Search

In the present paper, we propose a new pulse measurement methodology based on thermal imaging (contact-free). The method capitalizes both on the thermal undulation produced by the traveling pulse as well as the periodic expansion of the compliant vessel wall. The paper reports experiments on 34 subjects, where it compares the performance of the new pulse measurement method to the one we reported previously. The measurements were ground-truthed through a piezo-electric sensor. Statistical analysis reveals that the new imaging methodology is more accurate and robust than the previous one. Its performance becomes nearly perfect, when the vessel is not obstructed by a thick fat deposit. [ABSTRACT FROM AUTHOR]

This paper presents a model-based technique for lesion detection in colon CT scans that uses analytical shape models to map the local shape curvature at individual voxels to anatomical labels. Local intensity profiles and curvature information have been previously used for discriminating between simple geometric shapes such as spherical and cylindrical structures. This paper introduces novel analytical shape models for colon-specific anatomy, viz. folds and polyps, built by combining parts with simpler geometric shapes. The models better approximate the actual shapes of relevant anatomical structures while allowing the application of model-based analysis on the simpler model parts. All parameters are derived from the analytical models, resulting in a simple voxel labeling scheme for classifying individual voxels in a CT volume. The algorithm's performance is evaluated against expert-determined ground truth on a database of 42 scans and performance is quantified by free-response receiver-operator curves. [ABSTRACT FROM AUTHOR]

Individual white matter fibers cannot be resolved by current magnetic resonance (MR) technology. Many fibers of a fiber bundle will pass through an individual volume element (voxel). Individual visualized fiber tracts are thus the result of interpolation on a relatively coarse voxel grid, and an infinite number of them may be generated in a given volume by interpolation. This paper aims at creating a level set representation of a fiber bundle to describe this apparent continuum of fibers. It further introduces a coordinate system warped to the fiber bundle geometry, allowing for the definition of geometrically meaningful fiber bundle measures. [ABSTRACT FROM AUTHOR]

A Gabor wavelets based method is proposed in this paper for evaluating and tuning the parameters of image registration algorithms. The registration quality is measured by the anatomical variability of the registered images. We propose in this paper a local anatomical structure descriptor, namely the Maximum Responded Gabor Wavelet (MRGW) for such a purpose. The effectiveness of the descriptor is demonstrated through a practical spatial normalization example - the variance of MRGW is successfully applied to tune the parameters of a nonlinear spatial normalization algorithm, which is integrated in one of the most popular software packages for medical image processing - the Statistical Parametric Mapping (SPM). Keywords: 3D Gabor Wavelets, Medical Image Registration. [ABSTRACT FROM AUTHOR]

This paper proposes a novel framework for robust click-point linking: efficient localized registration that allows users to interactively prescribe where the accuracy has to be high. Given a user-specified point in one domain, it estimates a single point-wise correspondence between a data domain pair. In order to link visually dissimilar local regions, we propose a new strategy that robustly establishes such a correspondence using only geometrical relations without comparing the local appearances. The solution is formulated as a maximum likelihood (ML) estimation of a spatial likelihood model without an explicit parameter estimation. The likelihood is modeled by a Gaussian mixture whose component describes geometric context of the click-point relative to pre-computed scale-invariant salient-region features. The local ML estimation was efficiently achieved by using variable-bandwidth mean shift. Two transformation classes of pure translation and scaling/translation are considered in this paper. The feasibility of the proposed approach is evaluated with 16 pairs of whole-body CT data, demonstrating the effectiveness. [ABSTRACT FROM AUTHOR]

This paper presents a novel method for denoising MR images that relies on an optimal estimation, combining a likelihood model with an adaptive image prior. The method models images as random fields and exploits the properties of independent Rician noise to learn the higher-order statistics of image neighborhoods from corrupted input data. It uses these statistics as priors within a Bayesian denoising framework. This paper presents an information-theoretic method for characterizing neighborhood structure using nonparametric density estimation. The formulation generalizes easily to simultaneous denoising of multimodal MRI, exploiting the relationships between modalities to further enhance performance. The method, relying on the information content of input data for noise estimation and setting important parameters, does not require significant parameter tuning. Qualitative and quantitative results on real, simulated, and multimodal data, including comparisons with other approaches, demonstrate the effectiveness of the method. [ABSTRACT FROM AUTHOR]

