Multispectral analysis of magnetic resonance images

Tumor habitat and peritumoral region evolution-based imaging features to assess risk categorization of thymomas

AIM

To develop an aggregate model that integrated clinical data, habitat characteristics, and intratumoral and peritumoral features to assess the risk categorization of thymomas.

MATERIALS AND METHODS

We retrospectively analyzed 140 thymoma patients (70 low-risk and 70 high-risk), including pathological data. The patients were randomly divided into training cohort (n = 114) and test cohort (n = 26). The k-means clustering was utilized to partition the primary tumor into habitats based on intratumoral radiomic features, 6 distinct habitats were identified. By expanding the region of interest (ROI) mask, 2 peritumoral regions were obtained. Finally, 7 clinical characteristics, 3 habitat values, 20 radiomic features were utilized to develop an aggregated model, to predict the risk of thymoma. Shapley additive explanations (SHAP) interpretation was used for features importance ranking. The accuracy and area under curve (AUC) were used to analyze the performance of the models.

RESULTS

The aggregated model, which utilized the XGBoost classifier, demonstrated the best performance with an AUC of 0.811 and an accuracy of 0.769. In comparison, the radiomic model produced an AUC of 0.654 and an accuracy of 0.692. Additionally, the Intratumoral + peritumoral model exhibited an AUC of 0.728 and an accuracy of 0.769.

CONCLUSION

Our study establishes a novel tool to predict the risk of thymoma with a good performance. If prospectively validated, the model may refine thymoma patient selection for risk-adaptative therapy and improve prognosis.

Bayesian Depth-Wise Convolutional Neural Network Design for Brain Tumor MRI Classification

In recent years, deep learning has been applied to many medical imaging fields, including medical image processing, bioinformatics, medical image classification, segmentation, and prediction tasks. Computer-aided detection systems have been widely adopted in brain tumor classification, prediction, detection, diagnosis, and segmentation tasks. This work proposes a novel model that combines the Bayesian algorithm with depth-wise separable convolutions for accurate classification and predictions of brain tumors. We combine Bayesian modeling learning and Convolutional Neural Network learning methods for accurate prediction results to provide the radiologists the means to classify the Magnetic Resonance Imaging (MRI) images rapidly. After thorough experimental analysis, our proposed model outperforms other state-of-the-art models in terms of validation accuracy, training accuracy, F1-score, recall, and precision. Our model obtained high performances of 99.03% training accuracy and 94.32% validation accuracy, F1-score, precision, and recall values of 0.94, 0.95, and 0.94, respectively. To the best of our knowledge, the proposed work is the first neural network model that combines the hybrid effect of depth-wise separable convolutions with the Bayesian algorithm using encoders.

Joint total variation-based reconstruction of multiparametric magnetic resonance images for mapping tissue types

Multispectral analysis of coregistered multiparametric magnetic resonance (MR) images provides a powerful method for tissue phenotyping and segmentation. Acquisition of a sufficiently varied set of multicontrast MR images and parameter maps to objectively define multiple normal and pathologic tissue types can require long scan times. Accelerated MRI on clinical scanners with multichannel receivers exploits techniques such as parallel imaging, while accelerated preclinical MRI scanning must rely on alternate approaches. In this work, tumor-bearing mice were imaged at 7 T to acquire k-space data corresponding to a series of images with varying T1-, T2- and T2*-weighting. A joint reconstruction framework is proposed to reconstruct a series of T1-weighted images and corresponding T1 maps simultaneously from undersampled Cartesian k-space data. The ambiguity introduced by undersampling was resolved by using model-based constraints and structural information from a reference fully sampled image as the joint total variation prior. This process was repeated to reconstruct T2-weighted and T2*-weighted images and corresponding maps of T2 and T2* from undersampled Cartesian k-space data. Validation of the reconstructed images and parameter maps was carried out by computing tissue-type maps, as well as maps of the proton density fat fraction (PDFF), proton density water fraction (PDwF), fat relaxation rate ( R 2 f * ) and water relaxation rate ( R 2 w * ) from the reconstructed data, and comparing them with ground truth (GT) equivalents. Tissue-type maps computed using 18% k-space data were visually similar to GT tissue-type maps, with dice coefficients ranging from 0.43 to 0.73 for tumor, fluid adipose and muscle tissue types. The mean T1 and T2 values within each tissue type computed using only 18% k-space data were within 8%-10% of the GT values from fully sampled data. The PDFF and PDwF maps computed using 27% k-space data were within 3%-15% of GT values and showed good agreement with the expected values for the four tissue types.

Tumor habitat analysis by magnetic resonance imaging distinguishes tumor progression from radiation necrosis in brain metastases after stereotactic radiosurgery

OBJECTIVES

The identification of viable tumor after stereotactic radiosurgery (SRS) is important for future targeted therapy. This study aimed to determine whether tumor habitat on structural and physiologic MRI can distinguish viable tumor from radiation necrosis of brain metastases after SRS.

METHOD

Multiparametric contrast-enhanced T1- and T2-weighted imaging, apparent diffusion coefficient (ADC), and cerebral blood volume (CBV) were obtained from 52 patients with 69 metastases, showing enlarging enhancing masses after SRS. Voxel-wise clustering identified three structural MRI habitats (enhancing, solid low-enhancing, and nonviable) and three physiologic MRI habitats (hypervascular cellular, hypovascular cellular, and nonviable). Habitat-based predictors for viable tumor or radiation necrosis were identified by logistic regression. Performance was validated using the area under the curve (AUC) of the receiver operating characteristics curve in an independent dataset with 24 patients.

RESULTS

None of the physiologic MRI habitats was indicative of viable tumor. Viable tumor was predicted by a high-volume fraction of solid low-enhancing habitat (low T2-weighted and low CE-T1-weighted values; odds ratio [OR] 1.74, p <.001) and a low-volume fraction of nonviable tissue habitat (high T2-weighted and low CE-T1-weighted values; OR 0.55, p <.001). Combined structural MRI habitats yielded good discriminatory ability in both development (AUC 0.85, 95% confidence interval [CI]: 0.77-0.94) and validation sets (AUC 0.86, 95% CI:0.70-0.99), outperforming single ADC (AUC 0.64) and CBV (AUC 0.58) values. The site of progression matched with the solid low-enhancing habitat (72%, 8/11).

CONCLUSION

Solid low-enhancing and nonviable tissue habitats on structural MRI can help to localize viable tumor in patients with brain metastases after SRS.

KEY POINTS

• Structural MRI habitats helped to differentiate viable tumor from radiation necrosis. • Solid low-enhancing habitat was most helpful to find viable tumor. • Providing spatial information, the site of progression matched with solid low-enhancing habitat.

Understanding artificial intelligence based radiology studies: CNN architecture

Artificial intelligence (AI) in radiology has gained wide interest due to the development of neural network architectures with high performance in computer vision related tasks. As AI based software programs become more integrated into the clinical workflow, radiologists can benefit from better understanding the principles of artificial intelligence. This series aims to explain basic concepts of AI and its applications in medical imaging. In this article, we will review the background of neural network architecture and its application in imaging analysis.

