The aim of this paper is to present a functional analysis of a diffusion tensor tract statistics (FADTTS) pipeline for delineating the association between multiple diffusion properties along major white matter fiber bundles with a set of covariates of interest, such as age, diagnostic status and gender, and the structure of the variability of these white matter tract properties in various diffusion tensor imaging studies. The FADTTS integrates five statistical tools: (i) a multivariate varying coefficient model for allowing the varying coefficient functions in terms of arc length to characterize the varying associations between fiber bundle diffusion properties and a set of covariates, (ii) a weighted least squares estimation of the varying coefficient functions, (iii) a functional principal component analysis to delineate the structure of the variability in fiber bundle diffusion properties, (iv) a global test statistic to test hypotheses of interest, and (v) a simultaneous confidence band to quantify the uncertainty in the estimated coefficient functions. Simulated data are used to evaluate the finite sample performance of FADTTS. We apply FADTTS to investigate the development of white matter diffusivities along the splenium of the corpus callosum tract and the right internal capsule tract in a clinical study of neurodevelopment. FADTTS can be used to facilitate the understanding of normal brain development, the neural bases of neuropsychiatric disorders, and the joint effects of environmental and genetic factors on white matter fiber bundles. The advantages of FADTTS compared with the other existing approaches are that they are capable of modeling the structured inter-subject variability, testing the joint effects, and constructing their simultaneous confidence bands. However, FADTTS is not crucial for estimation and reduces to the functional analysis method for the single measure.

We introduce a labeled point set registration algorithm based on a family of novel information-theoretic measures derived as a generalization of the well-known Shannon entropy. This generalization, known as the Havrda–Charvat–Tsallis entropy, permits a fine-tuning between solution types of varying degrees of robustness of the divergence measure between multiple point sets. A variant of the traditional free-form deformation approach, known as directly manipulated free-form deformation, is used to model the transformation of the registration solution. We provide an overview of its open source implementation based on the Insight Toolkit of the National Institutes of Health. Characterization of the proposed framework includes comparison with other state of the art kernel-based methods and demonstration of its utility for lung registration via labeled point set representation of lung anatomy.

The acquisition of high-quality magnetic resonance (MR) images of neonatal brains is largely hampered by their characteristically small head size and insufficient tissue contrast. As a result, subsequent image processing and analysis, especially brain tissue segmentation, are often affected. To overcome this problem, a dedicated phased array neonatal head coil is utilized to improve MR image quality by augmenting signal-tonoise ratio and spatial resolution without lengthening data acquisition time. In addition, a specialized hybrid atlas-based tissue segmentation algorithm is developed for the delineation of fine structures in the acquired neonatal brain MR images. The proposed tissue segmentation method first enhances the sheet-like cortical gray matter (GM) structures in the to-be-segmented neonatal image with a Hessian filter for generation of a cortical GM confidence map. A neonatal population atlas is then generated by averaging the presegmented images of a population, weighted by their cortical GM similarity with respect to the to-be-segmented image. Finally, the neonatal population atlas is combined with the GM confidence map, and the resulting enhanced tissue probability maps for each tissue form a hybrid atlas is used for atlas-based segmentation. Various experiments are conducted to compare the segmentations of the proposed method with manual segmentation (on both images acquired with a dedicated phased array coil and a conventional volume coil), as well as with the segmentations of two population-atlas-based methods. Results show the proposed method is capable of segmenting the neonatal brain with the best accuracy, and also preserving the most structural details in the cortical regions. Hum BrainMapp 32:382–396, 2011.

Automated neural circuit reconstruction through electron microscopy (EM) images is a challenging problem. In this paper, we present a novel method that exploits multi-scale contextual information together with Radon-like features (RLF) to learn a series of discriminative models. The main idea is to build a framework which is capable of extracting information about cell membranes from a large contextual area of an EM image in a computationally efficient way. Toward this goal, we extract RLF that can be computed efficiently from the input image and generate a scale-space representation of the context images that are obtained at the output of each discriminative model in the series. Compared to a single-scale model, the use of a multi-scale representation of the context image gives the subsequent classifiers access to a larger contextual area in an effective way. Our strategy is general and independent of the classifier and has the potential to be used in any context based framework. We demonstrate that our method outperforms the state-of-the- art algorithms in detection of neuron membranes in EM images.

