Direct volume visualization has recently gained importance as a tool for the analysis of intracranial aneurysms focused on therapy planning. CT-angiography (CTA) intensities are mapped to color and opacity values by s...
详细信息
A robust and efficient method for the segmentation of 3D structures in CT and MR images is presented. The proposed method is based on 3D ray propagation by mean shift analysis with a smoothness constraint. Specificall...
详细信息
ISBN:
(数字)9783540457862
ISBN:
(纸本)3540442243
A robust and efficient method for the segmentation of 3D structures in CT and MR images is presented. The proposed method is based on 3D ray propagation by mean shift analysis with a smoothness constraint. Specifically, ray propagation is used to guide an evolving surface due to its computational efficiency. In addition, non-parametric analysis and shape priors are incorporated to the proposed technique for robust convergence. Several examples are depicted to illustrate its effectiveness.
A novel method to use model libraries in segmentation is introduced. Using similarity measures one model from a model library is selected. This model is then used in model-based segmentation. The proposed method is si...
详细信息
ISBN:
(数字)9783540457862
ISBN:
(纸本)3540442243
A novel method to use model libraries in segmentation is introduced. Using similarity measures one model from a model library is selected. This model is then used in model-based segmentation. The proposed method is simple, straightforward and fast. Various similarity measures, both voxel and edge measures, were examined. Two different segmentation methods were used for validating the functionality of the proposed procedure. Results show that a statistically significant improvement in segmentation accuracy was achieved in each study case.
This paper describes an example-based assisting approach for classifying pulmonary nodules in 3-D thoracic CT images. In this approach the internal and surrounding structures of the nodule are characterized by the dis...
详细信息
ISBN:
(数字)9783540457862
ISBN:
(纸本)3540442243
This paper describes an example-based assisting approach for classifying pulmonary nodules in 3-D thoracic CT images. In this approach the internal and surrounding structures of the nodule are characterized by the distribution pattern of CT density and 3-D curvature indexes. Each nodule is represented by means of a joint histogram using the distance value from the nodule center. When given an indeterminate nodule image, the images of lesions with known diagnoses (e.g. malignant ***) are retrieved from a 3-D nodule image database. The malignant likelihood of the indeterminate case is estimated by the difference between the representation patterns of the indeterminate case and the retrieved lesions. In the present study, we adopt the Mahalanobis distance as the difference measure and then, explore the feasibility of the classification based on patterns of similar lesion images.
A new method is presented to assist the clinician in planning a interventional procedure while the patient is already on the catheterization table. Based on several ECG-selected projections from a rotational X-ray acq...
详细信息
ISBN:
(数字)9783540457862
ISBN:
(纸本)3540442243
A new method is presented to assist the clinician in planning a interventional procedure while the patient is already on the catheterization table. Based on several ECG-selected projections from a rotational X-ray acquisition, both a volumetric cone-beam reconstruction of the coronary tree as well as a three-dimensional surface model of the vessel segment of interest are generated. The proposed method provides the clinician with the length and diameters of the vessel segment of interest as well as with an 'optimal working view'. In this view, the gantry is positioned such that the vessel segment of interest is the least foreshortened and vessel overlap is minimized during the entire heart cycle. Examples on a phantom object and on patient data demonstrate the accuracy and feasibility of the approach.
This paper presents a robotic vision system that automatically retrieves and positions surgical instruments in the robotized laparoscopic surgical environment. The goal of the automated task is to bring the instrument...
详细信息
ISBN:
(数字)9783540457862
ISBN:
(纸本)3540442243
This paper presents a robotic vision system that automatically retrieves and positions surgical instruments in the robotized laparoscopic surgical environment. The goal of the automated task is to bring the instrument from an unknown or hidden position to a desired location specified by the surgeon on the endoscopic image. To achieve this task, a special instrument-holder is designed that projects laser dot patterns onto the organ surface which are seen on the endoscopic images. Then, the surgical instrument positioning is done using an automatic visual servoing from the endoscopic image. Our approach is successfully validated in a real surgical environment by performing experiments on living pigs in the surgical training room of IRCAD.