Brain tissues have single-voxel signatures in multi-spectral MRI

Since the seminal works by Brodmann and contemporaries, it is well-known that different brain regions exhibit unique cytoarchitectonic and myeloarchitectonic features. Transferring the approach of classifying brain tissues - and other tissues - based on their intrinsic features to the realm of magnetic resonance (MR) is a longstanding endeavor. In the 1990s, atlas-based segmentation replaced earlier multi-spectral classification approaches because of the large overlap between the class distributions. Here, we explored the feasibility of performing global brain classification based on intrinsic MR features, and used several technological advances: ultra-high field MRI, q-space trajectory diffusion imaging revealing voxel-intrinsic diffusion properties, chemical exchange saturation transfer and semi-solid magnetization transfer imaging as a marker of myelination and neurochemistry, and current neural network architectures to analyze the data. In particular, we used the raw image data as well to increase the number of input features. We found that a global brain classification of roughly 97 brain regions was feasible with gross classification accuracy of 60%; and that mapping from voxel-intrinsic MR data to the brain region to which the data belongs is possible. This indicates the presence of unique MR signals of different brain regions, similar to their cytoarchitectonic and myeloarchitectonic fingerprints.

Comparison of Multispectral Image-Processing Methods for Brain Tissue Classification in BrainWeb Synthetic Data and Real MR Images

Accurate quantification of brain tissue is a fundamental and challenging task in neuroimaging. Over the past two decades, statistical parametric mapping (SPM) and FMRIB's Automated Segmentation Tool (FAST) have been widely used to estimate gray matter (GM) and white matter (WM) volumes. However, they cannot reliably estimate cerebrospinal fluid (CSF) volumes. To address this problem, we developed the TRIO algorithm (TRIOA), a new magnetic resonance (MR) multispectral classification method. SPM8, SPM12, FAST, and the TRIOA were evaluated using the BrainWeb database and real magnetic resonance imaging (MRI) data. In this paper, the MR brain images of 140 healthy volunteers (51.5 ± 15.8 y/o) were obtained using a whole-body 1.5 T MRI system (Aera, Siemens, Erlangen, Germany). Before classification, several preprocessing steps were performed, including skull stripping and motion and inhomogeneity correction. After extensive experimentation, the TRIOA was shown to be more effective than SPM and FAST. For real data, all test methods revealed that the participants aged 20–83 years exhibited an age-associated decline in GM and WM volume fractions. However, for CSF volume estimation, SPM8-s and SPM12-m both produced different results, which were also different compared with those obtained by FAST and the TRIOA. Furthermore, the TRIOA performed consistently better than both SPM and FAST for GM, WM, and CSF volume estimation. Compared with SPM and FAST, the proposed TRIOA showed more advantages by providing more accurate MR brain tissue classification and volume measurements, specifically in CSF volume estimation.

Identification of sarcomatoid differentiation in renal cell carcinoma by machine learning on multiparametric MRI

Sarcomatoid differentiation in RCC (sRCC) is associated with a poor prognosis, necessitating more aggressive management than RCC without sarcomatoid components (nsRCC). Since suspected renal cell carcinoma (RCC) tumors are not routinely biopsied for histologic evaluation, there is a clinical need for a non-invasive method to detect sarcomatoid differentiation pre-operatively. We utilized unsupervised self-organizing map (SOM) and supervised Learning Vector Quantizer (LVQ) machine learning to classify RCC tumors on T2-weighted, non-contrast T1-weighted fat-saturated, contrast-enhanced arterial-phase T1-weighted fat-saturated, and contrast-enhanced venous-phase T1-weighted fat-saturated MRI images. The SOM was trained on 8 nsRCC and 8 sRCC tumors, and used to compute Activation Maps for each training, validation (3 nsRCC and 3 sRCC), and test (5 nsRCC and 5 sRCC) tumor. The LVQ classifier was trained and optimized on Activation Maps from the 22 training and validation cohort tumors, and tested on Activation Maps of the 10 unseen test tumors. In this preliminary study, the SOM-LVQ model achieved a hold-out testing accuracy of 70% in the task of identifying sarcomatoid differentiation in RCC on standard multiparameter MRI (mpMRI) images. We have demonstrated a combined SOM-LVQ machine learning approach that is suitable for analysis of limited mpMRI datasets for the task of differential diagnosis.

Multiparameter MRI Predictors of Long-Term Survival in Glioblastoma Multiforme

Standard-of-care multiparameter magnetic resonance imaging (MRI) scans of the brain were used to objectively subdivide glioblastoma multiforme (GBM) tumors into regions that correspond to variations in blood flow, interstitial edema, and cellular density. We hypothesized that the distribution of these distinct tumor ecological "habitats" at the time of presentation will impact the course of the disease. We retrospectively analyzed initial MRI scans in 2 groups of patients diagnosed with GBM, a long-term survival group comprising subjects who survived >36 month postdiagnosis, and a short-term survival group comprising subjects who survived ≤19 month postdiagnosis. The single-institution discovery cohort contained 22 subjects in each group, while the multi-institution validation cohort contained 15 subjects per group. MRI voxel intensities were calibrated, and tumor voxels clustered on contrast-enhanced T1-weighted and fluid-attenuated inversion-recovery (FLAIR) images into 6 distinct "habitats" based on low- to medium- to high-contrast enhancement and low-high signal on FLAIR scans. Habitat 6 (high signal on calibrated contrast-enhanced T1-weighted and FLAIR sequences) comprised a significantly higher volume fraction of tumors in the long-term survival group (discovery cohort, 35% ± 6.5%; validation cohort, 34% ± 4.8%) compared with tumors in the short-term survival group (discovery cohort, 17% ± 4.5%, P < .03; validation cohort, 16 ± 4.0%, P < .007). Of the 6 distinct MRI-defined habitats, the fractional tumor volume of habitat 6 at diagnosis was significantly predictive of long- or short-term survival. We discuss a possible mechanistic basis for this association and implications for habitat-driven adaptive therapy of GBM.

MP2RAGE multispectral voxel-based morphometry in focal epilepsy

We assessed the applicability of MP2RAGE for voxel‐based morphometry. To this end, we analyzed its brain tissue segmentation characteristics in healthy subjects and the potential for detecting focal epileptogenic lesions (previously visible and nonvisible). Automated results and expert visual interpretations were compared with conventional VBM variants (i.e., T1 and T1 + FLAIR). Thirty‐one healthy controls and 21 patients with focal epilepsy were recruited. 3D T1‐, T2‐FLAIR, and MP2RAGE images (consisting of INV1, INV2, and MP2 maps) were acquired on a 3T MRI. The effects of brain tissue segmentation and lesion detection rates were analyzed among single‐ and multispectral VBM variants. MP2‐single‐contrast gave better delineation of deep, subcortical nuclei but was prone to misclassification of dura/vessels as gray matter, even more than conventional‐T1. The addition of multispectral combinations (INV1, INV2, or FLAIR) could markedly reduce such misclassifications. MP2 + INV1 yielded generally clearer gray matter segmentation allowing better differentiation of white matter and neighboring gyri. Different models detected known lesions with a sensitivity between 60 and 100%. In non lesional cases, MP2 + INV1 was found to be best with a concordant rate of 37.5%, specificity of 51.6% and concordant to discordant ratio of 0.60. In summary, we show that multispectral MP2RAGE VBM (e.g., MP2 + INV1, MP2 + INV2) can improve brain tissue segmentation and lesion detection in epilepsy.

