We propose a new similarity measure for atlas-to-image matching in the context of atlas-driven intensity-based tissue classification of MR brain images. the new measure directly matches probabilistic tissue class labe...
详细信息
ISBN:
(纸本)3540229760
We propose a new similarity measure for atlas-to-image matching in the context of atlas-driven intensity-based tissue classification of MR brain images. the new measure directly matches probabilistic tissue class labels to study image intensities, without need. for an atlas MR template. Non-rigid warping of the atlas to the study image is achieved by free-form deformation using a viscous fluid regularizer such that mutual information (MI) between atlas class labels and study image intensities is maximized. the new registration measure is compared withthe standard approach of maximization of MI between atlas and study images intensities. Our results show that the proposed registration scheme indeed improves segmentation quality, in the sense that the segmentations obtained using the atlas warped withthe proposed non-rigid registration scheme better explain the study image data than the segmentations obtained withthe atlas warped using standard intensity-based MI.
An efficient clinical image segmentation framework is proposed by combining a pattern classifier, hierarchical and coupled level sets. the framework has two stages: training and segmentation. During training, first, r...
详细信息
ISBN:
(纸本)3540229760
An efficient clinical image segmentation framework is proposed by combining a pattern classifier, hierarchical and coupled level sets. the framework has two stages: training and segmentation. During training, first, representative images are segmented using hierarchical level set. then the results are used to train a pattern classifier. During segmentation, first the image is classified by the trained classifier, and then coupled level set functions are used to further segment to get correct boundaries. the classifier provides an initial contour which is close to correct boundary for coupled level sets. this speeds up the convergence of coupled level sets. A hybrid coupled level set method which combines minimal variance functional and Laplacian edge detector is proposed. Experimental results show that by the proposed framework, we achieve accurate boundaries, with much faster convergence. this robust autonomous framework works efficiently in a clinical setting where there are limited types of medicalimages.
For minimally invasive curettage of femoral head osteonecrosis, we have developed a novel expandable blade tool which can be introduced into the femoral head through the subtrochanteric route under navigation guidance...
详细信息
ISBN:
(纸本)3540229779
For minimally invasive curettage of femoral head osteonecrosis, we have developed a novel expandable blade tool which can be introduced into the femoral head through the subtrochanteric route under navigation guidance. In this study, we evaluated the effectiveness and feasibility of this tool in comparison withthe Cebotome, a conventional bone cutter. A target area in the femoral head of a Sawbone femur model was curetted with each tool through the subtrochanteric route under navigation guidance. the volume of the curetted necrotic lesion was significantly larger and the procedure time was significantly shorter withthis tool than withthe Cebotome. the compressive strength of the femoral head curetted withthis tool and filled with hydroxyapatite blocks was comparable to that of the intact one. this expandable blade tool can be a suggestion for more effective and feasible curettage of necrotic lesions in femoral head osteonecrosis than conventional bone cutters.
this paper presents an improved method for the detection of "significant" low-level objects in medicalimages. the method overcomes topological problems where multiple redundant saddle points are detected in...
this paper presents an improved method for the detection of "significant" low-level objects in medicalimages. the method overcomes topological problems where multiple redundant saddle points are detected in digital images. Information derived from watershed regions is used to select and refine saddle points in the discrete domain and to construct the watersheds and watercourses (ridges and valleys). We also demonstrate an improved method of pruning the tessellation by which to define low level objects in zero order images. the algorithm was applied on a set of medicalimages with promising results. Evaluation was based on theoretical analysis and human observer experiments. (C) 2004 Elsevier B.V. All rights reserved.
Maxillofacial surgery simulation and planning is an extremely challenging area of research combining medicalimagery, computer graphics and mathematical modelling. In maxillofacial surgery abnormalities of the skeleto...
详细信息
ISBN:
(纸本)3540229779
Maxillofacial surgery simulation and planning is an extremely challenging area of research combining medicalimagery, computer graphics and mathematical modelling. In maxillofacial surgery abnormalities of the skeleton of the head are treat by skull remodelling. Since the human face plays a key role in interpersonal relationships, people are very sensitive to changes to their outlook. therefore planning of the operation and reliable prediction of the facial changes are very important. Recently, the use of 3D image-based surgery planning systems is more and more accepted in this field. Although the bone-related planning concepts and methods are maturing, prediction of soft tissue deformation needs further fundamental research. In this paper we present a soft tissue simulator that uses a fast tetrahedral mass spring system to calculate soft tissue deformation due to bone displacement in a short time interval. Results of soft tissue simulation for patients who had a maxillofacial surgery are shown. Finally we truly validated the simulation results and compared our method with others.
Multi-subject non-rigid registration algorithms using dense deformation fields often encounter cases where the transformation to be estimated has a large spatial variability. In these cases, linear stationary regulari...
