-year follow-up.

Automatic Segmentation of Meniscus in Multispectral MRI Using Regions with Convolutional Neural Network (R-CNN).

The meniscus has a significant function in human anatomy, and Magnetic Resonance Imaging (MRI) has an essential role in meniscus examination. Due to a variety of MRI data, it is excessively difficult to segment the meniscus with image processing methods. An MRI data sequence contains multiple images, and the region features we are looking for may vary from each image in the sequence. Therefore, feature extraction becomes more difficult, and hence, explicitly programming for segmentation becomes more difficult. Convolutional Neural Network (CNN) extracts features directly from images and thus eliminates the need for manual feature extraction. Regions with Convolutional Neural Network (R-CNN) allow us to use CNN features in object detection problems by combining CNN features with Region Proposals. In this study, we designed and trained an R-CNN for detecting meniscus region in MRI data sequence. We used transfer learning for training R-CNN with a small amount of meniscus data. After detection of the meniscus region by R-CNN, we segmented meniscus by morphological image analysis using two different MRI sequences. Automatic detection of the meniscus region with R-CNN made the meniscus segmentation process easier, and the use of different contrast features of two different image sequences allowed us to differentiate the meniscus from its surroundings.

Deep learning segmentation of gadolinium-enhancing lesions in multiple sclerosis

Objective: The aim of this study is to assess the performance of deep learning convolutional neural networks (CNNs) in segmenting gadolinium-enhancing lesions using a large cohort of multiple sclerosis (MS) patients. Methods: A three-dimensional (3D) CNN model was trained for segmentation of gadolinium-enhancing lesions using multispectral magnetic resonance imaging data (MRI) from 1006 relapsing–remitting MS patients. The network performance was evaluated for three combinations of multispectral MRI used as input: (U5) fluid-attenuated inversion recovery (FLAIR), T2-weighted, proton density-weighted, and pre- and post-contrast T1-weighted images; (U2) pre- and post-contrast T1-weighted images; and (U1) only post-contrast T1-weighted images. Segmentation performance was evaluated using the Dice similarity coefficient (DSC) and lesion-wise true-positive (TPR) and false-positive (FPR) rates. Performance was also evaluated as a function of enhancing lesion volume. Results: The DSC/TPR/FPR values averaged over all the enhancing lesion sizes were 0.77/0.90/0.23 using the U5 model. These values for the largest enhancement volumes (>500 mm3) were 0.81/0.97/0.04. For U2, the average DSC/TPR/FPR values were 0.72/0.86/0.31. Comparable performance was observed with U1. For all types of input, the network performance degraded with decreased enhancement size. Conclusion: Excellent segmentation of enhancing lesions was observed for enhancement volume ⩾70 mm3. The best performance was achieved when the input included all five multispectral image sets.

Multivariate use of MRI biomarkers to classify histologically confirmed necrosis in symptomatic total hip arthroplasty.

The failure of total hip arthroplasty (THA) is commonly associated with the necrosis of the periprosthetic tissue. To date, there is no established method to noninvasively quantify the progression of such necrosis. Magnetic resonance imaging (MRI) of soft tissues near implants has undergone a recent renaissance due to the development of multispectral metal-artifact reduction techniques. Advanced analysis of multispectral MRI has been shown capable of detecting small magnetism effects of metallic debris in periprosthetic tissue. The purpose of this study is to demonstrate the diagnostic utility of these MRI-based tissue-magnetism signatures. Together with morphological MRI metrics, such as synovial volume and thickness, these measurements are utilized as biomarkers to noninvasively detect soft-tissue necrosis in symptomatic THA patients ( ). All subjects underwent an advanced MRI scan before revision surgery and tissue biopsies utilized for necrosis grading. Statistical analyses demonstrated a weak, but significant positive correlation (P = .04) between MRI magnetism signatures and necrosis scores, while indicating no meaningful association between the latter and serum cobalt and chromium ion levels. Receiver-operating characteristic (ROC) analyses were then performed based on uni- and multivariate logistic regression models utilizing the measured MRI biomarkers as predictors of severe necrosis. The area under the curve of the ROC plots for MRI biomarkers as combined predictors were found to be 0.70 and 0.84 for cross-validation and precision-recall tests, respectively.