This paper presents a new registration method called Transitive Inverse-Consistent Manifold Registration (TICMR). The TICMR method jointly estimates correspondence maps between groups of three manifolds embedded in a higher dimensional image space while minimizing inverse consistency and transitivity errors. Registering three manifolds at once provides a means for minimizing the transitivity error which is not possible when registering only two manifolds. TICMR is an iterative method that uses the closest point projection operator to define correspondences between manifolds as they are non-rigidly registered. Examples of the TICMR method are presented for matching groups of three contours and groups of three surfaces. The contour registration is regularized by minimizing the change in bending energy of the curves while the surface registration is regularized by minimizing the change in elastic energy of the surfaces. The notions of inverse consistency error (ICE) and transitivity error (TE) are extended from volume registration to manifold registration by using a closest point projection operator. For the experiments in this paper, the TICMR method reduces the average ICE by 200 times (contour)/ 6 times (surface) and the average TE by 40 times (contour)/ 2-4 times (surface) compared to registering with a curvature constraint alone. Furthermore, the TICMR is shown to avoid some local minimum that are not avoided when registering with a curvature constraint alone. [ABSTRACT FROM AUTHOR]

In this paper a method to extract cerebral arteries from computed tomographic angiography (CTA) is proposed. Since CTA shows both bone and vessels, the examination of vessels is a difficult task. In the upper part of the brain, the arteries of main interest are not close to bone and can be well segmented out by thresholding and simple connected-component analysis. However in the lower part the separation is challenging due to the spatial closeness of bone and vessels and their overlapping intensity distributions. In this paper a CTA volume is partitioned into two sub-volumes according to the spatial relationship between bone and vessels. In the lower sub-volume, the concerning arteries are extracted by tracking the center line and detecting the border on each cross-section. The proposed tracking method can be characterized by the adaptive properties to the case of cerebral arteries in CTA. These properties improve the tracking continuity with less user-interaction. [ABSTRACT FROM AUTHOR]

This paper presents a new shape representation for a special class of 3-D objects. In a generative approach to object modeling inspired by m-reps [15], skeletons of objects are explicitly defined as continuous manifolds and boundaries are derived from the skeleton by a process that involves solving a Poisson PDE with a non-linear boundary condition. This formulation helps satisfy the equality constraints that are imposed on the parameters of the representation by rules of medial geometry. One benefit of the new approach is the ability to represent different instances of an anatomical structure using a common parametrization domain, simplifying the problem of computing correspondences between instances. Another benefit is the ability to continuously parameterize the volumetric region enclosed by the representation's boundary in a one-to-one and onto manner, in a way that preserves two of the three coordinates of the parametrization along vectors normal to the boundary. These two features make the new representation an attractive candidate for statistical analysis of shape and appearance. In this paper, the representation is carefully defined and the results of fitting the hippocampus in a deformable templates framework are presented. [ABSTRACT FROM AUTHOR]

It is widely accepted in the medical community that breast tissue density is an important risk factor for the development of breast cancer. Thus, the development of reliable automatic methods for classification of breast tissue is justified and necessary. Although different approaches in this area have been proposed in recent years, only a few are based on the BIRADS classification standard. In this paper we review different strategies for extracting features in tissue classification systems, and demonstrate, not only the feasibility of estimating breast density using automatic computer vision techniques, but also the benefits of segmentation of the breast based on internal tissue information. The evaluation of the methods is based on the full MIAS database classified according to BIRADS categories, and agreement between automatic and manual classification of 82% was obtained. [ABSTRACT FROM AUTHOR]

This paper introduces a new similarity measure for multi-modal image registration task. The measure is based on the generalized survival exponential entropy (GSEE) and mutual information (GSEE-MI). Since GSEE is estimated from the cumulative distribution function instead of the density function, it is observed that the interpolation artifact is reduced. The method has been tested on four real MR-CT data sets. The experimental results show that the GSEE-MI-based method is more robust than the conventional MI-based method. The accuracy is comparable for both methods. [ABSTRACT FROM AUTHOR]

Retinal vessel segmentation is an essential step of the diagnoses of various eye diseases. In this paper, we propose an automatic, efficient and unsupervised method based on gradient matrix, the normalized cut criterion and tracking strategy. Making use of the gradient matrix of the Lucas-Kanade equation, which consists of only the first order derivatives, the proposed method can detect a candidate window where a vessel possibly exists. The normalized cut criterion, which measures both the similarity within groups and the dissimilarity between groups, is used to search a local intensity threshold to segment the vessel in a candidate window. The tracking strategy makes it possible to extract thin vessels without being corrupted by noise. Using a multi-resolution segmentation scheme, vessels with different widths can be segmented at different resolutions, although the window size is fixed. Our method is tested on a public database. It is demonstrated to be efficient and insensitive to initial parameters. [ABSTRACT FROM AUTHOR]

