volBrain: An Online MRI Brain Volumetry System

The amount of medical image data produced in clinical and research settings is rapidly growing resulting in vast amount of data to analyze. Automatic and reliable quantitative analysis tools, including segmentation, allow to analyze brain development and to understand specific patterns of many neurological diseases. This field has recently experienced many advances with successful techniques based on non-linear warping and label fusion. In this work we present a novel and fully automatic pipeline for volumetric brain analysis based on multi-atlas label fusion technology that is able to provide accurate volumetric information at different levels of detail in a short time. This method is available through the volBrain online web interface (http://volbrain.upv.es), which is publically and freely accessible to the scientific community. Our new framework has been compared with current state-of-the-art methods showing very competitive results.

Granular computing: perspectives and challenges

Granular computing, as a new and rapidly growing paradigm of information processing, has attracted many researchers and practitioners. Granular computing is an umbrella term to cover any theories, methodologies, techniques, and tools that make use of information granules in complex problem solving. The aim of this paper is to review foundations and schools of research and to elaborate on current developments in granular computing research. We first review some basic notions of granular computing. Classification and descriptions of various schools of research in granular computing are given. We also present and identify some research directions in granular computing.

Cerebral Contour Extraction with Particle Method in Neonatal MR Images

Cerebral surface extraction from neonatal MR images is the basic work of quantifying the deformation of the cerebrum. Although there are many conventional methods of segmenting the cerebral region, only the rough area is given by counting the number of surface voxels in the segmented region. This article proposes a new method of extraction that is based on the particle method. The method introduces three kinds of particles that correspond to cerebrospinal fluid, gray matter, and white matter; it converts the brain MR images into the set of particles. The proposed method was applied to neonatal magnetic resonance images, and the experimental results showed that the cerebral contour was extracted with a root-mean-square-error of 0.51 mm compared with the ground truth contour given by a physician.

Automatic cerebral and cerebellar hemisphere segmentation in 3D MRI: adaptive disconnection algorithm

This paper describes the automatic Adaptive Disconnection method to segment cerebral and cerebellar hemispheres of human brain in three-dimensional magnetic resonance imaging (MRI). Using the partial differential equations based shape bottlenecks algorithm cooperating with an information potential value clustering process, it detects and cuts, first, the compartmental connections between the cerebrum, the cerebellum and the brainstem in the white matter domain, and then, the interhemispheric connections of the extracted cerebrum and cerebellum volumes. As long as the subject orientation in the scanner is given, the variations in subject location and normal brain morphology in different images are accommodated automatically, thus no stereotaxic image registration is required. The modeling of partial volume effect is used to locate cerebrum, cerebellum and brainstem boundaries, and make the interhemispheric connections detectable. The Adaptive Disconnection method was tested with 10 simulated images from the BrainWeb database and 39 clinical images from the LONI Probabilistic Brain Atlas database. It obtained lower error rates than a traditional shape bottlenecks algorithm based segmentation technique (BrainVisa) and linear and nonlinear registration based brain hemisphere segmentation methods. Segmentation accuracies were evaluated against manual segmentations. The Adaptive Disconnection method was also confirmed not to be sensitive to the noise and intensity non-uniformity in the images. We also applied the Adaptive Disconnection method to clinical images of 22 healthy controls and 18 patients with schizophrenia. A preliminary cerebral volumetric asymmetry analysis based on these images demonstrated that the Adaptive Disconnection method is applicable to study abnormal brain asymmetry in schizophrenia.

Accurate and robust extraction of brain regions using a deformable model based on radial basis functions

Brain extraction from head magnetic resonance (MR) images is a classification problem of segmenting image volumes into brain and non-brain regions. It is a difficult task due to the convoluted brain surface and the inapparent brain/non-brain boundaries in images. This paper presents an automated, robust, and accurate brain extraction method which utilizes a new implicit deformable model to well represent brain contours and to segment brain regions from MR images. This model is described by a set of Wendland's radial basis functions (RBFs) and has the advantages of compact support property and low computational complexity. Driven by the internal force for imposing the smoothness constraint and the external force for considering the intensity contrast across boundaries, the deformable model of a brain contour can efficiently evolve from its initial state toward its target by iteratively updating the RBF locations. In the proposed method, brain contours are separately determined on 2D coronal and sagittal slices. The results from these two views are generally complementary and are thus integrated to obtain a complete 3D brain volume. The proposed method was compared to four existing methods, Brain Surface Extractor, Brain Extraction Tool, Hybrid Watershed Algorithm, and Model-based Level Set, by using two sets of MR images as well as manual segmentation results obtained from the Internet Brain Segmentation Repository. Our experimental results demonstrated that the proposed approach outperformed these four methods when jointly considering extraction accuracy and robustness.