Evaluation of Therapeutic Response in Spinal Muscular Atrophy Using Multispectral Optoacoustic Tomography (MSOT) and Magnetic Resonance Imaging (MRI)

Evaluation of Therapeutic Response in Spinal Muscular Atrophy Using Multispectral Optoacoustic Tomography (MSOT) and Magnetic Resonance Imaging (MRI)

Carotid Bifurcation With Tandem Stenosis-A Patient-Specific Case Study Combined in vivo Imaging, in vitro Histology and in silico Simulation.

A patient-specific carotid bifurcation with tandem stenosis found at both internal carotid artery (ICA) and common carotid artery (CCA) was studied. The in vivo pre-carotid endarterectomy (pre-CEA) multi-spectral magnetic resonance imaging (MRI) were performed and in vitro post-CEA carotid plaque tissue sample was collected. MR imaging data and tissue sample staining histology were used to recognize the plaque components. Further, the computational fluid dynamics (CFD) were performed on four MR-based reconstructed 3D carotid bifurcation models (the patient-specific geometry with tandem stenosis and three presumptive geometries by removing the stenosis part). The flow and shear stress behavior affected by the tandem stenosis was analyzed. From the results of MR segmentation and histology analysis, plaque lipid pool and calcification were found at both ICA and CCA. From the result of CFD simulation, the flow shear stress behavior suggested the tandem stenosis as a more “dangerous” situation than a single-stenosis artery. Besides, the CFD results deduced that the stenosis at the CCA location formed initially and led to the subsequent formation of stenosis at ICA. This study suggests that when planning CEA, CFD simulation on the presumptive models could help clinicians to estimate the blood flow behavior after surgery. Particular attention should be paid to the case of tandem stenosis, as the local hemodynamic environment is more complex and treatment of one stenosis may lead to a variation in the hemodynamic loading on the second plaque, which may result in either a higher risk of plaque rupture or restenosis.

A simple and fast adaptive nonlocal multispectral filtering algorithm for efficient noise reduction in magnetic resonance imaging

PurposeWe recently introduced a multispectral (MS) nonlocal (NL) filter based on maximum likelihood estimation (MLE) of voxel intensities, termed MS-NLML. While MS-NLML provides excellent noise reduction and improved image feature preservation as compared to other NL or MS filters, it requires considerable processing time, limiting its application in routine analyses. In this work, we introduced a fast, simple, and robust filter, termed nonlocal estimation of multispectral magnitudes (NESMA), for noise reduction in multispectral (MS) magnetic resonance imaging (MRI). MethodsThrough extensive simulation and in-vivo analyses, we compared the performance of NESMA and MS-NLML in terms of noise reduction and processing efficiency. Further, we introduce two simple adaptive methods that permit spatial variation of similar voxels, R, used in the filtering. The first method is semi-adaptive and permits variation of R across the image by using a relative Euclidean distance (RED) similarity threshold. The second method is fully adaptive and filters the raw data with several RED similarity thresholds to spatially determine the optimal threshold value using an unbiased criterion. ResultsNESMA shows very similar filtering performance as compared to MS-NLML, however, with much simple implementation and very fast processing time. Further, for both filters, the adaptive methods were shown to further reduce noise in comparison with the conventional non-adaptive method in which R is set to a constant value throughout the image. ConclusionsNESMA is fast, robust, and straightforward to implement filter. These features render it suitable for routine clinical use and analysis of large MRI datasets.