We present a new method for automatic segmentation of heterogeneous image data, which is very common in medical image analysis. The main contribution of the paper is a mathematical formulation for incorporating soft model assignments into the calculation of affinities, which are traditionally model free. We integrate the resulting model-aware affinities into the multilevel segmentation by weighted aggregation algorithm. We apply the technique to the task of detecting and segmenting brain tumor and edema in multimodal MR volumes. Our results indicate the benefit of incorporating model-aware affinities into the segmentation process for the difficult case of brain tumor. [ABSTRACT FROM AUTHOR]

Ultrasound is a universal guidance tool for many medical procedures, whereas it is of poor image quality and resolution. Merging high-contrast image information from other image modalities enhances the guidance capability of ultrasound. However, few registration methods work well for it. In this paper we present a surface-to-image registration technique for mono- or multimodal medical data concerning ultrasound. This approach is able to automatically register the object surface to its counterpart in image volume. Three similarity measurements are investigated in the rigid registration experiments of the pubic arch in transrectal ultrasound images. It shown that the selection of the similarity function is related to the ultrasound characteristics of the object to be registered. Keywords: Image registration, similarity measure, ultrasound, pubic arch. [ABSTRACT FROM AUTHOR]

In this paper, we present a learning-based method for the detection and segmentation of 3D free-form tubular structures, such as the rectal tubes in CT colonoscopy. This method can be used to reduce the false alarms introduced by rectal tubes in current polyp detection algorithms. The method is hierarchical, detecting parts of the tube in increasing order of complexity, from tube cross sections and tube segments to the whole flexible tube. To increase the speed of the algorithm, candidate parts are generated using a voting strategy. The detected tube segments are combined into a flexible tube using a dynamic programming algorithm. Testing the algorithm on 210 unseen datasets resulted in a tube detection rate of 94.7% and 0.12 false alarms per volume. The method can be easily retrained to detect and segment other tubular 3D structures. [ABSTRACT FROM AUTHOR]

This paper develops a volumetric quantification approach of the airway wall in multi-detector computed tomography (MDCT), exploiting a 3D segmentation methodology based on patient-specific deformable mesh model. A comparative study carried out with respect to a reference 2D/3D surface quantification technique underlines the clinical interest of the proposed approach in assessing airway remodeling in asthmatics and in evaluating the efficiency of therapeutic protocols. [ABSTRACT FROM AUTHOR]

Digital brain atlases can be used in conjuction with magnetic resonance imaging (MRI) and computed tomography (CT) for planning and guidance during neurosurgery. Digital atlases are advantageous since they can be warped nonlinearly to fit each patient's unique anatomy. Functional neurosurgery with implantation of deep brain stimulating (DBS) electrodes requires accurate targeting, and has become a popular surgical technique in Parkinsonian patients. In this paper, we present a method for integrating postoperative data from subthalamic (STN) DBS implantation into an antomical atlas of the basal ganglia and thalamus. The method estimates electrode position from post-operative magnetic resonance imaging (MRI) data. These electrodes are then warped back into the atlas space and are modelled in three dimensions. The average of these models is then taken to show the region where the majority of STN DBS electrodes were implanted. The group with more favorable post-operative results was separated from the group which responded to the STN DBS implantation procedure less favourably to create a probablisitic distribution of DBS in the STN electrodes. [ABSTRACT FROM AUTHOR]

This paper presents a method to improve the semi-automatic method for intensity inhomogeneity correction by Dawant et al. through introducing a fully automatic approach to reference points generation, which is based on order statistics and integrates information from the fine to coarse scale representations of the input image. The method has been validated and compared with two popular methods, N3 and BFC. Advantages of the proposed method are demonstrated. [ABSTRACT FROM AUTHOR]

Traditional techniques for statistical fMRI analysis are often based on thresholding of individual voxel values or averaging voxel values over a region of interest. In this paper we present a mixture-based response-surface technique for extracting and characterizing spatial clusters of activation patterns from fMRI data. Each mixture component models a local cluster of activated voxels with a parametric surface function. A novel aspect of our approach is the use of Bayesian nonparametric methods to automatically select the number of activation clusters in an image. We describe an MCMC sampling method to estimate both parameters for shape features and the number of local activations at the same time, and illustrate the application of the algorithm to a number of different fMRI brain images. [ABSTRACT FROM AUTHOR]

This paper describes a novel approach to in-vivo measurement of brain surface folding in clinically acquired neonatal MR image data, which allows evaluation of surface curvature within subregions of the cortex. This paper addresses two aspects of this problem. Firstly: normalization of folding measures to provide area-independent evaluation of surface folding over arbitrary subregions of the cortex. Secondly: automated parcellation of the cortex at a particular developmental stage, based on an approximate spatial normalization of previously developed anatomical boundaries. The method was applied to seven premature infants (age 28-37 weeks) from which gray matter and gray-white matter interface surfaces were extracted. Experimental results show that previous folding measures are sensitive to the size of the surface of analysis, and that the area independent measures proposed here provide significant improvements. Such a system provides a tool to allow the study of structural development in the neonatal brain within specific functional subregions, which may be critical in identifying later neurological impairment. [ABSTRACT FROM AUTHOR]