Automatic compartmental decomposition for 3D MR images of human brain

A new method is developed to automatically decompose human brain MR images into cerebrum, cerebellum and brainstem. It utilizes the partial differential equations based shape bottlenecks algorithm to segment an interior brain tissue region into three compartmental seeds. Then the compartmental decomposition is obtained by reconstructing the compartments from the seeds according to the compartment boundary knowledge defined with partial volume information. This method was validated against manual segmentations of 35 T1-weighted MR images. It was demonstrated to be accurate and robust, and the mean Dice coefficients for cerebrum, cerebellum and brainstem were 0.99, 0.98 and 0.82, respectively.

Interactive segmentation of the cerebral lobes with fuzzy inference in 3T MR images

Measurement of volume and surface area of the frontal, parietal, temporal and occipital lobes from magnetic resonance (MR) images shows promise as a method for use in diagnosis of dementia. This article presents a novel computer-aided system for automatically segmenting the cerebral lobes from 3T human brain MR images. Until now, the anatomical definition of cerebral lobes on the cerebral cortex is somewhat vague for use in automatic delineation of boundary lines, and there is no definition of cerebral lobes in the interior of the cerebrum. Therefore, we have developed a new method for defining cerebral lobes on the cerebral cortex and in the interior of the cerebrum. The proposed method determines the boundaries between the lobes by deforming initial surfaces. The initial surfaces are automatically determined based on user-given landmarks. They are smoothed and deformed so that the deforming boundaries run along the hourglass portion of the three-dimensional shape of the cerebrum with fuzzy rule-based active contour and surface models. The cerebrum is divided into the cerebral lobes according to the boundaries determined using this method. The reproducibility of our system with a given subject was assessed by examining the variability of volume and surface area in three healthy subjects, with measurements performed by three beginners and one expert user. The experimental results show that our system segments the cerebral lobes with high reproducibility.

Transcranial ultrasonography system for visualizing skull and brain surface aided by fuzzy expert system

A conventional ultrasonography system can noninvasively provide human tissue and blood flow velocity information with real-time processing. In general, since the human skull prevents the disclosure of brain anatomy, we usually placed the sensor at the anterior and superior attachment site of the upper ear (the posterior temporal window) in adults. Due to this limitation, the conventional system cannot obtain transcranial information from arbitrary places in the skull. This paper describes a transcranial sonography system that can visualize the shape of the skull and brain surface from any point to examine skull fracture and brain disease such as cerebral atrophy and epidural or subdural hematoma. In this system, we develop anatomical knowledge of the human head, and we employ fuzzy inference to determine the skull and brain surface. To evaluate our method, three models are applied: the phantom model, the animal model with soft tissue, and the animal model with brain tissue. In all models, the shapes of the skull and the brain tissue surface are successfully determined. Next, the method is applied to two adults. As a result, we have determined the skin surface, skull surface, skull bottom, and brain tissue surface for the subjects' foreheads. Consequently, our system can provide the skull and brain surface information using three-dimensional shapes.

Analysis and validation of automated skull stripping tools: a validation study based on 296 MR images from the Honolulu Asia aging study

As population-based epidemiologic studies may acquire images from thousands of subjects, automated image post-processing is needed. However, error in these methods may be biased and related to subject characteristics relevant to the research question. Here, we compare two automated methods of brain extraction against manually segmented images and evaluate whether method accuracy is associated with subject demographic and health characteristics. MRI data (n = 296) are from the Honolulu Asia Aging Study, a population-based study of elderly Japanese-American men. The intracranial space was manually outlined on the axial proton density sequence by a single operator. The brain was extracted automatically using BET (Brain Extraction Tool) and BSE (Brain Surface Extractor) on axial proton density images. Total intracranial volume was calculated for the manually segmented images (ticvM), the BET segmented images (ticvBET) and the BSE segmented images (ticvBSE). Mean ticvBSE was closer to that of ticvM, but ticvBET was more highly correlated with ticvM than ticvBSE. BSE had significant over (positive error) and underestimated (negative error) ticv, but net error was relatively low. BET had large positive and very low negative error. Method accuracy, measured in percent positive and negative error, varied slightly with age, head circumference, presence of the apolipoprotein eepsilon4 polymorphism, subcortical and cortical infracts and enlarged ventricles. This epidemiologic approach to the assessment of potential bias in image post-processing tasks shows both skull-stripping programs performed well in this large image dataset when compared to manually segmented images. Although method accuracy was statistically associated with some subject characteristics, the extent of the misclassification (in terms of percent of brain volume) was small.