Ischemic stroke lesion segmentation using stacked sparse autoencoder

Automatic segmentation of ischemic stroke lesion volumes from multi-spectral Magnetic Resonance Imaging (MRI) sequences plays a vital role in quantifying and locating the lesion region. Most existing methods mainly rely on designing hand-crafted features followed by a classifier model for ischemic stroke lesion segmentation. Design of these features requires complex domain knowledge and often lacks the ability to differentiate between the stroke lesions and the normal classes. In this work, we propose an unsupervised featured learning approach based on stacked sparse autoencoder (SSAE) framework for automatically learning the features for accurate segmentation of stroke lesions from brain MR images. A deep architecture is designed using sparse autoencoder (SAE) layers, followed by support vector machine (SVM) classifier for classifying the patches into normal or lesions. We validated our approach on a publicly available Ischemic Stroke Lesion Segmentation (ISLES) 2015 dataset, with a mean precision of 0.968, mean dice coefficient (DC) of 0.943, mean recall of 0.924 and mean accuracy of 0.904. The experimental results show that our proposed approach significantly outperforms the state-of-the-art methods in terms of precision, DC, and recall. Quantitative evaluation was carried out and compared with the existing approaches, which demonstrates that the proposed method is 25.71%, 36.67%, and 16.96% higher in terms of precision, DC and recall values, respectively. The unsupervised features learned via SSAE framework performs better than the hand-crafted features and can be easily trained on large datasets.

Towards Clinical Diagnosis: Automated Stroke Lesion Segmentation on Multi-Spectral MR Image Using Convolutional Neural Network

The patient with ischemic stroke can benefit most from the earliest possible definitive diagnosis. While a quantitative evaluation of the stroke lesions on the magnetic resonance images (MRIs) is effective in clinical diagnosis, manually segmenting the stroke lesions is commonly used, which is, however, a tedious and time-consuming task. Therefore, how to segment the stroke lesions in a fully automated manner has recently extracted extensive attentions. Considering that the clinically acquired MRIs usually have thick slices, we propose a 2D-slice-based segmentation method. In particular, we use multi-spectral MRIs, i.e., diffusion weighted image, apparent diffusion coefficient, and T2-weighted image, as input, and propose a residual-structured fully convolutional network (Res-FCN). The proposed Res-FCN is trained and evaluated on a large data set with 212 clinically acquired MRIs, which achieves a mean dice coefficient of 0.645 with a mean number of false negative lesions of 1.515 per subject. The proposed Res-FCN is further evaluated on a public data set, i.e., ISLES2015-SISS, which presents a very competitive result among all 2D-slice-based segmentation methods.

NeXt for neuro‐radiosurgery: A fully automatic approach for necrosis extraction in brain tumor MRI using an unsupervised machine learning technique

AbstractStereotactic neuro‐radiosurgery is a well‐established therapy for intracranial diseases, especially brain metastases and highly invasive cancers that are difficult to treat with conventional surgery or radiotherapy. Nowadays, magnetic resonance imaging (MRI) is the most used modality in radiation therapy for soft‐tissue anatomical districts, allowing for an accurate gross tumor volume (GTV) segmentation. Investigating also necrotic material within the whole tumor has significant clinical value in treatment planning and cancer progression assessment. These pathological necrotic regions are generally characterized by hypoxia, which is implicated in several aspects of tumor development and growth. Therefore, particular attention must be deserved to these hypoxic areas that could lead to recurrent cancers and resistance to therapeutic damage. This article proposes a novel fully automatic method for necrosis extraction (NeXt), using the Fuzzy C‐Means algorithm, after the GTV segmentation. This unsupervised Machine Learning technique detects and delineates the necrotic regions also in heterogeneous cancers. The overall processing pipeline is an integrated two‐stage segmentation approach useful to support neuro‐radiosurgery.NeXtcan be exploited for dose escalation, allowing for a more selective strategy to increase radiation dose in hypoxic radioresistant areas. Moreover,NeXtanalyzes contrast‐enhanced T1‐weighted MR images alone and does not require multispectral MRI data, representing a clinically feasible solution. This study considers an MRI dataset composed of 32 brain metastatic cancers, wherein 20 tumors present necroses. The segmentation accuracy ofNeXtwas evaluated using both spatial overlap‐based and distance‐based metrics, achieving these average values: Dice similarity coefficient 95.93% ± 4.23% and mean absolute distance 0.225 ± 0.229 (pixels).