Thickness of the cerebral cortex may provide valuable information about normal and abnormal neuroanatomy. For accurate cortical thickness measurements in brain MRI, precise segmentation of the grey matter border is ne...
详细信息
ISBN:
(数字)9783540457862
ISBN:
(纸本)3540442243
Thickness of the cerebral cortex may provide valuable information about normal and abnormal neuroanatomy. For accurate cortical thickness measurements in brain MRI, precise segmentation of the grey matter border is necessary. In this paper we specifically address the problem of extracting the deep cortical folds or sulci, which can be difficult to resolve or totally obscured due to limited MRI resolution and contrast. We propose a method that iteratively solves Laplace's equation for adjacent sub-layers of the cortex. This approach preserves the laminar structure of the cortex and provides clear definition of deep sulci. The implementation is computationally efficient. We present inter-subject and intra-subject results that are consistent with the literature.
Using 3D rotational X-ray angiography (3DRA), 3D information of the vasculature can be obtained. prior to endovascular interventions. However, during interventions, the radiologist has to rely on fluoroscopy images to...
详细信息
ISBN:
(数字)9783540457862
ISBN:
(纸本)3540442243
Using 3D rotational X-ray angiography (3DRA), 3D information of the vasculature can be obtained. prior to endovascular interventions. However, during interventions, the radiologist has to rely on fluoroscopy images to manipulate the guide wire. In order to take full advantage of the 3D information from 3DRA data during endovascular interventions, a method is presented which yields an integrated display of the position of the guide wire and vasculature in 3D. The method relies on an automated method developed by the authors that simultaneously tracks the guide wire in biplane fluoroscopy images. Based on the known geometry, the 3D guide wire position is reconstructed and visualized in the 3D coordinate system of the vasculature. The method is illustrated in an intracranial anthropomorphic vascular phantom.
In this paper we present an integrated image registration algorithm for segmenting the heart muscle, the myocardium (MC). A sequence of magnetic resonance (MR) images of heart are acquired after injection of a contras...
详细信息
ISBN:
(数字)9783540457862
ISBN:
(纸本)3540442243
In this paper we present an integrated image registration algorithm for segmenting the heart muscle, the myocardium (MC). A sequence of magnetic resonance (MR) images of heart are acquired after injection of a contrast agent. An analysis of the perfusion of the contrast agent into myocardium is utilized to study its viability. Such a study requires segmentation of MC in each of the images acquired which is a difficult task due to rapidly changing contrast image the images. In this paper we present an information theoretic registration framework which integrates two channels of information, the pixel intensities and the local gradient information, to reliably and accurately segment the myocardium. In our framework, the physician hand draws contours representing the inner (the endocardium) and the outer (the epicardium) boundaries of the myocardium. These hand drawn contours are then propagated to the other images in the sequence of images acquired to segment the MC.
We propose anew guidance paradigm for computer-assisted orthopaedic surgery, based on nonrigid registration of a patient to a standard atlas model. Such a method would save costs and time compared to CT-based methods,...
详细信息
ISBN:
(数字)9783540457862
ISBN:
(纸本)3540442243
We propose anew guidance paradigm for computer-assisted orthopaedic surgery, based on nonrigid registration of a patient to a standard atlas model. Such a method would save costs and time compared to CT-based methods, while being more reliable than current imageless navigation tools. Here, we consider application of this paradigm to knee arthroplasty. This work reports laboratory results of assessing the simplest nonrigid registration method, which is an affine transformation. Results from CT scans of 15 patients show the method is more repeatable than the standard mechanical guide rods in the frontal plane. The affine transformations also detected a potential difference between osteoarthritic patients and the normal population, which may have implications for the implantation of artificial knee components.
暂无评论