Quantitative imaging of cancer in the postgenomic era: Radio(geno)mics, deep learning, and habitats

Although cancer often is referred to as "a disease of the genes," it is indisputable that the (epi)genetic properties of individual cancer cells are highly variable, even within the same tumor. Hence, preexisting resistant clones will emerge and proliferate after therapeutic selection that targets sensitive clones. Herein, the authors propose that quantitative image analytics, known as "radiomics," can be used to quantify and characterize this heterogeneity. Virtually every patient with cancer is imaged radiologically. Radiomics is predicated on the beliefs that these images reflect underlying pathophysiologies, and that they can be converted into mineable data for improved diagnosis, prognosis, prediction, and therapy monitoring. In the last decade, the radiomics of cancer has grown from a few laboratories to a worldwide enterprise. During this growth, radiomics has established a convention, wherein a large set of annotated image features (1-2000 features) are extracted from segmented regions of interest and used to build classifier models to separate individual patients into their appropriate class (eg, indolent vs aggressive disease). An extension of this conventional radiomics is the application of "deep learning," wherein convolutional neural networks can be used to detect the most informative regions and features without human intervention. A further extension of radiomics involves automatically segmenting informative subregions ("habitats") within tumors, which can be linked to underlying tumor pathophysiology. The goal of the radiomics enterprise is to provide informed decision support for the practice of precision oncology.

An overview of deep learning in medical imaging focusing on MRI

What has happened in machine learning lately, and what does it mean for the future of medical image analysis? Machine learning has witnessed a tremendous amount of attention over the last few years. The current boom started around 2009 when so-called deep artificial neural networks began outperforming other established models on a number of important benchmarks. Deep neural networks are now the state-of-the-art machine learning models across a variety of areas, from image analysis to natural language processing, and widely deployed in academia and industry. These developments have a huge potential for medical imaging technology, medical data analysis, medical diagnostics and healthcare in general, slowly being realized. We provide a short overview of recent advances and some associated challenges in machine learning applied to medical image processing and image analysis. As this has become a very broad and fast expanding field we will not survey the entire landscape of applications, but put particular focus on deep learning in MRI. Our aim is threefold: (i) give a brief introduction to deep learning with pointers to core references; (ii) indicate how deep learning has been applied to the entire MRI processing chain, from acquisition to image retrieval, from segmentation to disease prediction; (iii) provide a starting point for people interested in experimenting and perhaps contributing to the field of deep learning for medical imaging by pointing out good educational resources, state-of-the-art open-source code, and interesting sources of data and problems related medical imaging.

ACTIVE MEAN FIELDS FOR PROBABILISTIC IMAGE SEGMENTATION: CONNECTIONS WITH CHAN-VESE AND RUDIN-OSHER-FATEMI MODELS

Segmentation is a fundamental task for extracting semantically meaningful regions from an image. The goal of segmentation algorithms is to accurately assign object labels to each image location. However, image-noise, shortcomings of algorithms, and image ambiguities cause uncertainty in label assignment. Estimating the uncertainty in label assignment is important in multiple application domains, such as segmenting tumors from medical images for radiation treatment planning. One way to estimate these uncertainties is through the computation of posteriors of Bayesian models, which is computationally prohibitive for many practical applications. On the other hand, most computationally efficient methods fail to estimate label uncertainty. We therefore propose in this paper the Active Mean Fields (AMF) approach, a technique based on Bayesian modeling that uses a mean-field approximation to efficiently compute a segmentation and its corresponding uncertainty. Based on a variational formulation, the resulting convex model combines any label-likelihood measure with a prior on the length of the segmentation boundary. A specific implementation of that model is the Chan-Vese segmentation model (CV), in which the binary segmentation task is defined by a Gaussian likelihood and a prior regularizing the length of the segmentation boundary. Furthermore, the Euler-Lagrange equations derived from the AMF model are equivalent to those of the popular Rudin-Osher-Fatemi (ROF) model for image denoising. Solutions to the AMF model can thus be implemented by directly utilizing highly-efficient ROF solvers on log-likelihood ratio fields. We qualitatively assess the approach on synthetic data as well as on real natural and medical images. For a quantitative evaluation, we apply our approach to the icgbench dataset.

Multimodal MEMPRAGE, FLAIR, and [Formula: see text] Segmentation to Resolve Dura and Vessels from Cortical Gray Matter

While widely in use in automated segmentation approaches for the detection of group differences or of changes associated with continuous predictors in gray matter volume, T1-weighted images are known to represent dura and cortical vessels with signal intensities similar to those of gray matter. By considering multiple signal sources at once, multimodal segmentation approaches may be able to resolve these different tissue classes and address this potential confound. We explored here the simultaneous use of FLAIR and apparent transverse relaxation rates (a signal related to T2* relaxation maps and having similar contrast) with T1-weighted images. Relative to T1-weighted images alone, multimodal segmentation had marked positive effects on 1. the separation of gray matter from dura, 2. the exclusion of vessels from the gray matter compartment, and 3. the contrast with extracerebral connective tissue. While obtainable together with the T1-weighted images without increasing scanning times, apparent transverse relaxation rates were less effective than added FLAIR images in providing the above mentioned advantages. FLAIR images also improved the detection of cortical matter in areas prone to susceptibility artifacts in standard MPRAGE T1-weighted images, while the addition of transverse relaxation maps exacerbated the effect of these artifacts on segmentation. Our results confirm that standard MPRAGE segmentation may overestimate gray matter volume by wrongly assigning vessels and dura to this compartment and show that multimodal approaches may greatly improve the specificity of cortical segmentation. Since multimodal segmentation is easily implemented, these benefits are immediately available to studies focusing on translational applications of structural imaging.

Cancer heterogeneity and imaging

There is interest in identifying and quantifying tumor heterogeneity at the genomic, tissue pathology and clinical imaging scales, as this may help better understand tumor biology and may yield useful biomarkers for guiding therapy-based decision making. This review focuses on the role and value of using x-ray, CT, MRI and PET based imaging methods that identify, measure and map tumor heterogeneity. In particular we highlight the potential value of these techniques and the key challenges required to validate and qualify these biomarkers for clinical use.