详细信息
Multi-subject non-rigid registration algorithms using dense deformation fields often encounter cases where the transformation to be estimated has a large spatial variability. In these cases, linear stationary regularization methods are not sufficient. In this paper, we present an algorithm that uses a priori information about the nature of imaged objects in order to adapt the regularization of the deformations. We also present a robustness improvement that gives higher weight to those points in images that contain more information. Finally, a fast parallel implementation using networked personal computers is presented. In order to improve the usability of the parallel software by a clinical user, we have implemented it as a grid service that can be controlled by a graphics workstation embedded in the clinical environment. Results on inter-subject pairs of images show that our method can take into account the large variability of most brain structures. the registration time for images of size 256 x 256 x 124 is 5 min on 15 standard PCs. A comparison of our non-stationary visco-elastic smoothing versus solely elastic or fluid regularizations shows that our algorithm converges faster towards a more optimal solution in terms of accuracy and transformation regularity. (C) 2004 Elsevier B.V. All rights reserved.
We formulate the problem of finding a statistical representation of shape as a best basis selection problem in which the goal is to choose the basis for optimal shape representation from a very large library of bases....
详细信息
ISBN:
(纸本)3540229760
We formulate the problem of finding a statistical representation of shape as a best basis selection problem in which the goal is to choose the basis for optimal shape representation from a very large library of bases. In this work, our emphasis is on applying this basis selection framework using the wavelet packets library to estimate the probability density function of a class of shapes from a limited number of training samples. Wavelet packets offer a large number of complete orthonormal bases which can be searched for the basis that optimally allows the analysis of shape details at different scales. the estimated statistical shape distribution is capable of generalizing to shape examples not encountered during training, while still being specific to the modeled class of shapes. Using contours from two-dimensional MRI images of the corpus callosum, we demonstrate the ability of this approach to approximate the probability distribution of the modeled shapes, even with a few training samples.
作者:
Shen, DGUniv Penn
Sch Biomed Image Anal Dept Radiol Philadelphia PA 19104 USA
We previously presented a HAMMER image registration algorithm that demonstrated high accuracy in superposition of images from different individual brains. However, the HAMMER registration algorithm requires presegment...
详细信息
ISBN:
(纸本)3540229760
We previously presented a HAMMER image registration algorithm that demonstrated high accuracy in superposition of images from different individual brains. However, the HAMMER registration algorithm requires presegmentation of brain tissues, since the attribute vectors used to hierarchically match the corresponding pairs of points are defined from the segmented images. In many applications, the segmentation of tissues might be difficult, unreliable or even impossible to complete, which potentially limits the use of the HAMMER algorithm in more generalized applications. To overcome this limitation, we use local spatial intensity histograms to design a new type of attribute vector for each point in an intensity image. the histogram-based attribute vector is rotationally invariant, and more importantly it captures spatial information by integrating a number of local histograms that are calculated from multi-resolution images. the new attribute vectors are able to determine corresponding points across individual images. therefore, by hierarchically matching new attribute vectors, the proposed registration method performs as successfully as the previous HAMMER algorithm did in registering MR brain images, while providing more general applications in registering images of other organs. Experimental results show good performance of the proposed method in registering MR brain images and CT pelvis images.
A generalized image model (GIM) is presented. images are represented as sets of four-dimensional (4D) sites combining position and intensity information, as well as their associated uncertainty and joint variation. th...
详细信息
A generalized image model (GIM) is presented. images are represented as sets of four-dimensional (4D) sites combining position and intensity information, as well as their associated uncertainty and joint variation. this model seamlessly allows for the representation of bothimages and statistical models (such as those used for classification of normal/abnormal anatomy and for interpatient registration), as well as other representations such as landmarks or meshes. A GIM-based registration method aimed at the construction and application of statistical models of images is proposed. A procedure based on the iterative closest point (ICP) algorithm is modified to deal with features other than position and to integrate statistical information. Furthermore, we modify the ICP framework by using a Kalman filter to efficiently compute the transformation. the initialization and update of the statistical model are also described. Preliminary results show the feasibility of the approach and its potentialities. (C) 2004 Elsevier B.V. All rights reserved.
the purpose of this study is to develop an image-guided decision support system that assists decision-making in clinical differential diagnosis of pulmonary nodules. this approach retrieves and displays nodules that e...
详细信息
ISBN:
(纸本)3540229779
the purpose of this study is to develop an image-guided decision support system that assists decision-making in clinical differential diagnosis of pulmonary nodules. this approach retrieves and displays nodules that exhibit morphological and internal profiles consistent to the nodule in question. It uses a three-dimensional (3-D) CT image database of pulmonary nodules for which diagnosis is known. In order to build the system, there are following issues that should be solved, (1) to categorize the nodule database with respect to morphological and internal features, (2) to quickly search nodule images similar to an indeterminate nodule from a large database, and (3) to reveal malignancy likelihood computed by using similar nodule images. Especially, the first problem influences the design of other issues. the successful categorization of nodule pattern might lead physicians to find important cues that characterize benign and malignant nodules. this paper focuses on an approach to categorize the nodule database with respect to nodule shape and CT density patterns inside nodule.
暂无评论