Automated Prostate Gland Segmentation Based on an Unsupervised Fuzzy C-Means Clustering Technique Using Multispectral T1w and T2w MR Imaging

Prostate imaging analysis is difficult in diagnosis, therapy, and staging of prostate cancer. In clinical practice, Magnetic Resonance Imaging (MRI) is increasingly used thanks to its morphologic and functional capabilities. However, manual detection and delineation of prostate gland on multispectral MRI data is currently a time-expensive and operator-dependent procedure. Efficient computer-assisted segmentation approaches are not yet able to address these issues, but rather have the potential to do so. In this paper, a novel automatic prostate MR image segmentation method based on the Fuzzy C-Means (FCM) clustering algorithm, which enables multispectral T1-weighted (T1w) and T2-weighted (T2w) MRI anatomical data processing, is proposed. This approach, using an unsupervised Machine Learning technique, helps to segment the prostate gland effectively. A total of 21 patients with suspicion of prostate cancer were enrolled in this study. Volume-based metrics, spatial overlap-based metrics and spatial distance-based metrics were used to quantitatively evaluate the accuracy of the obtained segmentation results with respect to the gold-standard boundaries delineated manually by an expert radiologist. The proposed multispectral segmentation method was compared with the same processing pipeline applied on either T2w or T1w MR images alone. The multispectral approach considerably outperforms the monoparametric ones, achieving an average Dice Similarity Coefficient 90.77 ± 1.75, with respect to 81.90 ± 6.49 and 82.55 ± 4.93 by processing T2w and T1w imaging alone, respectively. Combining T2w and T1w MR image structural information significantly enhances prostate gland segmentation by exploiting the uniform gray appearance of the prostate on T1w MRI.

Adopting Quaternion Wavelet Transform to Fuse Multi-Modal Medical Images

Medical image fusion plays an important role in clinical applications such as image-guided surgery, image-guided radiotherapy, noninvasive diagnosis, and treatment planning. In this paper, we propose a novel multi-modal medical image fusion method based on simplified pulse-coupled neural network and quaternion wavelet transform. The proposed fusion algorithm is capable of combining not only pairs of computed tomography (CT) and magnetic resonance (MR) images, but also pairs of CT and proton-density-weighted MR images, and multi-spectral MR images such as T1 and T2. Experiments on six pairs of multi-modal medical images are conducted to compare the proposed scheme with four existing methods. The performances of various methods are investigated using mutual information metrics and comprehensive fusion performance characterization (total fusion performance, fusion loss, and modified fusion artifacts criteria). The experimental results show that the proposed algorithm not only extracts more important visual information from source images, but also effectively avoids introducing artificial information into fused medical images. It significantly outperforms existing medical image fusion methods in terms of subjective performance and objective evaluation metrics.

Multiobjective fuzzy clustering with coalition formation: the case of brain image processing

ABSTRACTThis paper presents a multi-objective fuzzy clustering approach under iterative modelling for the segmentation of human brain multispectral magnetic resonance image. It optimizes the global spatial fuzzy compactness and fuzzy spatial separation among clusters. Our method generates an ensemble of Pareto solutions among which the final solution will be proposed to the analyst. At this final step, the Shapley value concept is utilized to select the best solution. An empirical study on brain images shows a better performance of our proposed method when compared to competing algorithms.