From chalkboard, slides, and paper to e-learning: How computing technologies have transformed anatomical sciences education

Until the late-twentieth century, primary anatomical sciences education was relatively unenhanced by advanced technology and dependent on the mainstays of printed textbooks, chalkboard- and photographic projection-based classroom lectures, and cadaver dissection laboratories. But over the past three decades, diffusion of innovations in computer technology transformed the practices of anatomical education and research, along with other aspects of work and daily life. Increasing adoption of first-generation personal computers (PCs) in the 1980s paved the way for the first practical educational applications, and visionary anatomists foresaw the usefulness of computers for teaching. While early computers lacked high-resolution graphics capabilities and interactive user interfaces, applications with video discs demonstrated the practicality of programming digital multimedia linking descriptive text with anatomical imaging. Desktop publishing established that computers could be used for producing enhanced lecture notes, and commercial presentation software made it possible to give lectures using anatomical and medical imaging, as well as animations. Concurrently, computer processing supported the deployment of medical imaging modalities, including computed tomography, magnetic resonance imaging, and ultrasound, that were subsequently integrated into anatomy instruction. Following its public birth in the mid-1990s, the World Wide Web became the ubiquitous multimedia networking technology underlying the conduct of contemporary education and research. Digital video, structural simulations, and mobile devices have been more recently applied to education. Progressive implementation of computer-based learning methods interacted with waves of ongoing curricular change, and such technologies have been deemed crucial for continuing medical education reforms, providing new challenges and opportunities for anatomical sciences educators. Anat Sci Educ 9: 583-602. © 2016 American Association of Anatomists.

MRBrainS Challenge: Online Evaluation Framework for Brain Image Segmentation in 3T MRI Scans

Many methods have been proposed for tissue segmentation in brain MRI scans. The multitude of methods proposed complicates the choice of one method above others. We have therefore established the MRBrainS online evaluation framework for evaluating (semi)automatic algorithms that segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) on 3T brain MRI scans of elderly subjects (65–80 y). Participants apply their algorithms to the provided data, after which their results are evaluated and ranked. Full manual segmentations of GM, WM, and CSF are available for all scans and used as the reference standard. Five datasets are provided for training and fifteen for testing. The evaluated methods are ranked based on their overall performance to segment GM, WM, and CSF and evaluated using three evaluation metrics (Dice, H95, and AVD) and the results are published on the MRBrainS13 website. We present the results of eleven segmentation algorithms that participated in the MRBrainS13 challenge workshop at MICCAI, where the framework was launched, and three commonly used freeware packages: FreeSurfer, FSL, and SPM. The MRBrainS evaluation framework provides an objective and direct comparison of all evaluated algorithms and can aid in selecting the best performing method for the segmentation goal at hand.

Interactive Feature Space Explorer© for multi-modal magnetic resonance imaging

Wider information content of multi-modal biomedical imaging is advantageous for detection, diagnosis and prognosis of various pathologies. However, the necessity to evaluate a large number images might hinder these advantages and reduce the efficiency. Herein, a new computer aided approach based on the utilization of feature space (FS) with reduced reliance on multiple image evaluations is proposed for research and routine clinical use. The method introduces the physician experience into the discovery process of FS biomarkers for addressing biological complexity, e.g., disease heterogeneity. This, in turn, elucidates relevant biophysical information which would not be available when automated algorithms are utilized. Accordingly, the prototype platform was designed and built for interactively investigating the features and their corresponding anatomic loci in order to identify pathologic FS regions. While the platform might be potentially beneficial in decision support generally and specifically for evaluating outlier cases, it is also potentially suitable for accurate ground truth determination in FS for algorithm development. Initial assessments conducted on two different pathologies from two different institutions provided valuable biophysical perspective. Investigations of the prostate magnetic resonance imaging data resulted in locating a potential aggressiveness biomarker in prostate cancer. Preliminary findings on renal cell carcinoma imaging data demonstrated potential for characterization of disease subtypes in the FS.

Robust volume assessment of brain tissues for 3-dimensional fourier transformation MRI via a novel multispectral technique

A new TRIO algorithm method integrating three different algorithms is proposed to perform brain MRI segmentation in the native coordinate space, with no need of transformation to a standard coordinate space or the probability maps for segmentation. The method is a simple voxel-based algorithm, derived from multispectral remote sensing techniques, and only requires minimal operator input to depict GM, WM, and CSF tissue clusters to complete classification of a 3D high-resolution multislice-multispectral MRI data. Results showed very high accuracy and reproducibility in classification of GM, WM, and CSF in multislice-multispectral synthetic MRI data. The similarity indexes, expressing overlap between classification results and the ground truth, were 0.951, 0.962, and 0.956 for GM, WM, and CSF classifications in the image data with 3% noise level and 0% non-uniformity intensity. The method particularly allows for classification of CSF with 0.994, 0.961 and 0.996 of accuracy, sensitivity and specificity in images data with 3% noise level and 0% non-uniformity intensity, which had seldom performed well in previous studies. As for clinical MRI data, the quantitative data of brain tissue volumes aligned closely with the brain morphometrics in three different study groups of young adults, elderly volunteers, and dementia patients. The results also showed very low rates of the intra- and extra-operator variability in measurements of the absolute volumes and volume fractions of cerebral GM, WM, and CSF in three different study groups. The mean coefficients of variation of GM, WM, and CSF volume measurements were in the range of 0.03% to 0.30% of intra-operator measurements and 0.06% to 0.45% of inter-operator measurements. In conclusion, the TRIO algorithm exhibits a remarkable ability in robust classification of multislice-multispectral brain MR images, which would be potentially applicable for clinical brain volumetric analysis and explicitly promising in cross-sectional and longitudinal studies of different subject groups.

Imaging intratumor heterogeneity: role in therapy response, resistance, and clinical outcome

Tumors exhibit genomic and phenotypic heterogeneity, which has prognostic significance and may influence response to therapy. Imaging can quantify the spatial variation in architecture and function of individual tumors through quantifying basic biophysical parameters such as CT density or MRI signal relaxation rate; through measurements of blood flow, hypoxia, metabolism, cell death, and other phenotypic features; and through mapping the spatial distribution of biochemical pathways and cell signaling networks using PET, MRI, and other emerging molecular imaging techniques. These methods can establish whether one tumor is more or less heterogeneous than another and can identify subregions with differing biology. In this article, we review the image analysis methods currently used to quantify spatial heterogeneity within tumors. We discuss how analysis of intratumor heterogeneity can provide benefit over more simple biomarkers such as tumor size and average function. We consider how imaging methods can be integrated with genomic and pathology data, instead of being developed in isolation. Finally, we identify the challenges that must be overcome before measurements of intratumoral heterogeneity can be used routinely to guide patient care.

Experimental and computational investigation of altered mechanical properties in myocardium after hydrogel injection

The material properties of myocardium are an important determinant of global left ventricular function. Myocardial infarction results in a series of maladaptive geometric alterations which lead to increased stress and risk of heart failure. In vivo studies have demonstrated that material injection can mitigate these changes. More importantly, the material properties of these injectates can be tuned to minimize wall thinning and ventricular dilation. The current investigation combines experimental data and finite element modeling to correlate how injectate mechanics and volume influence myocardial wall stress. Experimentally, mechanics were characterized with biaxial testing and injected hydrogel volumes were measured with magnetic resonance imaging. Injection of hyaluronic acid hydrogel increased the stiffness of the myocardium/hydrogel composite region in an anisotropic manner, significantly increasing the modulus in the longitudinal direction compared to control myocardium. Increased stiffness, in combination with increased volume from hydrogel injection, reduced the global average fiber stress by ~14% and the transmural average by ~26% in the simulations. Additionally, stiffening in an anisotropic manner enhanced the influence of hydrogel treatment in decreasing stress. Overall, this work provides insight on how injectable biomaterials can be used to attenuate wall stress and provides tools to further optimize material properties for therapeutic applications.