In this paper, we present an original method that aims at parcellating the cortical surface in regions functionally meaningful, from individual anatomy. The parcellation is obtained using an anatomically constrained surface-based coordinate system from which we define a complete partition of the surface. The aim of our method is to exhibit a new way to describe the cortical surface organization, in both anatomical and functional terms. The method is described together with results applied to a functional somatotopy experiments. [ABSTRACT FROM AUTHOR]

In this paper, we treat the problem of reducing the false positives (FP) in the automatic detection of colorectal polyps at Computer Aided Detection in Computed Tomography Colonography (CAD-CTC) as a shape-filtering task. From the extracted candidate surface, we obtain a reliable shape distribution function and analyse it in the Fourier domain and use the resulting spectral data to classify the candidate surface as belonging to a polyp or a non-polyp class. The developed shape filtering scheme is computationally efficient (takes approximately 2 seconds per dataset to detect the polyps from the colonic surface) and offers robust polyp detection with an overall false positive rate of 5.44 per dataset at a sensitivity of 100% for polyps greater than 10mm when it was applied to standard and low dose CT data. [ABSTRACT FROM AUTHOR]

In model-based segmentation, automated region identification is achieved via registration of novel data to a pre-determined model. The desired structure is typically generated via manual tracing within this model. When model-based segmentation is applied to human cortical data, problems arise if left-right comparisons are desired. The asymmetry of the human cortex requires that both left and right models of a structure be composed in order to effectively segment the desired structures. Paradoxically, defining a model in both hemi-spheres carries a likelihood of introducing bias to one of the structures. This paper describes a novel technique for creating a symmetric average model in which both hemispheres are equally represented and thus left-right comparison is possible. This work is an extension of that proposed by Guimond et al [1]. Hippocampal segmentation is used as a test-case in a cohort of 118 normal eld-erly subjects and results are compared with expert manual tracing. [ABSTRACT FROM AUTHOR]

One critical issue in the context of image restoration is the problem of noise removal while keeping the integrity of relevant image information. Denoising is a crucial step to increase image conspicuity and to improve the performances of all the processings needed for quantitative imaging analysis. The method proposed in this paper is based on an optimized version of the Non Local (NL) Means algorithm. This approach uses the natural redundancy of information in image to remove the noise. Tests were carried out on synthetic datasets and on real 3T MR images. The results show that the NL-means approach outperforms other classical denoising methods, such as Anisotropic Diffusion Filter and Total Variation. [ABSTRACT FROM AUTHOR]

Segmentation of CSF and pulsative blood flow, based on a single phase contrast MRA (PC-MRA) image can lead to imperfect classifications. In this paper, we present a novel automated flow segmentation method by using PC-MRA image series. The intensity time series of each pixel is modeled as an autoregressive (AR) process and features including the Linear Prediction Coefficients (LPC), covariance matrix of LPC and variance of prediction error are extracted from each profile. Bayesian classification of the feature space is then achieved using a non-Gaussian likelihood probability function and unknown parameters of the likelihood function are estimated by a generalized Expectation-Maximization (EM) algorithm. The efficiency of the method evaluated on both synthetic and real retrospective gated PC-MRA images indicate that robust segmentation of CSF and vessels can be achieved by using this method. [ABSTRACT FROM AUTHOR]

This paper presents an integrated method for adaptive segmentation of brain tissues in three-dimensional (3-D) MRI (Magnetic Resonance Imaging) images. The method intends to do the volume segmentation in a slice-by-slice manner. Firstly, some slices in the volume are segmented using an automatic algorithm composed of watershed, fuzzy clustering (Fuzzy C-Means) and re-segmentation. Then their adjacent slices can be segmented conveniently by propagating the information of them. The information is consisted of watershed lines and thresholds obtained from the re-segmentation approach. This integrated approach yields a robust and precise segmentation. The efficacy of the proposed algorithm is validated using extensive experiments. [ABSTRACT FROM AUTHOR]

A novel method for the segmentation of 4D MR cardiac images is introduced in this paper. The method improves the traditional active shape model method by adopting an 3D spatially hierarchical expression of the shape model, which is used as an internal regulation force during the segmentation process. Generation of the landmarks for constructing the shape model is based on the active surface method itself utilizing the long range image force, gradient vector flow (GVF). For constructing hierarchical statistical shape models, initial landmarking is done on a manually segmented training set with different spatial resolutions. Principal component analysis is then used to derive the hierarchical expression of the shape model. Experimental results for 4D MR cardiac image segmentation are presented. [ABSTRACT FROM AUTHOR]