Multispectral MRI Image Fusion for Enhanced Visualization of Meningioma Brain Tumors and Edema Using Contourlet Transform and Fuzzy Statistics

This paper proposes a multispectral magnetic resonance imaging (MRI) image fusion scheme for improved visualization of anatomical and pathological information of meningioma (MG) brain tumors that combines the contourlet transform and fuzzy statistics. The proposed fusion technique mainly targets the tumor and its surrounding hyperintense (edema) region, which leads to improved brain imaging informatics for radiologists. The developed methodology mainly consists of the contourlet transform for multiscale and directional decomposition, fuzzy entropy for fusing approximation coefficients, and region-based fuzzy energy for fusing detailed coefficients of two input images with the same orientations. Two fusion rules are established here in order to fuse corresponding lower- and higher-frequency subbands of images. The proposed methodology is applied to five various combinations (such as T1-weighted and T2-weighted, T1 post-contrast and T2-weighted etc.) generated from four modalities of MRI images (T1-weighted, T1 post-contrast, T2-weighted, and fluid-attenuated inversion recovery (FLAIR)). A total of 150 MRI images (30 images from each of five combinations) are considered from 20 cases of MG brain tumors. A quantitative evaluation of the proposed method is performed in terms of three performance measures. The performance is compared with that of existing medical image fusion techniques tested on the same dataset. Experimental results show the superiority of the proposed methodology in terms of both qualitative and quantitative measures, which also indicates that fused images contain enriched diagnostic information that can aid the detection of tumors and edema. A fusion of post-contrast T1-weighted MRI images with FLAIR and T2-weighted MRI images provided clinically relevant information.

Heterogeneous Optimization Framework: Reproducible Preprocessing of Multi-Spectral Clinical MRI for Neuro-Oncology Imaging Research.

Neuroimaging research often relies on clinically acquired magnetic resonance imaging (MRI) datasets that can originate from multiple institutions. Such datasets are characterized by high heterogeneity of modalities and variability of sequence parameters. This heterogeneity complicates the automation of image processing tasks such as spatial co-registration and physiological or functional image analysis. Given this heterogeneity, conventional processing workflows developed for research purposes are not optimal for clinical data. In this work, we describe an approach called Heterogeneous Optimization Framework (HOF) for developing image analysis pipelines that can handle the high degree of clinical data non-uniformity. HOF provides a set of guidelines for configuration, algorithm development, deployment, interpretation of results and quality control for such pipelines. At each step, we illustrate the HOF approach using the implementation of an automated pipeline for Multimodal Glioma Analysis (MGA) as an example. The MGA pipeline computes tissue diffusion characteristics of diffusion tensor imaging (DTI) acquisitions, hemodynamic characteristics using a perfusion model of susceptibility contrast (DSC) MRI, and spatial cross-modal co-registration of available anatomical, physiological and derived patient images. Developing MGA within HOF enabled the processing of neuro-oncology MR imaging studies to be fully automated. MGA has been successfully used to analyze over 160 clinical tumor studies to date within several research projects. Introduction of the MGA pipeline improved image processing throughput and, most importantly, effectively produced co-registered datasets that were suitable for advanced analysis despite high heterogeneity in acquisition protocols.

Simultaneous vector-valued image segmentation and intensity nonuniformity correction using variational level set combined with Markov random field modeling

Object quantification requires an image segmentation to make measurements about size, material composition and morphology of the object. In vector-valued or multispectral images, each image channel has its signal characteristics and provides special information that may improve the results of image segmentation method. This paper presents a region-based active contour model for vector-valued image segmentation with a variational level set formulation. In this model, the local image intensities are characterized using Gaussian distributions with different means and variances. Furthermore, by utilizing Markov random field, the spatial correlation between neighboring pixels and voxels is modeled. With incorporation of intensity nonuniformity model, our method is able to deal with brain tissue segmentation from multispectral magnetic resonance (MR) images. Our experiments on synthetic images and multispectral cerebral MR images with different noise and bias level show the advantages of the proposed method.