In this paper, a new AdaBoost learning framework, called WNS-AdaBoost, is proposed for training discriminative models. The proposed approach significantly speeds up the learning process of adaptive boosting (AdaBoost) by reducing the number of data points. For this purpose, we introduce the weighted novelty selection (WNS) sampling strategy and combine it with AdaBoost to obtain an efficient and fast learning algorithm. WNS selects a representative subset of data thereby reducing the number of data points onto which AdaBoost is applied. In addition, WNS associates a weight with each selected data point such that the weighted subset approximates the distribution of all the training data. This ensures that AdaBoost can trained efficiently and with minimal loss of accuracy. The performance of WNS-AdaBoost is first demonstrated in a classification task. Then, WNS is employed in a probabilistic boosting-tree (PBT) structure for image segmentation. Results in these two applications show that the training time using WNS-AdaBoost is greatly reduced at the cost of only a few percent in accuracy.

Contextual information plays an important role in solving high-level vision problems and has been used widely in the ¯eld. However, using contextual information in an e®ective way remains a di±cult problem. To address this challenge, we propose a novel framework which utilizes context information in a multi-scale structure for learning discriminative models. We apply a series of linear ¯lters to the context image consecutively to create a scale space representation. The main idea is to take the advantage of the context image at di®erent scales instead of a single scale giving the classi¯er access to a larger contextual area. Moreover, ¯nest scale context information can be noisy while a scale space structure is more robust against noise, so our proposed method improves robustness as well as accuracy. In this framework, the improvements in accuracy between consecutive classi¯ers in a series architecture are larger and convergence is faster. Our strategy is general and independent of the classi¯er type. In other words, it has the potential to be used in any context based framework. We demonstrate performance of the algorithm on two challenging visual recognition tasks: image parsing and texture segmentation. With nearly same computational complexity our model outperforms the state of the art algorithms.

Centerline extraction is widely used in medical image processing. It can benefit applications such as building the connectivity map of neurons from microscopic images as well as examining retina vessels for preventing blindness. Many methods have been developed to extract centerlines from 2- D images. An algorithm based on 2-D rapid tensor voting is proposed in this paper. This method uses the Canny edge detector and a simple ridge finding algorithm to roughly extract centerlines, which is fast, does not require any seeds and allows the object to be disconnected. Then efficient 2-D tensor voting is applied to enhance the centerline, which can rapidly bridge the gaps caused by the earlier step and reject artifacts due to noise. We demonstrate the robustness of the algorithm and compare with existing methods. The result shows good computational efficiency as well as accuracy.

The degree of white matter (WM) myelination is rather inhomogeneous across the brain. As a consequence, white matter appears differently across the cortical lobes in MR images acquired during early postnatal development. At 1 year old specifically, the gray/white matter contrast of MR images in prefrontal and temporal lobes is limited and thus tissue segmentation results show commonly reduce accuracy in these lobes. In this novel work, we propose the use of spatial intensity growth maps (IGM) for T1 and T2 weighted image to compensate for local appearance inhomogeneity. The IGM captures expected intensity changes from 1 to 2 years of age, as appearance inhomogeneity is highly reduced by the age of 24 months. For that purpose, we employ MRI data from a large dataset of longitudinal (12 and 24 month old subjects) MR study of Autism. The IGM creation is based on automatically co-registered images at 12 months, corresponding registered 24 months images, and a final registration of all image to a prior average template. In template space, voxelwise correspondence is thus achieved and the IGM is computed as the coefficient of a voxelwise linear regression model between corresponding intensities at 1-year and 2-years. The proposed IGM shows low regression values of 1-10% in GM and CSF regions, as well as in WM regions at advanced stage of myelination at 1-year. However, in the prefrontal and temporal lobe we observed regression values of 20-25%, indicating that the IGM appropriately captures the expected large intensity change in these lobes due to myelination.The IGM is applied to cross-sectional MRI datasets of 1-year old subjects via registration, correction and tissue segmentation of the corrected dataset. We validated our approach in a small study of images with known, manual ”ground truth” segmentations. We furthermore present an EM-like optimization of adapting existing non-optimal prior atlas probability maps to fit known expert rater segmentations.