An open source multivariate framework for n-tissue segmentation with evaluation on public data

We introduce Atropos, an ITK-based multivariate n-class open source segmentation algorithm distributed with ANTs ( http://www.picsl.upenn.edu/ANTs). The Bayesian formulation of the segmentation problem is solved using the Expectation Maximization (EM) algorithm with the modeling of the class intensities based on either parametric or non-parametric finite mixtures. Atropos is capable of incorporating spatial prior probability maps (sparse), prior label maps and/or Markov Random Field (MRF) modeling. Atropos has also been efficiently implemented to handle large quantities of possible labelings (in the experimental section, we use up to 69 classes) with a minimal memory footprint. This work describes the technical and implementation aspects of Atropos and evaluates its performance on two different ground-truth datasets. First, we use the BrainWeb dataset from Montreal Neurological Institute to evaluate three-tissue segmentation performance via (1) K-means segmentation without use of template data; (2) MRF segmentation with initialization by prior probability maps derived from a group template; (3) Prior-based segmentation with use of spatial prior probability maps derived from a group template. We also evaluate Atropos performance by using spatial priors to drive a 69-class EM segmentation problem derived from the Hammers atlas from University College London. These evaluation studies, combined with illustrative examples that exercise Atropos options, demonstrate both performance and wide applicability of this new platform-independent open source segmentation tool.

Optimizing hippocampal segmentation in infants utilizing MRI post-acquisition processing

This study aims to determine the most reliable method for infant hippocampal segmentation by comparing magnetic resonance (MR) imaging post-acquisition processing techniques: contrast to noise ratio (CNR) enhancement, or reformatting to standard orientation. MR scans were performed with a 1.5 T GE scanner to obtain dual echo T2 and proton density (PD) images at term equivalent (38-42 weeks' gestational age). 15 hippocampi were manually traced four times on ten infant images by 2 independent raters on the original T2 image, as well as images processed by: a) combining T2 and PD images (T2-PD) to enhance CNR; then b) reformatting T2-PD images perpendicular to the long axis of the left hippocampus. CNRs and intraclass correlation coefficients (ICC) were calculated. T2-PD images had 17% higher CNR (15.2) than T2 images (12.6). Original T2 volumes' ICC was 0.87 for rater 1 and 0.84 for rater 2, whereas T2-PD images' ICC was 0.95 for rater 1 and 0.87 for rater 2. Reliability of hippocampal segmentation on T2-PD images was not improved by reformatting images (rater 1 ICC = 0.88, rater 2 ICC = 0.66). Post-acquisition processing can improve CNR and hence reliability of hippocampal segmentation in neonate MR scans when tissue contrast is poor. These findings may be applied to enhance boundary definition in infant segmentation for various brain structures or in any volumetric study where image contrast is sub-optimal, enabling hippocampal structure-function relationships to be explored.

Comparative analysis of nonlinear dimensionality reduction techniques for breast MRI segmentation

PURPOSE

Visualization of anatomical structures using radiological imaging methods is an important tool in medicine to differentiate normal from pathological tissue and can generate large amounts of data for a radiologist to read. Integrating these large data sets is difficult and time-consuming. A new approach uses both supervised and unsupervised advanced machine learning techniques to visualize and segment radiological data. This study describes the application of a novel hybrid scheme, based on combining wavelet transform and nonlinear dimensionality reduction (NLDR) methods, to breast magnetic resonance imaging (MRI) data using three well-established NLDR techniques, namely, ISOMAP, local linear embedding (LLE), and diffusion maps (DfM), to perform a comparative performance analysis.

METHODS

Twenty-five breast lesion subjects were scanned using a 3T scanner. MRI sequences used were T1-weighted, T2-weighted, diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE) imaging. The hybrid scheme consisted of two steps: preprocessing and postprocessing of the data. The preprocessing step was applied for B(1) inhomogeneity correction, image registration, and wavelet-based image compression to match and denoise the data. In the postprocessing step, MRI parameters were considered data dimensions and the NLDR-based hybrid approach was applied to integrate the MRI parameters into a single image, termed the embedded image. This was achieved by mapping all pixel intensities from the higher dimension to a lower dimensional (embedded) space. For validation, the authors compared the hybrid NLDR with linear methods of principal component analysis (PCA) and multidimensional scaling (MDS) using synthetic data. For the clinical application, the authors used breast MRI data, comparison was performed using the postcontrast DCE MRI image and evaluating the congruence of the segmented lesions.

RESULTS

The NLDR-based hybrid approach was able to define and segment both synthetic and clinical data. In the synthetic data, the authors demonstrated the performance of the NLDR method compared with conventional linear DR methods. The NLDR approach enabled successful segmentation of the structures, whereas, in most cases, PCA and MDS failed. The NLDR approach was able to segment different breast tissue types with a high accuracy and the embedded image of the breast MRI data demonstrated fuzzy boundaries between the different types of breast tissue, i.e., fatty, glandular, and tissue with lesions (>86%).

CONCLUSIONS

The proposed hybrid NLDR methods were able to segment clinical breast data with a high accuracy and construct an embedded image that visualized the contribution of different radiological parameters.

Novel whole brain segmentation and volume estimation using quantitative MRI

OBJECTIVES

Brain segmentation and volume estimation of grey matter (GM), white matter (WM) and cerebro-spinal fluid (CSF) are important for many neurological applications. Volumetric changes are observed in multiple sclerosis (MS), Alzheimer's disease and dementia, and in normal aging. A novel method is presented to segment brain tissue based on quantitative magnetic resonance imaging (qMRI) of the longitudinal relaxation rate R(1), the transverse relaxation rate R(2) and the proton density, PD.

METHODS

Previously reported qMRI values for WM, GM and CSF were used to define tissues and a Bloch simulation performed to investigate R(1), R(2) and PD for tissue mixtures in the presence of noise. Based on the simulations a lookup grid was constructed to relate tissue partial volume to the R(1)-R(2)-PD space. The method was validated in 10 healthy subjects. MRI data were acquired using six resolutions and three geometries.

RESULTS

Repeatability for different resolutions was 3.2% for WM, 3.2% for GM, 1.0% for CSF and 2.2% for total brain volume. Repeatability for different geometries was 8.5% for WM, 9.4% for GM, 2.4% for CSF and 2.4% for total brain volume.

CONCLUSION

We propose a new robust qMRI-based approach which we demonstrate in a patient with MS.

KEY POINTS

• A method for segmenting the brain and estimating tissue volume is presented • This method measures white matter, grey matter, cerebrospinal fluid and remaining tissue • The method calculates tissue fractions in voxel, thus accounting for partial volume • Repeatability was 2.2% for total brain volume with imaging resolution <2.0 mm.