Acute aortic dissection is a life-threatening condition and must be diagnosed and treated promptly. For treatment planning the reliable identification of the true and false lumen is crucial. However, a fully automatic Computer Aided Diagnosis system capable to display the different lumens in an easily comprehensible and timely manner is still not available. In this paper we present a method that segments the entire aorta and then identifies the two lumens separated by the dissection membrane. The algorithm misdetected part of the membrane in only one of the 15 cases tested, where the aorta has not been significantly altered by the presence of aneurisms. [ABSTRACT FROM AUTHOR]

In this paper, a novel three-dimensional registration method for Magnetic Resonance Image (MRI) and Paxinos-Watson Atlas of rat brain involving 3D affine transformations is proposed. For the purpose of adapting to a large range of transform parameters in a high registration accuracy, the registration procedure includes two steps: a principle components analysis (PCA) based coarse registration and a Hausdorff distance based fine registration. Both steps are free from the correspondence of the feature points of MRI and Atlas. We implemented this registration method in a rat brain 3D reconstruction and analysis system. Experiments have demonstrated that this two-step method can be successfully applied to registering the low resolution and noise affection MRI with Paxinos-Watson Atlas of rat brain. Keywords: principle component analysis(PCA), Hausdorff distance, image registration, 3D reconstruction. [ABSTRACT FROM AUTHOR]

In this paper, a 3D US imaging system for the guidance of RF ablation of uterine adenoma and uterine bleeding was developed to increase the operation success by accurate localization of the tumor position during treatment. A rotational scanning using an abdominal probe was employed. To reduce the distortion produced when the rotational axis is not collinear with the central beam of the probe, a new 3D reconstruction algorithm using 360° scanning is derived. Then, a fast 3D needle segmentation algorithm is used to find the electrode direction and determine the tip of electrode. Experiments with a water phantom demonstrated the feasibility of our 3D US image based guidance system. [ABSTRACT FROM AUTHOR]

It has long been recognized that one of the most difficult steps of intramedullary nailing of femoral shaft fractures is distal locking - the insertion of distal transverse interlocking screws, for which it is necessary to know the positions and orientations of the distal locking holes of the intramedullary nail. This paper presents a constrained optimization approach for solving this problem using single calibrated fluoroscopic image. The problem is formulated as a sequential two-stage model-based optimal fitting process. The first stage, nail axis determination, automatically estimates the axis of the distal part of the IMN through a constrained optimization. The second stage, pose recovery of DLHs, resolves the translation and rotation of the distal locking holes around the estimated axis by iteratively fitting the geometrical models of the DLHs to the image. We report the results of our in-vitro experiments, which demonstrate promising accuracy of the present approach. Keywords: Fluoroscopic X-ray, pose estimation, constrained optimization, computer-assisted intramedullary nailing. [ABSTRACT FROM AUTHOR]

This paper addresses a real-time haptic and graphic simulation system that allows a user to grasp the internal structure of a volumetric deformable object by touching and feeling. We have earlier proposed a voxel-based representation of an object for real-time haptic and graphic interaction. Although, the model may explain satisfactorily how to compute the feedback force and the haptic behavior using it is quite satisfactory, it is not intuitive. To make a better association and to resolve the confusion, this paper introduces another model using the force-voltage analogy concept. We construct a palpation simulator prototype where a selected target is a volumetric human liver. We conduct experiments and human factor study to evaluate the performance of the proposed model. Through the experiments and human factor studies, we verified that our model generated realistic feedback force and novices can easily access abnormal portions from the normal portions of the human liver. Keywords: Palpation, Modeling, Haptic, Virtual Reality. [ABSTRACT FROM AUTHOR]

Liver Perfusion gives important information about blood supply of liver. However, in daily clinical diagnosis, radiologists have to manually mark the perfusion position in time-sequence images due to the motion of liver caused by respiration. In this paper, we propose a novel hybrid method using a variation of active contours and modified chamfer matching to automatically detect the liver perfusion position and measure the intensity with a single shape prior. The experiment is taken on abdomen MRI series and the result reveals that after extracting liver's rough boundary by active contours, precise perfusion positions can be detected by the modified chamfer matching algorithm, and finally a refined intensity curve without respiration affection can be achieved. [ABSTRACT FROM AUTHOR]

