Showing papers in "Medical Image Analysis in 2004"
••
TL;DR: A framework for automatic brain tumor segmentation from MR images that makes use of the robust estimates of the location and dispersion of the normal brain tissue intensity clusters to determine the intensity properties of the different tissue types.
615 citations
••
TL;DR: An automatic atlas-based segmentation algorithm for 4D cardiac MR images is proposed based on the 4D extension of the expectation maximisation (EM) algorithm that incorporates spatial and temporal contextual information by using 4D Markov Random Fields.
284 citations
••
TL;DR: A method to register a preoperative MR volume to a sparse set of intraoperative ultrasound slices to aid needle placement during thermal ablation of liver metastases to allow the transfer of information from preoperative modalities to intraoperative abortion images.
265 citations
••
TL;DR: A fully automated deformable model technique for myocardium segmentation in 3D MRI is presented and a prior parametric spatially varying feature model is established by classification of grey value surface profiles.
260 citations
••
TL;DR: The results strongly suggest that the normalized hippocampal shape of the schizophrenic group is different from the control group, most significantly as a deformation difference in the tail region.
231 citations
••
TL;DR: This paper proposes a principled method for evaluating design choices and choosing parameter values and demonstrates the method through a performance analysis of a nonaffine registration algorithm for 3D images and aRegistration algorithm for 2D cortical surfaces.
221 citations
••
TL;DR: A new 3-D statistical shape model of the heart consisting of atria, ventricles and epicardium is described, which was constructed by combining information on standard short- and long-axis cardiac MR images.
200 citations
••
TL;DR: Overall, the experiments clearly demonstrate that deformations of the brain surface and deeper brain structures are uncorrelated.
161 citations
••
TL;DR: Extensions which improve the performance of the shape-based deformable active contour model presented earlier in [IEEE Conf. Comput. Vision Pattern Recog. 1 (2001) 463] for medical image segmentation are presented.
157 citations
••
TL;DR: This work defines a maximum a posteriori (MAP) estimation model using the joint prior information of the object shape and the image gray levels to realize image segmentation and finds the algorithm to be robust to noise and able to handle multidimensional data, while able to avoid the need for explicit point correspondences during the training phase.
133 citations
••
TL;DR: This method for automated WML segmentation is applicable to lesions of different sizes and shapes, and reaches an accuracy that is comparable to existing methods for multiple sclerosis lesion segmentation, suitable for detection of WMLs in large and longitudinal population studies.
••
TL;DR: This work creates and validate dynamic models of the heart and its components and finds that with the appropriate choice of similarity metric, the algorithm extracts the motion of the epicardial surface in CT images, or of the myocardium, right atrium, right ventricle, aorta, left atrium
••
TL;DR: A new tool for 3D segmentation that addresses problems by computing level-set surface models at interactive rates and the combination of these interactive tools enables users to produce good, reliable segmentations is described.
••
TL;DR: In this paper, a model-based approach to interactive segmentation of abdominal aortic aneurysms from CTA data is presented, in which a shape model of the contours in two adjacent image slices is progressively fitted to the entire volume.
••
TL;DR: This work developed a variety of 3D editing tools that can be used to correct or improve results of initial automatic segmentation procedures, demonstrating the superiority of the 3D approach over the time-consuming slice-by-slice editing of 3d datasets, which is still widely used in medical image processing today.
••
TL;DR: An algorithm that uses a priori information about the nature of imaged objects in order to adapt the regularization of the deformations and a robustness improvement that gives higher weight to those points in images that contain more information is presented.
••
TL;DR: It is shown that anisotropic diffusion is a convenient framework to implement the restored direction as a prior to drive the regularization process in a way that preserves discontinuities and respects the local coherence of the magnitude map.
••
TL;DR: A Win32 program is developed which permits the convenient and fast application of standardized anatomy to individual brains which potentially contain tumors and the nonrigid approach is more precise than the conventional piecewise linear matching.
••
TL;DR: This paper presents a novel algorithm for extracting and visualizing the fiber tracts in the CNS, specifically in the brain, through a data smoothing phase and a fiber tract mapping phase.
••
TL;DR: Two methods that map each hemisphere of the cortex to a portion of a sphere in a standard way are described that are likely to be used in automatic labelling of segmented sulcal regions.
••
TL;DR: These invariants are used to find some correlates of handedness and sex among the shapes of 116 different cortical sulci automatically identified in each of 142 brains of the ICBM database.
••
TL;DR: A statistical predictive model was developed to optimize the needle biopsy sites, by maximizing the probability of detecting cancer, in a statistical atlas of spatial distribution of prostate cancer from a large patient cohort.
••
TL;DR: This work proposes to improve upon the latter approach by adaptively placing control points where they are needed in warping transforms, using local estimates of mutual information and entropy to identify local regions requiring additional DOF.
••
TL;DR: The methods presented in this paper are evaluated on synthetic images of branching tubular objects as well as on blood vessels in head MR angiogram data and show impressive resistance to noise and the ability to detect branches spanning a variety of widths and branching angles.
••
TL;DR: A new algorithm for 3D medical image segmentation based on minimizing a global energy defined from a learned non-parametric estimation of the statistics of the region to be segmented is presented.
••
TL;DR: The ZBS algorithm provided segmentation accuracies similar to that obtained with the vessel enhancement filter, and was notably better than the filter based segmentation for aneurysms where the assumptions of the filter were violated.
••
TL;DR: The idea is to provide surgeons with a tool which can teach them the correlation between deformation and applied force, and the experimental results are promising even though the used force feedback device is somewhat constraining the realism.
••
TL;DR: Accuracies of a point-based and an intensity-based fluoroscopic methods of assessing patella tracking were determined by comparing the pattern of patellar motion with respect to orientation and translation with the patterns measured using Roentgen stereophotogrammetric analysis in three cadaver knee specimens.
••
TL;DR: The IB quantization provides a consistent representation of the data, allowing for an easy interpretation and comparison of datasets, and is principled through an information theoretic formulation, which is relevant in many situations.
••
TL;DR: This study proposes a method that is based on the Iterative Closest Point algorithm and a pre-computed closest point map obtained with a slight modification of the fast marching method proposed by Sethian and shows that on these data sets this registration method leads to accuracy numbers that are comparable to those obtained with voxel-based methods.