ABNORMALITY DETECTION IN BRAIN MR IMAGES USING MINIMUM ERROR THRESHOLDING METHOD

Medical image segmentation plays an instrumental role in clinical diagnosis. An ideal medical image segmentation scheme should possess some preferred properties such as minimum user interaction, fast computation, and accurate and robust segmentation results. In this paper, an automated algorithm is proposed to enable the doctors to detect the presence of abnormal tissues in brain magnetic resonance images (MRIs). The merged image of different weighted images of each slice is obtained by averaging the intensities of pixels and is enhanced based on their local information by variance mapping. The abnormal regions are segmented by using minimum error thresholding method by formulating a criterion function. The segmentation is performed on the real data of MRI images for different abnormalities and the results are compared with radiologist labeled ground truth. Quantitative analysis between ground truth and segmented abnormal region is presented in terms of Percent Match and Correspondence Ratio. A maximum average percent match of 98.56% and correspondence ratio of 0.8892 of an MRI data is obtained.

Learning likelihoods for labeling (L3): a general multi-classifier segmentation algorithm

PURPOSE

To develop an MRI segmentation method for brain tissues, regions, and substructures that yields improved classification accuracy. Current brain segmentation strategies include two complementary strategies. Multi-spectral classification techniques generate excellent segmentations for tissues with clear intensity contrast, but fail to identify structures defined largely by location, such as lobar parcellations and certain subcortical structures. Conversely, multi-template label fusion methods are excellent for structures defined largely by location, but perform poorly when segmenting structures that cannot be accurately identified through a consensus of registered templates.

METHODS

We propose here a novel multi-classifier fusion algorithm with the advantages of both types of segmentation strategy. We illustrate and validate this algorithm using a group of 14 expertly hand-labeled images.

RESULTS

Our method generated segmentations of cortical and subcortical structures that were more similar to hand-drawn segmentations than majority vote label fusion or a recently published intensity/label fusion method.

CONCLUSIONS

We have presented a novel, general segmentation algorithm with the advantages of both statistical classifiers and label fusion techniques.

Volumetric reduction in various cortical regions of elderly patients with early-onset and late-onset mania

BACKGROUND

Few studies have examined alterations of the brain in elderly bipolar patients. As late-onset mania is associated with increased cerebrovascular morbidity and neurological damage compared with typical/early-onset mania, we investigated differences in the volume of various cortical regions between elderly patients with early-onset versus late-onset mania.

METHODS

We recruited 44 bipolar patients aged over 60 years, who underwent volumetric magnetic resonance imaging at 1.5 T. The analytic method is based on the hidden Markov random field model with an expectation-maximization algorithm. We determined the volume of each cortical region as a percentage of the total intracranial volume. The cutoff age for defining early versus late onset was 45 years.

RESULTS

The study participants consisted of 25 patients with early-onset mania and 19 patients with late-onset mania; their mean ages were 65.7 years and 62.8 years, respectively. The demographic variables of the two groups were comparable. The volumes of the left caudate nucleus (p = 0.022) and left middle frontal gyrus (p = 0.013) were significantly greater and that of the right posterior cingulate gyrus (p = 0.019) was significantly smaller in the late-onset group. More patients with late-onset mania had comorbid cerebrovascular disease (p = 0.072).

CONCLUSIONS

The right posterior cingulate gyrus is smaller and the left caudate nucleus and left middle frontal gyrus are larger in patients with late-onset mania compared with those with early-onset mania. Volumetric change in brain regions may vary in elderly bipolar patients with early and late-onset mania.

Quantitative analysis in clinical applications of brain MRI using independent component analysis coupled with support vector machine

PURPOSE

To effectively perform quantification of brain normal tissues and pathologies simultaneously, independent component analysis (ICA) coupled with support vector machine (SVM) is investigated and evaluated for effective volumetric measurements of normal and lesion tissues using multispectral MR images.

MATERIALS AND METHODS

Synthetic and real MR data of normal brain and white matter lesion (WML) data were used to evaluate the accuracy and reproducibility of gray matter (GM), white matter (WM), and WML volume measurements by using the proposed ICA+SVM method to analyze three sets of MR images, T1-weighted, T2-weighted, and proton density/fluid-attenuated inversion recovery images.

RESULTS

The Tanimoto indexes of GM/WM classification in the normal synthetic data calculated by the ICA+SVM method were 0.82/0.89 for data with 0% noise level. As for clinical MR data experiments, the ICA+SVM method clearly extracted the normal tissues and white matter hyperintensity lesions from the MR images, with low intra- and inter-operator coefficient of variations.

CONCLUSION

The experiments conducted provide evidence that the ICA+SVM method has shown promise and potential in applications to classification of normal and pathological tissues in brain MRI.

Automated brain tissue segmentation based on fractional signal mapping from inversion recovery Look-Locker acquisition

Most current automated segmentation methods are performed on T(1)- or T(2)-weighted MR images, relying on relative image intensity that is dependent on other MR parameters and sensitive to B(1) magnetic field inhomogeneity. Here, we propose an image segmentation method based on quantitative longitudinal magnetization relaxation time (T(1)) of brain tissues. Considering the partial volume effect, fractional volume maps of brain tissues (white matter, gray matter, and cerebrospinal fluid) were obtained by fitting the observed signal in an inversion recovery procedure to a linear combination of three exponential functions, which represents the relaxations of each of the tissue types. A Look-Locker acquisition was employed to accelerate the acquisition process. The feasibility and efficacy of this proposed method were evaluated using simulations and experiments. The potential applications of this method in the study of neurological disease as well as normal brain development and aging are discussed.

The brain MR Image segmentation techniques and use of diagnostic packages

RATIONALE AND OBJECTIVES

This article provides a survey of segmentation methods for medical images. Usually, classification of segmentation methods is done based on the approaches adopted and the domain of application.

MATERIALS AND METHODS

This survey is conducted on the recent segmentation methods used in biomedical image processing and explores the methods useful for better segmentation. A critical appraisal of the current status of semiautomated and automated methods is made for the segmentation of anatomical medical images emphasizing the advantages and disadvantages. Computer-aided diagnosis (CAD) used by radiologists as a second opinion has become one of the major research areas in medical imaging and diagnostic radiology. A picture archiving communication system (PACS) is an integrated workflow system for managing images and related data that is designed to streamline operations throughout the whole patient care delivery process.

RESULTS

By using PACS, the medical image interpretation may be changed from conventional hard-copy images to soft-copy studies viewed on the systems workstations.

CONCLUSION

The automatic segmentations assist the doctors in making quick diagnosis. The CAD need not be comparable to that of physicians, but is surely complementary.

Automatic segmentation of newborn brain MRI

Quantitative brain tissue segmentation from newborn MRI offers the possibility of improved clinical decision making and diagnosis, new insight into the mechanisms of disease, and new methods for the evaluation of treatment protocols for preterm newborns. Such segmentation is challenging, however, due to the imaging characteristics of the developing brain. Existing techniques for newborn segmentation either achieve automation by ignoring critical distinctions between different tissue types or require extensive expert interaction. Because manual interaction is time consuming and introduces both bias and variability, we have developed a novel automatic segmentation algorithm for brain MRI of newborn infants. The key algorithmic contribution of this work is a new approach for automatically learning patient-specific class-conditional probability density functions. The algorithm achieves performance comparable to expert segmentations while automatically identifying cortical gray matter, subcortical gray matter, cerebrospinal fluid, myelinated white matter and unmyelinated white matter. We compared the performance of our algorithm with a previously published semi-automated algorithm and with expert-drawn images. Our algorithm achieved an accuracy comparable with methods that require undesirable manual interaction.