Adaptive model initialization and deformation for automatic segmentation of T1-weighted brain MRI data

A fully automatic, two-step, T1-weighted brain magnetic resonance imaging (MRI) segmentation method is presented. A preliminary mask of parenchyma is first estimated through adaptive image intensity analysis and mathematical morphological operations. It serves as the initial model and probability reference for a level-set algorithm in the second step, which finalizes the segmentation based on both image intensity and geometric information. The Dice coefficient and Euclidean distance between boundaries of automatic results and the corresponding references are reported for both phantom and clinical MR data. For the 28 patient scans acquired at our institution, the average Dice coefficient was 98.2% and the mean Euclidean surface distance measure was 0.074 mm. The entire segmentation for either a simulated or a clinical image volume finishes within 2 min on a modern PC system. The accuracy and speed of this technique allow us to automatically create patient-specific finite element models within the operating room on a timely basis for application in image-guided updating of preoperative scans.

Putting our heads together: a consensus approach to brain/non-brain segmentation in T1-weighted MR volumes

We describe an approach to brain extraction from T1-weighted MR volumes that uses a hierarchy of masks created by different models to form a consensus mask. The algorithm (McStrip) incorporates atlas-based extraction via nonlinear warping, intensity-threshold masking with connectivity constraints, and edge-based masking with morphological operations. Volume and boundary metrics were computed to evaluate the reproducibility and accuracy of McStrip against manual brain extraction on 38 scans from normal and ataxic subjects. McStrip masks were reproducible across six repeat scans of a normal subject and were significantly more accurate than the masks produced by any of the individual algorithmic components.

Controlling for premorbid brain size in imaging studies: T1-derived cranium scaling factor vs. T2-derived intracranial vault volume

Intracranial vault (ICV) volume, obtained from T2-weighted magnetic resonance imaging (MRI), is generally used to estimate premorbid brain size in imaging studies. T1-weighted sequences lack the signal characteristics for ICV measurements [they have poor contrast at the outer boundary of sulcal cranium scaling factor (CSF)] but are valuable in imaging studies due to their excellent gray vs. white matter contrast. Smith et al. [NeuroImage 17 (2002) 479] suggested a T1-derived cranium scaling factor as an alternative control variable for premorbid brain size in cross-sectional studies. This index, which is computed using the SIENAX software, is a scaling factor comparing an individual's skull to a template skull derived from the Montreal Neurological Institute (MNI) average of 152 T1 studies (the MNI152). SIENAX computes coarsely defined estimates for the individual and MNI skulls rather than well-defined volumes. To test how well this approach would work as a control variable for premorbid brain size in cross-sectional studies, we compared the T1-derived cranium scaling factor to T2-derived ICV measurements in a sample of 92 individuals: 39 white males, 22 white females, and 31 African-American males, with an age range of 26-78 years. The correlation between T1- and T2-derived variables was 0.94 and did not differ across subject groups. The T1-derived cranium scaling factor accounted for a statistically significant portion (87%) of the variance of the T2-derived ICV measure and thus is a good surrogate for ICV measurement of premorbid brain size as a reference measure in MRI atrophy studies. Furthermore, neither race, sex, nor age accounted for any additional variance in ICV, indicating that neither race-, gender-, nor age-associated cranial bone thickness effects were present in this data set.

Automated segmentation of human brain MR images using a multi-agent approach

Image interpretation consists in finding a correspondence between radiometric information and symbolic labeling with respect to specific spatial constraints. It is intrinsically a distributed process in terms of goals to be reached, zones in the image to be processed and methods to be applied. To cope the the difficulty inherent in this process, several information processing steps are required to gradually extract information. In this paper we advocate the use of situated cooperative agents as a framework for managing such steps. Dedicated agent behaviors are dynamically adapted depending on their position in the image, of their topographic relationships and of the radiometric information available. The information collected by the agents is gathered, shared via qualitative maps, or used as soon as available by acquaintances. Incremental refinement of interpretation is obtained through a coarse to fine strategy. Our work is essentially focused on radiometry-based tissue interpretation where knowledge is introduced or extracted at several levels to estimate models for tissue-intensity distribution and to cope with noise, intensity non-uniformity and partial volume effect. Several experiments on phantom and real images were performed. A complete volume can be segmented in less than 5 min with about 0.84% accuracy of the segmented reference. Comparison with other techniques demonstrates the potential interest of our approach for magnetic resonance imaging (MRI) brain scan interpretation.