A main focus of statistical shape analysis is the description of variability of a population of geometric objects. In this paper, we present work in progress towards modeling the shape and pose variability of sets of multiple objects. Principal geodesic analysis (PGA) is the extension of the standard technique of principal component analysis (PCA) into the nonlinear Riemannian symmetric space of pose and our medial m-rep shape description, a space in which use of PCA would be incorrect. In this paper, we discuss the decoupling of pose and shape in multi-object sets using different normalization settings. Further, we introduce new methods of describing the statistics of object pose using a novel extension of PGA, which previously has been used for global shape statistics. These new pose statistics are then combined with shape statistics to form a more complete description of multi-object complexes. We demonstrate our methods in an application to a longitudinal pediatric autism study with object sets of 10 subcortical structures in a population of 20 subjects. The results show that global scale accounts for most of the major mode of variation across time. Furthermore, the PGA components and the corresponding distribution of different subject groups vary significantly depending on the choice of normalization, which illustrates the importance of global and local pose alignment in multi-object shape analysis. [ABSTRACT FROM AUTHOR]

Ground Glass Opacity (GGO) is defined as hazy increased attenuation within a lung that is not associated with obscured underlying vessels. Since pure (nonsolid) or mixed (partially solid) GGO at the thin-section CT are more likely to be malignant than those with solid opacity, early detection and treatment of GGO can improve a prognosis of lung cancer. However, due to indistinct boundaries and inter- or intra-observer variation, consistent manual detection and segmentation of GGO have proved to be problematic. In this paper, we propose a novel method for automatic detection and segmentation of GGO from chest CT images. For GGO detection, we develop a classifier by boosting k-NN, whose distance measure is the Euclidean distance between the nonparametric density estimates of two examples. The detected GGO region is then automatically segmented by analyzing the texture likelihood map of the region. We applied our method to clinical chest CT volumes containing 10 GGO nodules. The proposed method detected all of the 10 nodules with only one false positive nodule. We also present the statistical validation of the proposed classifier for GGO detection as well as very promising results for automatic GGO segmentation. The proposed method provides a new powerful tool for automatic detection as well as accurate and reproducible segmentation of GGO. [ABSTRACT FROM AUTHOR]

The process of constructing an atlas typically involves selecting one individual from a sample on which to base or root the atlas. If the individual selected is far from the population mean, then the resulting atlas is biased towards this individual. This, in turn, can bias any inferences made with the atlas. Unbiased atlas construction addresses this issue by either basing the atlas on the individual which is the median of the sample or by an iterative technique whereby the atlas converges to the unknown population mean. In this paper, we explore the question of whether a single atlas is appropriate for a given sample or whether there is sufficient image based evidence from which we can infer multiple atlases, each constructed from a subset of the data. We refer to this process as atlas stratification. Essentially, we determine whether the sample, and hence the population, is multi-modal and is best represented by an atlas per mode. We use the mean shift algorithm to identify the modes of the sample and multidimensional scaling to visualize the clustering process. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of creating probabilistic brain atlases from manually labeled training data. We propose a general mesh-based atlas representation, and compare different atlas models by evaluating their posterior probabilities and the posterior probabilities of their parameters. Using such a Baysian framework, we show that the widely used "average" brain atlases constitute relatively poor priors, partly because they tend to overfit the training data, and partly because they do not allow to align corresponding anatomical features across datasets. We also demonstrate that much more powerful representations can be built using content-adaptive meshes that incorporate non-rigid deformation field models. We believe extracting optimal prior probability distributions from training data is crucial in light of the central role priors play in many automated brain MRI analysis techniques. [ABSTRACT FROM AUTHOR]

This paper presents an outlier immune 3D active shape models framework for robust volumetric segmentation of the carotid artery required for accurate plaque burden assessment. In the proposed technique, outlier handling is based on a shape metric that is invariant to scaling, rotation and translation by using the ratio of inter-landmark distances as a local shape dissimilarity measure. Tolerance intervals for each descriptor are calculated from the training samples and used to infer the validity of landmarks. The identified outliers are corrected prior to the model fitting using the ratios distributions and appearance information. To improve the feature point search, the method exploits the geometrical knowledge from the outlier analysis at the previous iteration to weight the gray level appearance based fitness measure. A combined intensity-phase feature point search is also introduced which significantly limits the presence of outliers and improves the overall search accuracy. Both numerical and in vivo assessments of the method involving volumetric segmentation of the carotid artery have shown that the outlier handling technique is capable of handling a significant presence of outliers independently of the amplitudes. [ABSTRACT FROM AUTHOR]