Evaluation of automated brain MR image segmentation and volumetry methods

We compare three widely used brain volumetry methods available in the software packages FSL, SPM5, and FreeSurfer and evaluate their performance using simulated and real MR brain data sets. We analyze the accuracy of gray and white matter volume measurements and their robustness against changes of image quality using the BrainWeb MRI database. These images are based on "gold-standard" reference brain templates. This allows us to assess between- (same data set, different method) and also within-segmenter (same method, variation of image quality) comparability, for both of which we find pronounced variations in segmentation results for gray and white matter volumes. The calculated volumes deviate up to >10% from the reference values for gray and white matter depending on method and image quality. Sensitivity is best for SPM5, volumetric accuracy for gray and white matter was similar in SPM5 and FSL and better than in FreeSurfer. FSL showed the highest stability for white (<5%), FreeSurfer (6.2%) for gray matter for constant image quality BrainWeb data. Between-segmenter comparisons show discrepancies of up to >20% for the simulated data and 24% on average for the real data sets, whereas within-method performance analysis uncovered volume differences of up to >15%. Since the discrepancies between results reach the same order of magnitude as volume changes observed in disease, these effects limit the usability of the segmentation methods for following volume changes in individual patients over time and should be taken into account during the planning and analysis of brain volume studies.

Slowed orienting of covert visual-spatial attention in autism: Specific deficits associated with cerebellar and parietal abnormality

The most commonly reported finding from structural brain studies in autism is abnormality of the cerebellum. Autopsy and magnetic resonance imaging (MR) studies from nine independent research groups have found developmental abnormality of the cerebellar vermis or hemispheres in the majority of the more than 240 subjects with autism who were studied. We reported previously that patients with autism and those with acquired damage to the cerebellum were slow to shift attention between and within sensory modalities. In this study, we found that patients with autism who come from a group with significant cerebellar abnormality were also slow to orient attention in space.

A subgroup of these patients who have additional or corollary parietal abnormality, like previously studied patients with acquired parietal damage, were also slow to detect and respond to information outside an attended location. Posner, Walker, Friedrich, and Rafal (1984) showed that patients with parietal lesions were slow to respond to contralesional information if they were attending an ipsilesional location. This study has replicated that finding in patients with autism who have developmental bilateral parietal abnormality, and found a strong correlation between the attentional deficits and the amount of neuroanatomic parietal abnormality in these patients. This is the first time in the study of autism that there is evidence for a statistically significant association of the size of a specific brain structural abnormality with a specific behavioral deficit.

These findings illustrate that in autism different patterns of underlying brain pathology may result in different patterns of functional deficits. In conjunction with previous studies of patients with acquired lesions, these data have implications for the brain bases of normal attention. The cerebellum may affect the speed with which attentional resources can be activated, while the parietal cortex affects the ability to use those resources for efficient information processing at locations outside an attended focus. Deficits in the speed and efficiency with which neural activity can be modulated to facilitate processing can clearly influence cognitive function. Such deficits may contribute to the behavioral disabilities that characterize autism.

Automated segmentation and classification of high throughput yeast assay spots

Several technologies for characterizing genes and proteins from humans and other organisms use yeast growth or color development as read outs. The yeast two-hybrid assay, for example, detects protein-protein interactions by measuring the growth of yeast on a specific solid medium, or the ability of the yeast to change color when grown on a medium containing a chromogenic substrate. Current systems for analyzing the results of these types of assays rely on subjective and inefficient scoring of growth or color by human experts. Here, an image analysis system is described for scoring yeast growth and color development in high throughput biological assays. The goal is to locate the spots and score them in color images of two types of plates named "X-Gal" and "growth assay" plates, with uniformly placed spots (cell areas) on each plate (both plates in one image). The scoring system relies on color for the X-Gal spots, and texture properties for the growth assay spots. A maximum likelihood projection-based segmentation is developed to automatically locate spots of yeast on each plate. Then color histogram and wavelet texture features are extracted for scoring using an optimal linear transformation. Finally, an artificial neural network is used to score the X-Gal and growth assay spots using the extracted features. The performance of the system is evaluated using spots of 60 images. After training the networks using training and validation sets, the system was assessed on the test set. The overall accuracies of 95.4% and 88.2% are achieved, respectively, for scoring the X-Gal and growth assay spots.

Combo acquisitions: balancing scan time reduction and image quality

Recently a new technique for the combined acquisition of multicontrast images, termed "combo acquisition," was introduced. In combo acquisitions, the three concepts of 1) variable acquisition parameters, 2) k-space data sharing, and 3) multicontrast imaging are systematically integrated to reduce MRI scan time and improve data utilization in a clinical setting. In this study, two-contrast and three-contrast spin-echo (SE) and turbo spin-echo (TSE) combo acquisition protocols that were designed and optimized in simulation experiments were implemented on a 1.5 T clinical scanner. Phantom and human brain data from volunteers and patients were acquired. Scan time reductions of 25-52% were achieved compared to standard acquisitions, largely confirming the simulation results. We evaluated the resulting images by quantitatively analyzing the preservation of contrast and the signal-to-noise ratio (SNR). In addition, data sets for 10 clinical cases obtained with TSE combo and corresponding standard acquisitions were graded by two experienced neuroradiologists in terms of the level of artifacts and image quality for comparison. Only minor image degradation with the combo scans was observed, indicating an inherent trade-off between scan time reduction and image quality. The specific aspects of combo acquisitions with respect to motion, flow, and k-space data weighting are discussed.

Characterization of cerebral tissue by MRI map ISODATA in embolic stroke in rat

ISODATA using MRI parameter-weighted images has been previously employed to characterize ischemic cell damage after stroke in rats. In an effort to increase the objectivity and to further automate the ISODATA, MRI parameter maps were now employed. Male Wistar rats were subjected to embolic stroke and received treatment via a femoral vein at 4 h post-stroke. The control rats received saline and were sacrificed at 6, 24 and 48 h after stroke, respectively. Treated rats received rtPA alone or were treated with a combination of rtPA and an antibody, 7E3 F(ab')2, against the glycoprotein receptor that binds the platelet to fibrin. These rats were sacrificed at 24, or 48, h post-stroke. T1, T2 and diffusion maps were employed for map ISODATA analysis. H&E histological analysis of coronal sections of tissue was performed and compared with map ISODATA from the corresponding sections. ISODATA signatures were highly correlated (R approximately 0.80, P < 0.0001) with the ischemic cell damage analyzed at 6, 24 and 48 h post-stroke. At 24 and 48 h after stroke, ISODATA lesion sizes were highly correlated (R > 0.97, P < 0.001) with lesion sizes measured histologically. The combination treatment of rtPA and 7E3 F(ab')2 reduced both infarction size (P < 0.002) and average signature (P < 0.03) at 48 h after stroke, compared to saline-treated animals. No significant difference was found between saline and rtPA-alone-treated rats. The map ISODATA successfully provides objective and automated quantitation of the ischemic damage in both size and severity in an embolic stroke model of rat with and without a therapeutic intervention.