We are working to develop beating-heart atrial septal defect (ASD) closure techniques using real-time 3-D ultrasound guidance. The major image processing challenges are the low image quality and the high frame rate. This paper presents comparative results for ASD tracking in sequences of 3D cardiac ultrasound. We introduce a block flow technique, which combines the velocity computation from optical flow for an entire block with template matching. Enforcing similarity constraints to both the previous and first frames ensures optimal and unique solutions. We compare the performance of the proposed algorithm with that of block matching and optical flow on six in-vivo 4D datasets acquired from porcine beating-heart procedures. Results show that our technique is more stable and has higher sensitivity than both optical flow and block matching in tracking ASDs. Computing velocity at the block level, our technique is much faster than optical flow and comparable in computation cost to block matching. [ABSTRACT FROM AUTHOR]

In this paper, we present a left atrium registration system which utilizes a 3D intra-cardiac ultrasound catheter for faster (more than 700 times) and higher quality surface registration point collection than current systems and eventually improves the registration accuracy and stability. With better registration our system can greatly improve the ablation catheter navigation system which is being used in many hospitals to guide left atrium endocardium ablation procedure. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new visualization technique for virtual colonoscopy (VC). The proposed method is called Virtual Fly-Over, which splits the entire colon anatomy into exactly two halves. Then, it assigns a virtual camera to each half to perform fly-over navigation, which has several advantages over both traditional fly-through and related methods. First, by controlling the elevation of the camera, there is no restriction on its field of view (FOV) angle (e.g., >90o) to maximize visualized surface areas, and hence no perspective distortion. Second, the camera viewing volume is perpendicular to each colon half, so potential polyps that are hidden behind haustral folds are easily found. Finally, because the orientation of the splitting surface is controllable, the navigation can be repeated at a different split orientation to overcome the problem of having a polyp that is divided between the two halves of the colon. Quantitative experimental results on 15 clinical datasets have shown that the average surface visibility coverage is 99.59±0.2%. [ABSTRACT FROM AUTHOR]

Workflow recovery is crucial for designing context-sensitive service systems in future operating rooms. Abstract knowledge about actions which are being performed is particularly valuable in the OR. This knowledge can be used for many applications such as optimizing the workflow, recovering average workflows for guiding and evaluating training surgeons, automatic report generation and ultimately for monitoring in a context aware operating room. This paper describes a novel way for automatic recovery of the surgical workflow. Our algorithms perform this task without an implicit or explicit model of the surgery. This is achieved by the synchronization of multidimensional state vectors of signals recorded in different operations of the same type. We use an enhanced version of the dynamic time warp algorithm to calculate the temporal registration. The algorithms have been tested on 17 signals of six different surgeries of the same type. The results on this dataset are very promising because the algorithms register the steps in the surgery correctly up to seconds, which is our sampling rate. Our software visualizes the temporal registration by displaying the videos of different surgeries of the same type with varying duration precisely synchronized to each other. The synchronized videos of one surgery are either slowed down or speeded up in order to show the same steps as the ones presented in the videos of the other surgery. [ABSTRACT FROM AUTHOR]

The idea of in-situ visualization for surgical procedures has been widely discussed in the community [1,2,3,4]. While the tracking technology offers nowadays a sufficient accuracy and visualization devices have been developed that fit seamlessly into the operational workflow [1,3], one crucial problem remains, which has been discussed already in the first paper on medical augmented reality [4]. Even though the data is presented at the correct place, the physician often perceives the spatial position of the visualization to be closer or further because of virtual/real overlay. This paper describes and evaluates novel visualization techniques that are designed to overcome misleading depth perception of trivially superimposed virtual images on the real view. We have invited 20 surgeons to evaluate seven different visualization techniques using a head mounted display (HMD). The evaluation has been divided into two parts. In the first part, the depth perception of each kind of visualization is evaluated quantitatively. In the second part, the visualizations are evaluated qualitatively in regard to user friendliness and intuitiveness. This evaluation with a relevant number of surgeons using a state-of-the-art system is meant to guide future research and development on medical augmented reality. [ABSTRACT FROM AUTHOR]

Estimation of the system parameters, given noisy input/output data, is a major field in control and signal processing. Many different estimation methods have been proposed in recent years. Among various methods, Extended Kalman Filtering (EKF) is very useful for estimating the parameters of a nonlinear and time-varying system. Moreover, it can remove the effects of noises to achieve significantly improved results. Our task here is to estimate the coefficients in a spring-beam-damper needle steering model. This kind of spring-damper model has been adopted by many researchers in studying the tissue deformation. One difficulty in using such model is to estimate the spring and damper coefficients. Here, we proposed an online parameter estimator using EKF to solve this problem. The detailed design is presented in this paper. Computer simulations and physical experiments have revealed that the simulator can estimate the parameters accurately with fast convergent speed and improve the model efficacy. Keywords: Online parameter estimation, spring/damper model, EKF. [ABSTRACT FROM AUTHOR]

Modeling the deflection of flexible needles is an essential part of needle insertion simulation and path planning. In this paper, three models are compared in terms of accuracy in simulating the bending of a prostate brachytherapy needle. The first two utilize the finite element method, one using geometric non-linearity and triangular plane elements, the other using non-linear beam elements. The third model uses angular springs to model cantilever deflection. The simulations are compared with the experimental bent needle configurations. The models are assessed in terms of geometric conformity using independently identified and pre-identified model parameters. The results show that the angular spring model, which is also the simplest, simulates the needle more accurately than the others. [ABSTRACT FROM AUTHOR]

In this paper, we present a comprehensive framework to detect morphological changes in skull vaults of adolescent idiopathic scoliosis girls. To our knowledge, this is the first attempt to use a combination of medical knowledge, image analysis techniques, statistical learning tools, and scientific visualization methods to detect skull morphological changes. The shape analysis starts from a reliable 3-D segmentation of the skull using thresholding and math-morphological operations. The gradient vector flow is used to model the skull vault surface, which is followed by a spherically uniform sampling. The scale-normalized distances from the shape centroid to sample points are defined as the features. The most discriminative features are selected using recursive feature elimination for support vector machine. The results of this study specify the skull vault surface changes and shed light on building the evidence of bone formation abnormality in AIS girls. [ABSTRACT FROM AUTHOR]

A variety of different methods of finding correspondences across sets of images to build statistical shape models have been proposed, each of which is likely to result in a different model. When dealing with large datasets (particularly in 3D), it is difficult to evaluate the quality of the resulting models. However, if the different methods are successfully modelling the true underlying shape variation, the resulting models should be similar. If two different techniques lead to similar models, it suggests that they are indeed approximating the true shape change. In this paper we explore a method of comparing statistical shape models by evaluating the Bhattacharya overlap between their implied shape distributions. We apply the technique to investigate the similarity of three models of the same 3D dataset constructed using different methods. [ABSTRACT FROM AUTHOR]

Rician noise introduces a bias into MRI measurements that can have a significant impact on the shapes and orientations of tensors in diffusion tensor magnetic resonance images. This is less of a problem in structural MRI, because this bias is signal dependent and it does not seriously impair tissue identification or clinical diagnoses. However, diffusion imaging is used extensively for quantitative evaluations, and the tensors used in those evaluations are biased in ways that depend on orientation and signal levels. This paper presents a strategy for filtering diffusion tensor magnetic resonance images that addresses these issues. The method is a maximum a posteriori estimation technique that operates directly on the diffusion weighted images and accounts for the biases introduced by Rician noise. We account for Rician noise through a data likelihood term that is combined with a spatial smoothing prior. The method compares favorably with several other approaches from the literature, including methods that filter diffusion weighted imagery and those that operate directly on the diffusion tensors. [ABSTRACT FROM AUTHOR]

This paper presents results of a pilot study evaluating the efficacy of robotic assistance using novel steerable electrode arrays for cochlear implant surgery. The current surgical setup of cochlear implant surgery is briefly reviewed and its limitations are highlighted. In an effort to reduce trauma to the structure of the cochlea, the kinematics and path planning for novel cochlear steerable electrodes are developed to minimize the interaction forces between the electrode and the cochlea. An experimental robotic system is used to compare the electrode insertion forces of steerable implants with those of non-steerable electrodes. The results of these experiments show about 70% reduction in the insertion forces when steerable electrodes are used with our proposed path planning and control. A distance metric explaining this reduction in the insertion force is defined and experimentally validated. Although this is only a preliminary study, we believe that these results provide a strong indication to the potential of robot-assisted cochlear implant surgery to provide a significant reduction in trauma rates during cochlear implant surgery. [ABSTRACT FROM AUTHOR]

Three dimensional medial paths or curve skeletons ( ) are an essential component of any virtual endoscopy (VE) system, because they serve as flight paths for a virtual camera to navigate the human organ and to examine its internal structures. In this paper, we propose a novel framework for computing flight paths of tubular structures for VE using partial differential equation (PDE). The method works in two passes. In the first pass, the overall topology of the organ is analyzed and its important topological nodes are identified, while in the second pass, the actual flight paths are computed by tracking them starting from each identified node. The proposed framework is robust, fully automatic, computationally efficient, and computes that are centered, connected, thin, and less sensitive to boundary noise. We have extensively validated the robustness of the proposed method both quantitatively and qualitatively against several synthetic phantoms and clinical datasets. [ABSTRACT FROM AUTHOR]