Partial volume segmentation of brain magnetic resonance images based on maximum a posteriori probability

Noise, partial volume (PV) effect, and image-intensity inhomogeneity render a challenging task for segmentation of brain magnetic resonance (MR) images. Most of the current MR image segmentation methods focus on only one or two of the above-mentioned effects. The objective of this paper is to propose a unified framework, based on the maximum a posteriori probability principle, by taking all these effects into account simultaneously in order to improve image segmentation performance. Instead of labeling each image voxel with a unique tissue type, the percentage of each voxel belonging to different tissues, which we call a mixture, is considered to address the PV effect. A Markov random field model is used to describe the noise effect by considering the nearby spatial information of the tissue mixture. The inhomogeneity effect is modeled as a bias field characterized by a zero mean Gaussian prior probability. The well-known fuzzy C-mean model is extended to define the likelihood function of the observed image. This framework reduces theoretically, under some assumptions, to the adaptive fuzzy C-mean (AFCM) algorithm proposed by Pham and Prince. Digital phantom and real clinical MR images were used to test the proposed framework. Improved performance over the AFCM algorithm was observed in a clinical environment where the inhomogeneity, noise level, and PV effect are commonly encountered.

Unbiased segmentation of diffusion-weighted magnetic resonance images of the brain using iterative clustering

Segmentation of diffusion-weighted echo-planar imaging (DW-EPI) is challenging because of concerns regarding spatial resolution and distortion. Methods commonly used require manual input and often need thresholding measures to segment white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF). This may introduce operator bias and misclassification error. When comparing patients with a diffuse disease process-such as multiple sclerosis (MS)--with healthy controls, although information from all images may be biased due to disease effect, this is more so if the data set employed to perform segmentation is also used as a measured outcome for the study, for example, fractional anisotropy maps. Presented in this work is an unbiased method for segmenting DW-EPI data sets using the b=0 and single-shot inversion recovery EPI into WM, GM and CSF. The method employs an iterative clustering technique to account for partial volume effects and signal variation caused by radiofrequency inhomogeneity. The technique is evaluated with both real and synthetic brain data and results compared with statistical parametric mapping (SPM02). With synthetic brain data, where a gold standard of segmentation exists, the presented method showed less misclassification compared to SPM02. The unbiased method proposed may provide a more accurate methodology of segmentation in the analysis of DWI-EPI images in conditions such as MS.

Automated segmentation of neuroanatomical structures in multispectral MR microscopy of the mouse brain

We present the automated segmentation of magnetic resonance microscopy (MRM) images of the C57BL/6J mouse brain into 21 neuroanatomical structures, including the ventricular system, corpus callosum, hippocampus, caudate putamen, inferior colliculus, internal capsule, globus pallidus, and substantia nigra. The segmentation algorithm operates on multispectral, three-dimensional (3D) MR data acquired at 90-microm isotropic resolution. Probabilistic information used in the segmentation is extracted from training datasets of T2-weighted, proton density-weighted, and diffusion-weighted acquisitions. Spatial information is employed in the form of prior probabilities of occurrence of a structure at a location (location priors) and the pairwise probabilities between structures (contextual priors). Validation using standard morphometry indices shows good consistency between automatically segmented and manually traced data. Results achieved in the mouse brain are comparable with those achieved in human brain studies using similar techniques. The segmentation algorithm shows excellent potential for routine morphological phenotyping of mouse models.

Statistical analysis of fractal-based brain tumor detection algorithms

Fractals are geometric objects that have a noninteger fractal dimension (FD). The FD has been exploited for various biomedical recognition applications such as breast tumor and lung tumor detection. Our previous work shows that the FD is useful in the detection of brain tumors when a reference nontumor image is available. In this work, we extend our previous work by statistically validating the results of FD analysis on a set of 80 real MR and CT images. Our half-image technique requires that the tumor is located in one half of the brain whereas our whole-image technique does not. Furthermore, we alleviate the need for a reference (control) nontumor image to compute the tumor FD, which was necessary in our previous work. We also compare the brain tumor detection performance of our algorithms with other fractal-based algorithms in the literature and statistically validate our results against manually segmented tumor images. We find that the tumor region offers a statistically significant lower FD compared with that of the nontumor area for most of the FD algorithms studied in this work. Thus, our statistical analysis suggests that these FD algorithms may be exploited successfully to determine the possible presence and location of brain tumors in MR and CT images.

Multiparametric ISODATA analysis of embolic stroke and rt-PA intervention in rat

To increase the sensitivity of MRI parameters to detect tissue damage of ischemic stroke, an unsupervised analysis method, Iterative Self-Organizing Data Analysis Technique Algorithm (ISODATA), was applied to analyze the temporal evolution of ischemic damage in a focal embolic cerebral ischemia model in rat with and without recombinant tissue plasminogen activator (rt-PA) treatment. Male Wistar rats subjected to embolic stroke were investigated using a 7-T MRI system. Rats were randomized into control (n=9) and treated (n=9) groups. The treated rats received rt-PA via a femoral vein at 4 h after onset of embolic ischemia. ISODATA analysis employed parametric maps or weighted images (T1, T2, and diffusion). ISODATA results with parametric maps are superior to ISODATA with weighted images, and both of them were highly correlated with the infarction size measured from the corresponding histological section. At 24 h after embolic stroke, the average map ISODATA lesion sizes were 37.7+/-7.0 and 39.2+/-5.6 mm2 for the treated and the control group, respectively. Average histological infarction areas were 37.9+/-7.4 mm2 for treated rats and 39.4+/-6.1 mm2 for controls. The R2 values of the linear correlation between map ISODATA and histological data were 0.98 and 0.96 for treated and control rats, respectively. Both histological and map ISODATA data suggest that there is no significant difference in infarction area between non-treated and rt-PA-treated rats when treatment was administered 4 h after the onset of embolic stroke. The ISODATA lesion size analysis was also sensitive to changes of lesion size during acute and subacute stages of stroke. Our data demonstrate that the multiparameter map ISODATA approach provides a more sensitive quantitation of the ischemic lesion at all time points than image ISODATA and single MRI parametric analysis using T1, T2 or ADCw.

Segmentation of magnetic resonance brain images through discriminant analysis

Segmentation (tissue classification) of medical images obtained from a magnetic resonance (MR) system is a primary step in most applications of medical image post-processing. This paper describes nonparametric discriminant analysis methods to segment multispectral MR images of the brain. Starting from routinely available spin-lattice relaxation time, spin-spin relaxation time, and proton density weighted images (T1w, T2w, PDw), the proposed family of statistical methods is based on: (i) a transform of the images into components that are statistically independent from each other; (ii) a nonparametric estimate of probability density functions of each tissue starting from a training set; (iii) a classic Bayes 0-1 classification rule. Experiments based on a computer built brain phantom (brainweb) and on eight real patient data sets are shown. A comparison with parametric discriminant analysis is also reported. The capability of nonparametric discriminant analysis in improving brain tissue classification of parametric methods is demonstrated. Finally, an assessment of the role of multispectrality in classifying brain tissues is discussed.